Yangyan Li

Fast-FoundationStereo. [CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

citation_analyzer. Beyond the count: AI-driven insights into who is citing, how they're citing, and in which research domains.

pointelligence. the official implementation of PointCNN++ (CVPR 2026)

lingbot-va. [RSS 2026] Causal video-action world model for generalist robot control

lingbot-vla. A Pragmatic VLA Foundation Model

lingbot-depth. Masked Depth Modeling for Spatial Perception

lingbot-world. Advancing Open-source World Models

nanochat. The best ChatGPT that $100 can buy.

mini-sglang. A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

ml-sharp. Sharp Monocular View Synthesis in Less Than a Second

HY-WorldPlay. HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

replicAnt. replicAnt - generating annotated images of animals in complex environments with Unreal Engine

scAnt. open-source 3D scanning and processing pipeline

CausVid. (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models

torchtitan. A PyTorch native platform for training generative AI models

Megatron-LM. Ongoing research training transformer models at scale

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

tilus. Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.

dinov3. Reference PyTorch implementation and models for DINOv3

vipe. ViPE: Video Pose Engine for Geometric 3D Perception

WarpConvNet. Make your wildest 3D ConvNet dream architectures come true

vggt. [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

open-r1. Fully open reproduction of DeepSeek-R1

DeepSeek-V3. Python

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

gsplat. CUDA accelerated rasterization of gaussian splatting

DRTK. Differentiable Rendering Toolkit

convex-splatting. [CVPR 2025 - Highlight] Original implementation of "3D Convex Splatting: Radiance Field Rendering with 3D Smooth Convexes"

slam-handbook-public-release. Release repo for our SLAM Handbook

brush. 3D Reconstruction for all

gaussian-splatting-lightning. A 3D Gaussian Splatting framework with various derived algorithms and an interactive web viewer

slang-torch. A Python package for calling Slang modules from PyTorch.

Triplet. Python

vision3d. Vision3D: A 3D Vision Library built with PyTorch

slang-gaussian-rasterization. Slang

vismatch. Wrapper of 50+ image matching models with a unified interface

Transformer-in-Computer-Vision. A paper list of some recent Transformer-based CV works.

puzzlefusion-plusplus. Code for paper "PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify" [ICLR 2025]

glomap. [DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited

ao. PyTorch native quantization and sparsity for training and inference

fiftyone. Refine high-quality datasets and visual AI models

theseus. A library for differentiable nonlinear optimization

ShaDDR. Pytorch Implementation of ShaDDR (SIGGRAPH Asia 2023 Conference)

Awesome-Video-Diffusion-Models. [CSUR] A Survey on Video Diffusion Models

pytorch-ssim. pytorch structural similarity (SSIM) loss

Jigsaw. [NeurIPS 2023] Jigsaw: Learning to Assemble Multiple Fractured Objects

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

Manifold. Convert any Triangle Mesh to Watertight Manifold

ManifoldPlus. ManifoldPlus: A Robust and Scalable Watertight Manifold Surface Generation Method for Triangle Soups

LEAP. [ICLR 2024] Code for LEAP: Liberate Sparse-view 3D Modeling from Camera Poses

colmap. COLMAP - Structure-from-Motion and Multi-View Stereo

ADOP. C++

compute_rasterizer. Rendering Point Clouds with Compute Shaders

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

leptonai. A Pythonic framework to simplify AI service building

One-2-3-45. [NeurIPS 2023] Official code of "One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization"

ciao-sig23. HTML

NeuSC. A Temporal Voyage: Code for "Neural Scene Chronology" [CVPR 2023]

ann-benchmarks. Benchmarks of approximate nearest neighbor libraries in Python

mold. mold: A Modern Linker 🦠

hnswlib. Header-only C++/python library for fast approximate nearest neighbors

pr-agent. 🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.

IAE. [ICCV 2023] "Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning"

getpy. A Vectorized Python Dict/Set

DeepGlobalRegistration. [CVPR 2020 Oral] A differentiable framework for 3D registration

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

sdfstudio. A Unified Framework for Surface Reconstruction

nerfstudio. A collaboration friendly studio for NeRFs

nerfacc. A General NeRF Acceleration Toolbox in PyTorch.

octformer. OctFormer: Octree-based Transformers for 3D Point Clouds [SIGGRAPH 2023]

triton. Development repository for the Triton language and compiler

openpoints. OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [ASSANet](https://arxiv.org/abs/2110.10538), [PointNeXt](https://arxiv.org/abs/2206.04670)

DO-Conv. Depthwise Over-parameterized Convolutional Layer

corl_22_frame_mining. [CoRL22] Frame Mining - a Free Lunch for Learning Robotic Manipulation from 3D Point Clouds

KPConv-PyTorch. Kernel Point Convolution implemented in PyTorch

torch-points3d. Pytorch framework for doing deep learning on point clouds.

PointNeXt. [NeurIPS'22] PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies

MinkowskiEngine. Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

simple_bev. A Simple Baseline for BEV Perception

Open-World-Tracking. Official code for "Opening up Open World Tracking" (CVPR 2022)

modelverse. Modelverse: Content-Based Search for Deep Generative Models

Images2Video. Encode a sequence of images into a video file

ProcCG. Procedural city generation.

semiring-einsum. Generic PyTorch implementation of einsum that supports different semirings

PointCNN. PointCNN: Convolution On X-Transformed Points (NeurIPS 2018)

torchsparse. [MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

keops. KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

Sync2Gen. Python

PrimitiveNet. PrimitiveNet: Primitive Instance Segmentation with Local Primitive Embedding under Adversarial Metric (ICCV 2021)

ARAPReg. Python

GANSketching. Sketch Your Own GAN: Customizing a GAN model with hand-drawn sketches.

