3DV20
* *3D Imaging, Modeling, Processing, Visualization and Transmission
* 3D Deep Learning for Biological Function Prediction from Physical Fields
* 3D-Aware Ellipse Prediction for Object-Based Camera Pose Estimation
* Adiabatic Quantum Graph Matching with Permutation Matrix Constraints
* Adversarial Self-Supervised Scene Flow Estimation
* Benchmarking Image Retrieval for Visual Localization
* Better Patch Stitching for Parametric Surface Reconstruction
* BP-MVSNet: Belief-Propagation-Layers for Multi-View-Stereo
* Class-unbalanced domain adaptation for object detection via dynamic weighting mechanism
* COALESCE: Component Assembly by Learning to Synthesize Connections
* Compression and Completion of Animated Point Clouds using Topological Properties of the Manifold
* Convolutional Autoencoders for Human Motion Infilling
* Correspondence Matrices are Underrated
* Cycle-Consistent Generative Rendering for 2D-3D Modality Translation
* Deep Depth Estimation on 360° Images with a Double Quaternion Loss
* Deep Learning Based Single-Photon 3D Imaging with Multiple Returns
* Deep LiDAR localization using optical flow sensor-map correspondences
* Deep NRSfM++: Towards Unsupervised 2D-3D Lifting in the Wild
* Deep Sketch-Based Modeling: Tips and Tricks
* Deep SVBRDF Estimation on Real Materials
* DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction
* Dense Point Diffusion for 3D Object Detection
* Depth Completion Using a View-constrained Deep Prior
* Depthwise Separable Temporal Convolutional Network for Action Segmentation
* Differential Photometric Consistency
* Distributed Photometric Bundle Adjustment
* Divide et Impera Approach for 3D Shape Reconstruction from Multiple Views, A
* Do End-to-end Stereo Algorithms Under-utilize Information?
* Do We Need Depth in State-Of-The-Art Face Authentication?
* DynOcc: Learning Single-View Depth from Dynamic Occlusion Cues
* Efficient Scene Compression for Visual-based Localization
* Error Bounds of Projection Models in Weakly Supervised 3D Human Pose Estimation
* Fast Discontinuity-Aware Subpixel Correspondence in Structured Light
* Fast Simultaneous Gravitational Alignment of Multiple Point Sets
* FC-vSLAM: Integrating Feature Credibility in Visual SLAM
* GAMesh: Guided and Augmented Meshing for Deep Point Networks
* Generalized Pose-and-Scale Estimation using 4-Point Congruence Constraints
* GIF: Generative Interpretable Faces
* Global Context Aware Convolutions for 3D Point Cloud Understanding
* Graphite: Graph-Induced Feature Extraction for Point Cloud Registration
* Grasping Field: Learning Implicit Representations for Human Grasps
* High-Dynamic-Range Lighting Estimation From Face Portraits
* HyperSLAM: A Generic and Modular Approach to Sensor Fusion and Simultaneous Localization And Mapping in Continuous-Time
* Improved Modeling of 3D Shapes with Multi-view Depth Maps
* Improving Structure from Motion with Reliable Resectioning
* Instant recovery of shape from spectrum via latent space connections
* Intrinsic Autoencoders for Joint Deferred Neural Rendering and Intrinsic Image Decomposition
* Intrinsic Dynamic Shape Prior for Dense Non-Rigid Structure from Motion
* Introducing Pose Consistency and Warp-Alignment for Self-Supervised 6D Object Pose Estimation in Color Images
* Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level optimization
* KAPLAN: A 3D Point Descriptor for Shape Completion
* KeystoneDepth: History in 3D
* LCD: Line Clustering and Description for Place Recognition
* Learning 3D Faces from Photo-Realistic Facial Synthesis
* Learning Distribution Independent Latent Representation for 3D Face Disentanglement
* Learning Implicit Surface Light Fields
* Learning Monocular Dense Depth from Events
* Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks
* Learning to Guide Local Feature Matches
