Description: Dynamic Dual Trainable Bounds for Ultra-Low Precision Super-Resolution Networks.- OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers.- Highly Accurate Dichotomous Image Segmentation.- Boosting Supervised Dehazing Methods via Bi-Level Patch Reweighting.- Flow-Guided Transformer for Video Inpainting.- Shift-tolerant Perceptual Similarity Metric.- Perception-Distortion Balanced ADMM Optimization for Single-Image Super-Resolution.- VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder.- Uncertainty Learning in Kernel Estimation for Multi-stage Blind Image Super-Resolution.- Learning Spatio-Temporal Downsampling for Effective Video Upscaling.- Learning Local Implicit Fourier Representation for Image Warping.- SepLUT: Separable Image-Adaptive Lookup Tables for Real-Time Image Enhancement.- Blind Image Decomposition.- MuLUT: Cooperating Multiple Look-Up Tables for Efficient ImageSuper-Resolution.- Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution.- Spatial-Frequency Domain Information Integration for Pan-Sharpening.- Adaptive Patch Exiting for Scalable Single Image Super-Resolution.- Efficient Meta-Tuning for Content-Aware Neural Video Delivery.- Reference-Based Image Super-Resolution with Deformable Attention Transformer.- Local Color Distributions Prior for Image Enhancement.- L-CoDer: Language-Based Colorization with Color-Object Decoupling Transformer.- From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution.- Towards Interpretable Video Super-Resolution via Alternating Optimization.- Event-Based Fusion for Motion Deblurring with Cross-Modal Attention.- Fast and High Quality Image Denoising via Malleable Convolution.- TAPE: Task-Agnostic Prior Embedding for Image Restoration.- Uncertainty Inspired Underwater Image Enhancement.- Hourglass Attention Network for Image Inpainting.- Unfolded Deep Kernel Estimation for Blind Image Super-Resolution.- Event-Guided Deblurring of Unknown Exposure Time Videos.- ReCoNet: Recurrent Correction Network for Fast and Efficient Multi-Modality Image Fusion.- Content Adaptive Latents and Decoder for Neural Image Compression.- Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution.- Unidirectional Video Denoising by Mimicking Backward Recurrent Modules with Look-Ahead Forward Ones.- Self-Supervised Learning for Real-World Super-Resolution from Dual Zoomed Observations.- Secrets of Event-Based Optical Flow.- Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing.- ERDN: Equivalent Receptive Field Deformable Network for Video Deblurring.- Rethinking Generic Camera Models for Deep Single Image Camera Calibration to Recover Rotation and Fisheye Distortion.- ART-SS: An Adaptive Rejection Technique for Semi-Supervised Restoration for Adverse Weather-Affected Images.- Fusion from Decomposition: A Self-Supervised Decomposition Approach for Image Fusion.-Learning Degradation Representations for Image Deblurring.

Please Wait