POT. POT : Python Optimal Transport

ShapeConv. ShapeConv: Shape-aware Convolutional Layer for Indoor RGB-D Semantic Segmentation (ICCV 2021)

helloworld. C

zeno. ZEn NOde system - a simulation & rendering engine in nodes

digital_video_introduction. A hands-on introduction to video technology: image, video, codec (av1, vp9, h265) and more (ffmpeg encoding). Translations: 🇺🇸 🇨🇳 🇯🇵 🇮🇹 🇰🇷 🇷🇺 🇧🇷 🇪🇸

Swin-Transformer. This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

iso-points. Code for Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations

Trescope. Trescope is a comprehensive 3D machine learning development tool devoted to improve developing experience and speed in 3D field, which helps researchers and developers to label, debug, visualize various 3D data

FLAVR. Code for FLAVR: A fast and efficient frame interpolation technique.

awesome-tensor-compilers. A list of awesome compiler projects and papers for tensor computation and deep learning.

neural-engine. Everything we actually know about the Apple Neural Engine (ANE)

alibabacloud-RTCInteractiveClass-demo. alibabacloud-RTCInteractiveClass-demo

alibabacloud-AliRtcSuperClass-demo. alibabacloud-AliRtcSuperClass-demo

avatarify-python. Avatars for Zoom, Skype and other video-conferencing apps.

MultiScanRegistration. C++

SINet. Camouflaged Object Detection, CVPR 2020 (Oral)

scanobjectnn. Code for Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data, ICCV 2019

SampleNet. Differentiable Point Cloud Sampling (CVPR 2020 Oral)

H3DNet. Python

HybridPose. HybridPose: 6D Object Pose Estimation under Hybrid Representation (CVPR 2020)

votenet. Deep Hough Voting for 3D Object Detection in Point Clouds

Point-Cloud-Perception-Papers-Reading. Some papers about 3D point cloud processing from LiDAR, cameras, etc.

PointMVSNet. Code for "Point-based Multi-view Stereo Network" (ICCV 2019 Oral) & "Visibility-aware Point-based Multi-view Stereo Network" (TPAMI)

SeetaFace2. SeetaFace 2: open source, full stack face recognization toolkit.

PolyFit. Polygonal Surface Reconstruction from Point Clouds (C++ & Python)

pytracking. Visual tracking library based on PyTorch.

996.ICU. Repo for counting stars and contributing. Press F to pay respect to glorious developers.

dragonfly. An open source python library for scalable Bayesian optimisation.

partnet_dataset. PartNet Dataset Official Release Repo

pytorch_geometric. Graph Neural Network Library for PyTorch

tf-estimator-distribute-so. this repository serves as a minimal, reproducible example to the issue I describe in https://stackoverflow.com/questions/50924287/how-to-influence-the-name-scope-of-collated-variables-slots

SSD.TensorFlow. State-of-the-art Single Shot MultiBox Detector in Pure TensorFlow, QQ Group: 758790869

deepfloat. An exploration of log domain "alternative floating point" for hardware ML/AI accelerators.

MCCNN. Monte Carlo Convolution for Learning on Non-Uniformly Sampled Point Clouds

rethinking-network-pruning. Rethinking the Value of Network Pruning (Pytorch) (ICLR 2019)

DiDA. Disentangled Synthesis for Domain Adaptation

PointCNN.Pytorch. A PyTorch implemetation of PointCNN (CS294-131 Course Proj)

pointwise. Code for Pointwise Convolutional Neural Networks, CVPR 2018

dgcnn. Python

frustum-pointnets. Frustum PointNets for 3D Object Detection from RGB-D Data

3D-Machine-Learning. A resource repository for 3D machine learning

SO-Net. SO-Net: Self-Organizing Network for Point Cloud Analysis, CVPR2018

PointCNN.MX. A MXNet implemetation of PointCNN

hangzhou_house_knowledge. 2017年买房经历总结出来的买房购房知识分享给大家，希望对大家有所帮助。买房不易，且买且珍惜。Sharing the knowledge of buy an own house that according to the experience at hangzhou in 2017 to all the people. It's not easy to buy a own house, so I hope that it would be useful to everyone.

gumbel_sinkhorn. Python

svgpathtools. A collection of tools for manipulating and analyzing SVG Path objects and Bezier curves.

SparseConvNet. Submanifold sparse convolutional networks

complement-me. Python

pose-hg-3d. Code repository for Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

graph_matching. Matlab

octnet. OctNet: Learning Deep 3D Representations at High Resolutions

setup-ipsec-vpn. Set up your own IPsec VPN server in just a few minutes, with IPsec/L2TP, Cisco IPsec and IKEv2. Supports Ubuntu, Debian, CentOS/RHEL, Alpine Linux and Raspberry Pi OS. Includes client config and management scripts.

FPNN. Field Probing Neural Networks for 3D Data

Hospital. OpenPower工作组收集汇总的医院开放数据

RenderForCNN. Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views

image_shape_align. Matlab

cs231n.github.io. Public facing notes page

JointEmbedding. Joint Embeddings of Shapes and Images via CNN Image Purification