* Learning to Infer Semantic Parameters for 3D Shape Editing
* Learning Wasserstein Isometric Embedding for Point Clouds
* LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment
* Linear Approach to Absolute Pose Estimation for Light Fields, A
* LM-Reloc: Levenberg-Marquardt Based Direct Visual Relocalization
* LMSCNet: Lightweight Multiscale 3D Semantic Completion
* Localising In Complex Scenes Using Balanced Adversarial Adaptation
* MaskNet: A Fully-Convolutional Network to Estimate Inlier Points
* Matching-space Stereo Networks for Cross-domain Generalization
* MonoClothCap: Towards Temporally Coherent Clothing Capture from Monocular RGB Video
* Motion Annotation Programs: A Scalable Approach to Annotating Kinematic Articulations in Large 3D Shape Collections
* Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion
* New Distributional Ranking Loss With Uncertainty: Illustrated in Relative Depth Estimation, A
* Nighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative Regions
* NodeSLAM: Neural Object Descriptors for Multi-View Shape Reconstruction
* Novel Depth from Defocus Framework Based on a Thick Lens Camera Model, A
* PanoNet3D: Combining Semantic and Geometric Understanding for LiDAR Point Cloud Detection
* PeeledHuman: Robust Shape Representation for Textured 3D Human Body Reconstruction
* PLACE: Proximity Learning of Articulation and Contact in 3D Environments
* PoseNet3D: Learning Temporally Consistent 3D Human Pose via Knowledge Distillation
* Precomputed Radiance Transfer for Reflectance and Lighting Estimation
* Progressive Conditional Generative Adversarial Network for Generating Dense and Colored 3D Point Clouds, A
* RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
* Recalibration of Neural Networks for Point Cloud Analysis
* Reducing Drift in Structure From Motion Using Extended Features
* Refractive Multi-view Stereo
* Registration Loss Learning for Deep Probabilistic Point Set Registration
* Restoration of Motion Blur in Time-of-Flight Depth Image Using Data Alignment
* Rethinking PointNet Embedding for Faster and Compact Model
* RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty
* RocNet: Recursive Octree Network for Efficient 3D Deep Representation
* Rotation-Invariant Point Convolution With Multiple Equivariant Alignments.
* RotPredictor: Unsupervised Canonical Viewpoint Learning for Point Cloud Classification
* Saliency Guided Subdivision for Single-View Mesh Reconstruction
* Scalable Point Cloud-based Reconstruction with Local Implicit Functions
* Scene Flow from Point Clouds with or without Learning
* SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion
* Screen-space Regularization on Differentiable Rasterization
* Self-Supervised 2D Image to 3D Shape Translation with Disentangled Representations
* Self-supervised Depth Denoising Using Lower- and Higher-quality RGB-D sensors
* Self-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion
* Self-Supervised Learning of Point Clouds via Orientation Estimation
* Semantic Deep Face Models
* Semantic Implicit Neural Scene Representations With Semi-Supervised Training
* SF-UDA3D: Source-Free Unsupervised Domain Adaptation for LiDAR-Based 3D Object Detection
* Shape from Tracing: Towards Reconstructing 3D Object Geometry and SVBRDF Material from Images via Differentiable Path Tracing
* Simulated Annealing for 3D Shape Correspondence
* Smart Time-Multiplexing of Quads Solves the Multicamera Interference Problem
* SMPLy Benchmarking 3D Human Pose Estimation in the Wild
* Spatial Attention Improves Iterative 6D Object Pose Estimation
* Style Transfer for Keypoint Matching Under Adverse Conditions
* Temporal LiDAR Frame Prediction for Autonomous Driving
* Time Shifted IMU Preintegration for Temporal Calibration in Incremental Visual-Inertial Initialization
* Torch-Points3D: A Modular Multi-Task Framework for Reproducible Deep Learning on 3D Point Clouds
