Postdoc researcher at HKU, interested in 3D GenAI. PhD from USTC.
Person-Attribute-Recognition-MarketDuke. A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.
404DreamCube. [ICCV 2025] Official implementation of the paper "DreamCube: 3D Panorama Generation via Multi-plane Synchronization".
181Single-Human-Parsing-LIP. PSPNet implemented in PyTorch for single-person human parsing task, evaluating on Look Into Person (LIP) dataset.
161DreamWaltz-G. [TPAMI 2025] Official implementation of the paper "DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion".
156pytorch-differentiable-histogram. PyTorch implementation for differentiable histogram
23Degradation-Invariant-ReID-pytorch. [IJCV 2022] Official implementation of the paper "Learning Degradation-Invariant Representation for Robust Real-World Person Re-Identification".
12Rank-Diminishing-in-Deep-Neural-Networks. [NeurIPS 2022] Official implementation of the paper "Rank Diminishing in Deep Neural Networks".
8FeatureVisualizer-pytorch. An implementation of feature visualizer for pytorch tensor, based on Matplotlib.
6selfie-animeStyle-convertor. An application of cycleGAN. Covert real selfie photos to anime style's selfie images.
4Google-KickStart. Google KickStart 刷题记录
3PaintAndRecognition-opencv-tf. This is a program depending on opencv3.1,python2.7 and tensorflow1.0. It can track objects by KCF algorithm,then paint its trajectory,next we can recognition this trajectory as a character or numbers.
3OmniX. OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes
2diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch
1Awesome-3D-AIGC.
1LeetCode. LeetCode 刷题记录
1