Computer Vision - ECCV 2022

The 39-volume set, comprising the LNCS books 13661 until 13699, constitutes the refereed proceedings of the 17th European Conference on Computer Vision, ECCV 2022, held in Tel Aviv, Israel, during October 2327, 2022.

The 1645 papers presented in these proceedings were carefully reviewed and selected from a total of 5804 submissions. The papers deal with topics such as computer vision; machine learning; deep neural networks; reinforcement learning; object recognition; image classification; image processing; object detection; semantic segmentation; human pose estimation; 3d reconstruction; stereo vision; computational photography; neural networks; image coding; image reconstruction; object recognition; motion estimation.

Inhalt
Learning Mutual Modulation for Self-Supervised Cross-Modal Super Resolution.- Spectrum-Aware and Transferable Architecture Search for Hyperspectral Image Restoration.- Neural Color Operators for Sequential Image Retouching.- Optimizing Image Compression via Joint Learning with Denoising.- Restore Globally, Refine Locally: A Mask-Guided Scheme to Accelerate Super-Resolution Networks.- Compiler-Aware Neural Architecture Search for On-Mobile Real-Time Super-Resolution.- Modeling Mask Uncertainty in Hyperspectral Image Reconstruction.- Perceiving and Modeling Density for Image Dehazing.- Stripformer: Strip Transformer for Fast Image Deblurring.- Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction.- Frequency and Spatial Dual Guidance for Image Dehazing.- Towards Real-World HDRTV Reconstruction: A Data Synthesis Based Approach.- Learning Discriminative Shrinkage Deep Networks for Image Deconvolution.- KXNet: A Model-Driven Deep Neural Network for Blind Super Resolution.- ARM: Any-Time Super-Resolution Method.- Attention-Aware Learning for Hyperparameter Prediction in Image Processing Pipelines.- RealFlow: EM-Based Realistic Optical Flow Dataset Generation from Videos.- Memory-Augmented Model-Driven Network for Pansharpening.- All You Need Is RAW: Defending against Adversarial Attacks with Camera Image Pipelines.- Ghost-Free High Dynamic Range Imaging with Context-Aware Transformer.- Style-Guided Shadow Removal .- D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution.- GRIT-VLP: Grouped Mini-Batch Sampling for Efficient Vision and Language Pre-training.- Efficient Video Deblurring Guided by Motion Magnitude.- Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and a New Physics-Inspired Transformer Model .- Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compression.- Image Super-Resolution with Deep Dictionary.- TempFormer: Temporally Consistent Transformer for Video Denoising.- RAWtoBit: A Fully End-to-End Camera ISP Network.- DRCNet: Dynamic Image Restoration Contrastive Network.- Zero-Shot Learning for Reflection Removal of Single 360-Degree Image.- Transformer with Implicit Edges for Particle-Based Physics Simulation.- Rethinking Video Rain Streak Removal: A New Synthesis Model and a Deraining Network with Video Rain Prior.- Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images.- Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance.- AlphaVC: High-Performance and Efficient Learned Video Compression.- Content-Oriented Learned Image Compression.- RRSR:Reciprocal Reference-Based Image Super-Resolution with Progressive Feature Alignment and Selection.- Contrastive Prototypical Network with Wasserstein Confidence Penalty.- Learn to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition.- Self-Support Few-Shot Semantic Segmentation.- Few-Shot Object Detection with Model Calibration.- Self-Supervision Can Be a Good Few-Shot Learner.