* Towards 3D VR-Sketch to 3D Shape Retrieval
* Towards a MEMS-based Adaptive LIDAR
* Towards Geometry Guided Neural Relighting with Flash Photography
* Transformer-Based Network for Dynamic Hand Gesture Recognition, A
* TRANSPR: Transparency Ray-Accumulating Neural 3D Scene Point Renderer
* Two-Stage Relation Constraint for Semantic Segmentation of Point Clouds
* Underwater Scene Recovery Using Wavelength-Dependent Refraction of Light
* Unsupervised Dense Shape Correspondence using Heat Kernels
* Using Image Sequences for Long-Term Visual Localization
* VIPNet: A Fast and Accurate Single-View Volumetric Reconstruction by Learning Sparse Implicit Point Guidance
* Visualizing Spectral Bundle Adjustment Uncertainty
124 for 3DV20
3DV21
* *3D Imaging, Modeling, Processing, Visualization and Transmission
* 3D Lip Event Detection via Interframe Motion Divergence at Multiple Temporal Resolutions
* 3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning
* 3D reconstruction of insects: an improved multifocus stacking and an evaluation of learning-based MVS approaches
* 3D Reconstruction of Novel Object Shapes from Single Images
* 3D-MetaConNet: Meta-learning for 3D Shape Classification and Segmentation
* 3DVNet: Multi-View Depth Prediction and Volumetric Refinement
* 4D Human Body Capture from Egocentric Video via 3D Scene Grounding
* AIR-Nets: An Attention-Based Framework for Locally Conditioned Implicit Representations
* Algebraic Constraint for Preserving Convexity of Planar Homography
* Attacking Image Classifiers To Generate 3D Textures
* Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation
* Body Size and Depth Disambiguation in Multi-Person Reconstruction from Single Images
* CAMPARI: Camera-Aware Decomposed Generative Neural Radiance Fields
* Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation
* Collaborative Regression of Expressive Bodies using Moderation
* Conflicts between Likelihood and Knowledge Distillation in Task Incremental Learning for 3D Object Detection
* Convex Joint Graph Matching and Clustering via Semidefinite Relaxations
* Curiosity-driven 3D Object Detection Without Labels
* Dance In the Wild: Monocular Human Animation with Neural Dynamic Appearance Synthesis
* Data-Driven 3D Reconstruction of Dressed Humans From Sparse Views
* Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks, A
* Deep Multi-View Stereo Gone Wild
* Deep Physics-aware Inference of Cloth Deformation for Monocular Human Performance Capture
* Deep Regression on Manifolds: A 3D Rotation Case Study
* DeepBBS: Deep Best Buddies for Point Cloud Registration
* DiffSDFSim: Differentiable Rigid-Body Dynamics With Implicit Shapes
* Digging Into Self-Supervised Learning of Feature Descriptors
* Direct Dense Pose Estimation
* Direct-PoseNet: Absolute Pose Regression with Photometric Consistency
* DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
* DPFM: Deep Partial Functional Maps
* DSP-SLAM: Object Oriented SLAM with Deep Shape Priors
* Dual Geometric Graph Network (DG2N) Iterative Network for Deformable Shape Alignment
* Dual Mesh Convolutional Networks for Human Shape Correspondence
* DurLAR: A High-Fidelity 128-Channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-Modal Autonomous Driving Applications
* Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras
* E-RAFT: Dense Optical Flow from Event Cameras
* Efficiently Distributed Watertight Surface Reconstruction
* EgoGlass: Egocentric-View Human Pose Estimation From an Eyeglass Frame
* ESL: Event-based Structured Light
* Event Guided Depth Sensing
* Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation
* Exploring Versatile Prior for Human Motion via Motion Frequency Guidance
* FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling
* Fine-Grained VR Sketching: Dataset and Insights.
