Siyu Huang

ff3r. [CVPR'26 Findings] FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views

Bezier_splatting. Python

Awesome-MLLM-Reasoning-Benchmarks. A Comprehensive Survey on Evaluating Reasoning Capabilities in Multimodal Large Language Models.

sam3. The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Bonnet. [ISBI'26 Oral] Bonnet: Ultra-Fast Whole-Body Bone Segmentation from CT Scans

dinov3. Reference PyTorch implementation and models for DINOv3

Awesome-Diabetic-Retinopathy-Detection. Papers and Public Datasets for Diabetic Retinopathy Detection

EyeCLIP. Python

Fundus2Video. Python

FSGCD. Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement (ICMR 2025)

LLM4SVG. [CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102

SoftShadow. Official Implimentation of SoftShadow: Leveraging Penumbra-Aware Soft Masks for Shadow Removal

latent-radiance-field. [ICLR 2025] Latent Radiance Fields with 3D-aware 2D Representations

AutoAL. Python

3DGS-Enhancer.

nsf-proposal-latex-samples. LaTeX samples for NSF Research.gov Proposal Submission. For more information about Research.gov Proposal Submission visit https://www.research.gov/research-web/content/aboutpsm Feedback syee@nsf.gov

Awesome-Shadow-Removal. Collection of recent shadow removal works, including papers, codes, datasets, and metrics.

Self-Cascade. [ECCV2024] Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

S3-TTA. This repository contains the implementation and pretrained model for the paper presented at ISBI2024: S3-TTA: Scale-Style Selection for Test-Time Augmentation in Biomedical Image Segmentation

GC-GAN. Python

NARUTO. [CVPR2024] NARUTO: Neural Active Reconstruction

awesome-tips.

QuantArt. Official PyTorch implementation of QuantArt (CVPR2023)

Latent-Space-Anchoring. PyTorch Implementation of Latent Space Anchoring (TPAMI 2023)

ShadowDiffusion. ShadowDiffusion (CVPR2023), Pytorch implementation

ShadowFormer. ShadowFormer (AAAI2023), Pytorch implementation

stable-diffusion. A latent text-to-image diffusion model

CelebV-HQ. [ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset

imagen-pytorch. Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

Rethinking-Counting. [CVPR 2022] Rethinking Spatial Invariance of Convolutional Networks for Object Counting

diffvg. Differentiable Vector Graphics Rasterization

GOOD. GOOD: A Graph Out-of-Distribution Benchmark [NeurIPS 2022 Datasets and Benchmarks]

Neural-Texture-Extraction-Distribution. The PyTorch implementation for paper "Neural Texture Extraction and Distribution for Controllable Person Image Synthesis" (CVPR2022 Oral)

AutoGCL. AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators (AAAI 2022)

BM-NAS. BM-NAS: Bilevel Multimodal Neural Architecture Search (AAAI 2022 Oral)

svox2. Plenoxels: Radiance Fields without Neural Networks

gdrive. Google Drive CLI Client

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

StarGANv2-VC. StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion

voice-conversion. Voice Conversion pipeline consisting of GE2E speaker encoder, AutoVC conversion model and MelGAN vocoder.

stylegan3. Official PyTorch implementation of StyleGAN3

SketchClassification. Pytorch Sketch Classification

ml-projects. Implementation of web friendly ML models using TensorFlow.js. pix2pix, face segmentation, fast style transfer and many more ...

genforce. An efficient PyTorch library for deep generative modeling.

sofgan. [TOG 2022] SofGAN: A Portrait Image Generator with Dynamic Styling

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

MockingBird. 🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

nerf-pytorch. A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

ReLLIE. ReLLIE (ACMMM2021), Pytorch implementation

alphafold. Open source code for AlphaFold 2.

awesome-explainable-graph-reasoning. A collection of research papers and software related to explainability in graph machine learning.

giraffe. This repository contains the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

keypoint_deformer. KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control. CVPR 2021 Oral presentation

diffusion-point-cloud. :thought_balloon: Diffusion Probabilistic Models for 3D Point Cloud Generation (CVPR 2021)

nerf. Code release for NeRF (Neural Radiance Fields)

ArtFlow. Official PyTorch implementation of "ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows"

DIG. A library for graph deep learning research

StyleNAS. Official pytorch implementation of the paper: "Ultrafast Photorealistic Style Transfer via Neural Architecture Search"

BCCD_Dataset. BCCD (Blood Cell Count and Detection) Dataset is a small-scale dataset for blood cells detection.

PaddleSpeech. Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

PaddleFormers. PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

deepfashion2-kps-agg-finetune. 1st place solution (Team StylingAI Inc. & PKU AIIC) for CVPR 2020 DeepFashion2 Clothes Landmark Detection Track. Aggregation and Finetuning for Clothes Landmark Detection

wenyan. 文言文編程語言 A programming language for the ancient Chinese.

GPT2-Chinese. Chinese version of GPT2 training code, using BERT tokenizer.

random-network-distillation. Code for the paper "Exploration by Random Network Distillation"

TrDec_pytorch. Python

CSRNet-pytorch. CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes

crowdcount-mcnn. Single Image Crowd Counting via MCNN (Unofficial Implementation)

social-lstm-tf. Tensorflow implementation of the Social LSTM model

CIDNN. CIDNN: Encoding Crowd Interaction with Deep Neural Network

countception. Count-Ception: Counting by Fully Convolutional Redundant Counting

Inverse-Reinforcement-Learning. Implementations of selected inverse reinforcement learning algorithms.

visual-interaction-networks-pytorch. This's an implementation of deepmind Visual Interaction Networks paper using pytorch

visual-interaction-networks_tensorflow. Tensorflow Implementation of Visual Interaction Networks

MakeLabelForMarketAndDuke. Make label files for training and testing on Market-1501 Attribute and DukeMTMC-attribute Dataset