Yonghui Wang

Awesome-Document-Understanding. Document Artifical Intelligence

Detect-AnyShadow. Official PyTorch implementation for TCSVT 23 "Detect Any Shadow: Segment Anything for Video Shadow Detection"

ROOT. ROOT: VLM based System for Indoor Scene Understanding and Beyond

UDoc-GAN. Official PyTorch implementation for ACM MM22 "UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior"

TGDoc. "Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs" 2023

SwinShadow. Official PyTorch implementation for TOMM24 "SwinShadow: Shifted Window for Ambiguous Adjacent Shadow Detection"

RetinexNet. An implement of RetinexNet

OpenVLM-Finetuning. Repository of finetuning Open-Source VLM

AdaptVision. AdaptVision: Dynamic Input Scaling in MLLMs for Versatile Scene Understanding

PRNet. Official PyTorch implementation for CVIU 23 "Progressive Recurrent Network for Shadow Removal"

SVL. Python