* FLYBO: A Unified Benchmark Environment for Autonomous Flying Robots
* Fusing Posture and Position Representations for Point Cloud-Based Hand Gesture Recognition
* GASCN: Graph Attention Shape Completion Network
* GCSR: Gray Code Super-Resolution 3D Scanning
* Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
* GenIcoNet: Generative Icosahedral Mesh Convolutional Network
* Geometric Adversarial Attacks and Defenses on 3D Point Clouds
* Globally Optimal Multi-Scale Monocular Hand-Eye Calibration Using Dual Quaternions
* Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction
* High Fidelity 3D Reconstructions with Limited Physical Views
* Human Performance Capture from Monocular Video in the Wild
* HumanGAN: A Generative Model of Human Images
* HyNet: 3D Segmentation Using Hybrid Graph Networks
* Image Stitching with Locally Shared Rotation Axis
* Intention-based Long-Term Human Motion Anticipation
* Investigating Attention Mechanism in 3D Point Cloud Object Detection
* It Is All In The Weights: Robust Rotation Averaging Revisited
* Joint 3D Human Shape Recovery and Pose Estimation from a Single Image with Bilayer Graph
* KAMA: 3D Keypoint Aware Body Mesh Articulation
* L2D2: Learnable Line Detector and Descriptor
* LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies
* Learning 3D Semantic Segmentation with only 2D Image Supervision
* Learning Iterative Robust Transformation Synchronization
* Learning Local Recurrent Models for Human Mesh Recovery
* Learning Residue-Aware Correlation Filters and Refining Scale Estimates with the GrabCut for Real-Time UAV Tracking
* Learning Scale-Adaptive Representations for Point-Level LiDAR Semantic Segmentation
* Learning To Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation
* Leveraging MoCap Data for Human Mesh Recovery
* Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo
* Lifted Semantic Graph Embedding for Omnidirectional Place Recognition
* MaCal - Macro Lens Calibration and the Focus Stack Camera Model
* Mesh-Based Reconstruction of Dynamic Foam Images Using X-Ray CT
* MeshMVS: Multi-View Stereo Guided Mesh Reconstruction
* Mix3D: Out-of-Context Data Augmentation for 3D Scenes
* Modality-Guided Subnetwork for Salient Object Detection
* Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements
* Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss
* MP-Mono: Monocular 3D Detection Using Multiple Priors for Autonomous Driving
* Multi-Category Mesh Reconstruction From Image Collections
* Multi-scale Space-time Registration of Growing Plants
* NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping
* Neighborhood-based Neural Implicit Reconstruction from Point Clouds
* Neural Disparity Refinement for Arbitrary Resolution Stereo
* Neural Human Deformation Transfer
* NeuralBlox: Real-Time Neural Representation Fusion for Robust Volumetric Mapping
* NeuralDiff: Segmenting 3D objects that move in egocentric videos
* Non-Linear Anisotropic Diffusion for Memory-Efficient Computed Tomography Super-Resolution Reconstruction
* NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis
* NVSS: High-quality Novel View Selfie Synthesis
* Object SLAM-Based Active Mapping and Robotic Grasping
* Occlusion Guided Self-supervised Scene Flow Estimation on 3D Point Clouds
* Open-set 3D Object Detection
* PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation
* Parameterization of Ambiguity in Monocular Depth Prediction
* PhysXNet: A Customizable Approach for Learning Cloth Dynamics on Dressed People
* PLNet: Plane and Line Priors for Unsupervised Indoor Depth Estimation
* Point2FFD: Learning Shape Representations of Simulation-Ready 3D Models for Engineering Design Optimization
* PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation
* PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
* Practical Pose Trajectory Splines With Explicit Regularization
* Projective Urban Texturing
* R4Dyn: Exploring Radar for Self-Supervised Monocular Depth Estimation of Dynamic Scenes
* RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching
* Ray Tracing-Guided Design of Plenoptic Cameras
* RealisticHands: A Hybrid Model for 3D Hand Reconstruction
* Recovering Real-World Reflectance Properties and Shading From HDR Imagery
* RefRec: Pseudo-labels Refinement via Shape Reconstruction for Unsupervised 3D Domain Adaptation
* Representing Shape Collections With Alignment-Aware Linear Models
