PBDL19
* *Physics Based Vision Meets Deep Learning
* Event-Driven Video Frame Synthesis
* Learning From Synthetic Photorealistic Raindrop for Single Image Raindrop Removal
* Multi-Level and Multi-Scale Spatial and Spectral Fusion CNN for Hyperspectral Image Super-Resolution
* Multispectral Reconstruction From Reference Objects in the Scene
* Single Image Intrinsic Decomposition with Discriminative Feature Encoding
PBDL21
* *Physics Based Vision Meets Deep Learning
* Deep Single Fisheye Image Camera Calibration for Over 180-degree Projection of Field of View
* DeLiEve-Net: Deblurring Low-light Images with Light Streaks and Local Events
* Efficient light transport acquisition by coded illumination and robust photometric stereo by dual photography using deep neural network
* Enforcing Temporal Consistency in Video Depth Estimation
* Generative Models for Multi-Illumination Color Constancy
* HyperMixNet: Hyperspectral Image Reconstruction with Deep Mixed Network from a Snapshot Measurement
* Multi-Level Adaptive Separable Convolution for Large-Motion Video Frame Interpolation
* Precise Forecasting of Sky Images Using Spatial Warping
* Weakly-supervised Semantic Segmentation in Cityscape via Hyperspectral Image
10 for PBDL21
PBDL24
* *Physics Based Vision Meets Deep Learning
* Computational Spectral Imaging with Unified Encoding Model and Beyond
* Gain-first or Exposure-first: Benchmark for Better Low-light Video Photography and Enhancement
* Generalized Foggy-Scene Semantic Segmentation by Frequency Decoupling
* Generating Material-Aware 3D Models from Sparse Views
* GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning
* Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters
* Physics Based Camera Privacy: Lens and Network Co-Design to the Rescue
* Point-Supervised Semantic Segmentation of Natural Scenes via Hyperspectral Imaging
* ViTKD: Feature-based Knowledge Distillation for Vision Transformers
10 for PBDL24