GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.

[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.

End-to-end learning of deep visual representations for image retrieval

PlaneRCNN detects and reconstructs piece-wise planar surfaces from a single RGB image

LeetGPU Challenges

Source code for the ECCV 2022 paper "Benchmarking Localization and Mapping for Augmented Reality".

Simultaneous Visual Odometry, Object Detection, and Instance Segmentation

This github is a supplementary material including data, code, trained model and demo for the paper "NDT-Transformer: Large-Scale 3D Point Cloud Localisation using the Normal Distribution Transform …

coding practice track