* Residual Geometric Feature Transform Network for 3D Surface Super-Resolution
* RGBD-Net: Predicting Color and Depth Images for Novel Views Synthesis
* Robust Fitting with Truncated Least Squares: A Bilevel Optimization Approach
* SAFA: Structure Aware Face Animation
* Scalable Cluster-Consistency Statistics for Robust Multi-Object Matching
* SceneFormer: Indoor Scene Generation with Transformers
* Self-Supervised Light Field Depth Estimation Using Epipolar Plane Images
* Self-Supervised Monocular Scene Decomposition and Depth Estimation
* Semi-supervised 3D Object Detection via Temporal Graph Neural Networks
* Shortest Paths in Graphs with Matrix-Valued Edges: Concepts, Algorithm and Application to 3D Multi-Shape Analysis
* SIDER: Single-Image Neural Optimization for Facial Geometric Detail Recovery
* Skeleton-Driven Neural Occupancy Representation for Articulated Hands, A
* Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision
* Spatio-Temporal Human Shape Completion With Implicit Function Networks
* Spatio-temporal Transformer for 3D Human Motion Prediction, A
* Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning
* Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations
* SUPPLE: Extracting Hand Skeleton with Spherical Unwrapping Profiles
* SVMAC: Unsupervised 3D Human Pose Estimation from a Single Image with Single-view-multi-angle Consistency
* Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
* Task-Generic Hierarchical Human Motion Prior using VAEs
* TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering
* Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos
* Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes
* Variational Monocular Depth Estimation for Reliability Prediction
* Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
* VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion
* Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments
142 for 3DV21
3DV22
* *3D Imaging, Modeling, Processing, Visualization and Transmission
* 3inGAN: Learning a 3D Generative Model from Images of a Self-similar Scene
* 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs, The
* ACDet: Attentive Cross-view Fusion for LiDAR-based 3D Object Detection
* Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes
* Any-Shot GIN: Generalizing Implicit Networks for Reconstructing Novel Classes
* Arbitrary Point Cloud Upsampling with Spherical Mixture of Gaussians
* Articulated 3D Human-Object Interactions From RGB Videos: An Empirical Analysis of Approaches and Challenges
* Benchmark and a Baseline for Robust Multi-view Depth Estimation, A
* Benchmarking Pedestrian Odometry: The Brown Pedestrian Odometry Dataset (BPOD)
* Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes
* CADOps-Net: Jointly Learning CAD Operation Types and Steps from Boundary-Representations
* Controllable Radiance Fields for Dynamic Face Synthesis
* Cross-Spectral Neural Radiance Fields
* Cut-and-Paste Object Insertion by Enabling Deep Image Prior for Reshading
* Dimensions of Motion: Monocular Prediction through Flow Subspaces
* Distortion-aware Depth Estimation with Gradient Priors from Panoramas of Indoor Scenes
* Domain Adaptive 3D Pose Augmentation for In-the-Wild Human Mesh Recovery
* Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces
* Efficient Human Pose Estimation via 3D Event Point Cloud
* Fast Gradient Descent for Surface Capture Via Differentiable Rendering
* Flexible Multi-view Multi-modal Imaging System for Outdoor Scenes, A
* GAN2X: Non-Lambertian Inverse Rendering of Image GANs
* Garment Ideation: Iterative View-Aware Sketch-Based Garment Modeling
* gCoRF: Generative Compositional Radiance Fields
* GNPM: Geometric-Aware Neural Parametric Models
* GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction
* Guided Co-Modulated GAN for 360° Field of View Extrapolation
* High-Speed and Low-Latency 3D Sensing with a Parallel-Bus Pattern
* HoW-3D: Holistic 3D Wireframe Perception from a Single Image
* Human Body Measurement Estimation with Adversarial Augmentation
* HVTR: Hybrid Volumetric-Textural Rendering for Human Avatars
* HybridSDF: Combining Deep Implicit Shapes and Geometric Primitives for 3D Shape Representation and Manipulation
* Interactive Sketching of Mannequin Poses
* Keypoint Cascade Voting for Point Cloud Based 6DoF Pose Estimation
* LC-NAS: Latency Constrained Neural Architecture Search for Point Cloud Networks
