Machine learning for image processing

Multistage Spatial Context Models for Learned Image Compression

RETIFORMER: RETINEX-BASED ENHANCEMENT IN TRANSFORMER FOR LOW-LIGHT IMAGE

PRIME: 3D Human Pose and Body Shape Recovery with Perspective Projection

Learning Generalizable Light Field Networks from Few Images

M2TSR: Multi-range and Mix-grained Transformer for Single Image Super-Resolution

Learning Supervised Covariation Projection Through General Covariance

A discriminative multi-channel noise feature representation method for image manipulation localization

SR-init: An Interpretable Layer Pruning Method

Classifying Pathological Images Based on Multi-Instance Learning and End-to-End Attention Pooling

Rain2Avoid: Self-supervised Single Image Deraining

End-to-End Non-Autoregressive Image Captioning

PCQA-GRAPHPOINT: EFFICIENT DEEP-BASED GRAPH METRIC FOR POINT CLOUD QUALITY ASSESSMENT