* Long Term Motion Prediction Using Keyposes
* ManiFlow: Implicitly Representing Manifolds with Normalizing Flows
* MoCapDeform: Monocular 3D Human Motion Capture in Deformable Scenes
* MonoNHR: Monocular Neural Human Renderer
* MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer
* Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations
* Neural Point-based Shape Modeling of Humans in Challenging Clothing
* On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
* OoD-Pose: Camera Pose Regression From Out-of-Distribution Synthetic Views
* Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation
* PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking
* Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
* Polar-Photometric Stereo Under Natural Illumination
* Pose Guided Human Motion Transfer by Exploiting 2D and 3D Information
* Progressive Multi-Scale Light Field Networks
* Push-the-Boundary: Boundary-aware Feature Propagation for Semantic Segmentation of 3D Point Clouds
* Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors
* Robust RGB-D Fusion for Saliency Detection
* SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation
* SDA-SNE: Spatial Discontinuity-Aware Surface Normal Estimation via Multi-Directional Dynamic Programming
* SHRAG: Semantic Hierarchical Graph for Floorplan Representation
* Simultaneous Localisation and Mapping With Quadric Surfaces
* Smooth Non-Rigid Shape Matching via Effective Dirichlet Energy Optimization
* SO(3) Rotation Equivariant Point Cloud Completion using Attention-based Vector Neurons
* Spectral Teacher for a Spatial Student: Spectrum-Aware Real-Time Dense Shape Correspondence
* SphereDepth: Panorama Depth Estimation from Spherical Domain
* SRFeat: Learning Locally Accurate and Globally Consistent Non-Rigid Shape Correspondence
* Structure-Aware 3D VR Sketch to 3D Shape Retrieval
* Structured Latent Space for Human Body Motion Generation, A
* Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction, The
* SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation
* TEACH: Temporal Action Composition for 3D Humans
* TempCLR: Reconstructing Hands via Time-Coherent Contrastive Learning
* Temporal Shape Transfer Network for 3D Human Motion
* There and Back Again: 3D Sign Language Generation from Text Using Back-Translation
* Visual Localization via Few-Shot Scene Region Classification
72 for 3DV22
3DV24
* *3D Imaging, Modeling, Processing, Visualization and Transmission
* 3D Pose Estimation of Two Interacting Hands from a Monocular Event Camera
* 3D-TexSeg: Unsupervised Segmentation of 3D Texture Using Mutual Transformer Learning
* 3DRef: 3D Dataset and Benchmark for Reflection Detection in RGB and Lidar Data
* ActiveNeuS: Neural Signed Distance Fields for Active Stereo
* Addressing Low-Shot MVS by Detecting and Completing Planar Surfaces
* ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation
* Benchmark Grocery Dataset of Realworld Point Clouds From Single View, A
* BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds
* BLiSS: Bootstrapped Linear Shape Space
* Classical Photometric Stereo in Point Lighting Environments: Error Analysis and Mitigation
* CloSe: A 3D Clothing Segmentation Dataset and Model
* Cloth2Tex: A Customized Cloth Texture Generation Pipeline for 3D Virtual Try-On
* CoARF: Controllable 3D Artistic Style Transfer for Radiance Fields
* Coherent Enhancement of Depth Images and Normal Maps Using Second-Order Geometric Models on Weighted Finite Graphs
* Color-NeuS: Reconstructing Neural Implicit Surfaces with Color
* CombiNeRF: A Combination of Regularization Techniques for Few-Shot Neural Radiance Field View Synthesis
* Compositional 3D Scene Generation using Locally Conditioned Diffusion
* Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models
* ContactArt: Learning 3D Interaction Priors for Category-level Articulated Object and Hand Poses Estimation
* Continuous Cost Aggregation for Dual-Pixel Disparity Extraction
* Control3Diff: Learning Controllable 3D Diffusion Models from Single-view Images
* Controllable Dynamic Appearance for Neural 3D Portraits
* Correspondence-Free Online Human Motion Retargeting
* Cross Branch Fusion-Based Contrastive Learning Framework for Point Cloud Self-supervised Learning, A
* Cross3DVG: Cross-Dataset 3D Visual Grounding on Different RGB-D Scans
* DAC: Detector-Agnostic Spatial Covariances for Deep Local Features
* DeDoDe: Detect, Don't Describe: Describe, Don't Detect for Local Feature Matching
* Deep Event Visual Odometry
* DeepDR: Deep Structure-Aware RGB-D Inpainting for Diminished Reality
* DeepShaRM: Multi-View Shape and Reflectance Map Recovery Under Unknown Lighting
* DehazeNeRF: Multi-image Haze Removal and 3D Shape Reconstruction using Neural Radiance Fields
* Depth Reconstruction with Neural Signed Distance Fields in Structured Light Systems
* Developability Approximation for Neural Implicits Through Rank Minimization
* Diffusion Shape Prior for Wrinkle-Accurate Cloth Registration
* Diffusion-HPC: Synthetic Data Generation for Human Mesh Recovery in Challenging Domains
* Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
* Dynamic Prototype Adaptation with Distillation for Few-shot Point Cloud Segmentation
* DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction With an Optimizable Feature Grid
* Efficient 3D Articulated Human Generation with Layered Surface Volumes
* Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding
* Event-Based Visual Odometry on Non-Holonomic Ground Vehicles
* Exploit Spatiotemporal Contextual Information for 3D Single Object Tracking via Memory Networks
* Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion
* Fast High Dynamic Range Radiance Fields for Dynamic Scenes
* Fast Relative Pose Estimation using Relative Depth
* FastHuman: Reconstructing High-Quality Clothed Human in Minutes
* Few-View Object Reconstruction with Unknown Categories and Camera Poses
* FoVA-Depth: Field-of-View Agnostic Depth Estimation for Cross-Dataset Generalization
* Fusing Directions and Displacements in Translation Averaging
* GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar
* GAPS: Geometry-Aware, Physics-Based, Self-Supervised Neural Garment Draping
* Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects
* Generating Continual Human Motion in Diverse 3D Scenes
* Geometrically Consistent Partial Shape Matching
* GHuNeRF: Generalizable Human NeRF from a Monocular Video
* GRIP: Generating Interaction Poses Using Spatial Cues and Latent Consistency
* Handbook on Leveraging Lines for Two-View Relative Pose Estimation
* HOC-Search: Efficient CAD Model and Pose Retrieval From RGB-D Scans
* HumanReg: Self-supervised Non-rigid Registration of Human Point Cloud
* Hyper-SNBRDF: Hypernetwork for Neural BRDF Using Sinusoidal Activation
* Improved Scene Landmark Detection for Camera Localization
* Incorporating Rotation Invariance with Non-invariant Networks for Point Clouds
* InstantAvatar: Efficient 3D Head Reconstruction via Surface Rendering
* Interaction Replica: Tracking Human-Object Interaction and Scene Changes From Human Motion
* IS-NEAR: Implicit Semantic Neural Engine and Multi-Sensor Data Rendering With 3D Global Feature
* Joint Spatial-Temporal Calibration for Camera and Global Pose Sensor
* LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories
* Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction
* Learning Based Infinite Terrain Generation with Level of Detailing
* Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images
* LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals
* Local Appearance Model for Volumetric Capture of Diverse Hairstyles, A
* LocPoseNet: Robust Location Prior for Unseen Object Pose Estimation
* LumiGAN: Unconditional Generation of Relightable 3D Human Faces
* MACS: Mass Conditioned 3D Hand and Object Motion Synthesis
* MC-Stereo: Multi-Peak Lookup and Cascade Search Range for Stereo Matching
* MELON: NeRF with Unposed Images in SO(3)
* Mirror-Aware Neural Humans
* Mixing-Denoising Generalizable Occupancy Networks
* MixRT: Mixed Neural Representations For Real-Time NeRF Rendering
* MonoLSS: Learnable Sample Selection For Monocular 3D Detection
* Multi-Body Neural Scene Flow
* MuVieCAST: Multi-View Consistent Artistic Style Transfer
* NCRF: Neural Contact Radiance Fields for Free-Viewpoint Rendering of Hand-Object Interaction
* NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
* NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes
* Neural Field Regularization by Denoising for 3D Sparse-View X-Ray Computed Tomography
* NeVRF: Neural Video-Based Radiance Fields for Long-Duration Sequences
* NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM
* Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting
* OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection
* Occlusion Resilient 3D Human Pose Estimation
* OPDMulti: Openable Part Detection for Multiple Objects
* Oriented-grid Encoder for 3D Implicit Representations
* Out of the Room: Generalizing Event-Based Dynamic Motion Segmentation for Complex Scenes
* PACE: Human and Camera Motion Estimation from in-the-wild Videos
* PanoSSC: Exploring Monocular Panoptic 3D Scene Reconstruction for Autonomous Driving
* Partial-View Object View Synthesis via Filtering Inversion
* PathFusion: Path-Consistent Lidar-Camera Deep Feature Fusion
* PhoMoH: Implicit Photorealistic 3D Models of Human Heads
* Photometric visibility matrix for the automatic selection of optimal viewpoints
* Physically Plausible Full-Body Hand-Object Interaction Synthesis
* Physics-based Indirect Illumination for Inverse Rendering
* Physics-Based Rigid Body Object Tracking and Friction Filtering From RGB-D Videos
* PIVOT-Net: Heterogeneous Point-Voxel-Tree-based Framework for Point Cloud Compression
* Pix4Point: Image Pretrained Standard Transformers for 3D Point Cloud Understanding
* PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Urban Scene Reconstruction
* POCO: 3D Pose and Shape Estimation with Confidence
* Practical Measurement and Neural Encoding of Hyperspectral Skin Reflectance
* PRAGO: Differentiable Multi-View Pose Optimization From Objectness Detections*
* PU-SDF: Arbitrary-Scale Uniformly Upsampling Point Clouds via Signed Distance Functions
* Purposer: Putting Human Motion Generation in Context
* Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature
* Quantum-Hybrid Stereo Matching With Nonlinear Regularization and Spatial Pyramids
* RaNeuS: Ray-adaptive Neural Surface Reconstruction
* Range-Agnostic Multi-View Depth Estimation with Keyframe Selection
* Ray-Patch: An Efficient Querying for Light Field Transformers
* Relative Pose for Nonrigid Multi-Perspective Cameras: The Static Case
* RelPose++: Recovering 6D Poses from Sparse-view Observations
* Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization
* Revisiting Map Relations for Unsupervised Non-Rigid Shape Matching
* RIVQ-VAE: Discrete Rotation-Invariant 3D Representation Learning
* ROAM: Robust and Object-Aware Motion Generation Using Neural Pose Descriptors
* Robust Point Cloud Processing Through Positional Embedding
* RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation
* S4C: Self-Supervised Semantic Scene Completion With Neural Fields
* SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
* Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering
* SceNeRFlow: Time-Consistent Reconstruction of General Dynamic Scenes
* SCENES: Subpixel Correspondence Estimation With Epipolar Supervision
* Select-Sliced Wasserstein Distance for Point Cloud Learning
* Self-Supervised Learning of Neural Implicit Feature Fields for Camera Pose Refinement
* Self-Supervised Learning of Skeleton-Aware Morphological Representation for 3D Neuron Segments
* SimpleEgo: Predicting Probabilistic Body Pose from Egocentric Cameras
* Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture
* SlimmeRF: Slimmable Radiance Fields
* Sparse 3D Reconstruction via Object-Centric Ray Sampling
* SPHEAR: Spherical Head Registration for Complete Statistical 3D Modeling
* Split, Merge, and Refine: Fitting Tight Bounding Boxes via Over-Segmentation and Iterative Search
* Stable Surface Regularization for Fast Few-Shot NeRF
* SUCRe: Leveraging Scene Structure for Underwater Color Restoration
* Synthesizing Physically Plausible Human Motions in 3D Scenes
* TADA! Text to Animatable Digital Avatars
* TECA: Text-Guided Generation and Editing of Compositional 3D Avatars
* TeCH: Text-Guided Reconstruction of Lifelike Clothed Humans
* Test-Time Augmentation for 3D Point Cloud Classification and Segmentation
* TextMesh: Generation of Realistic 3D Meshes From Text Prompts
* Towards Learning Monocular 3D Object Localization from 2D Labels Using the Physical Laws of Motion
* UAVD4L: A Large-Scale Dataset for UAV 6-DoF Localization
* Unsupervised 3D Keypoint Discovery with Multi-View Geometry
* Unsupervised Representation Learning for Diverse Deformable Shape Collections
* Visual Tomography: Physically Faithful Volumetric Models of Partially Translucent Objects
* YOLO-6D-Pose: Enhancing YOLO for Single-Stage Monocular Multi-Object 6D Pose Estimation
* Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps
155 for 3DV24