Guangchi Fang

my_opencode_skills. This repository collects my personal OpenCode skills for reusable research workflows.

my_codex_skills. This repository collects my personal Codex skills for reusable research workflows.

Interaction2Eval. HTML

mini-splatting2. Python

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

mini-splatting. Python

3dgs-mcmc. [NeurIPS 2024 Spotlight] Implementation of the paper "3D Gaussian Splatting as Markov Chain Monte Carlo"

GGSC. Code for "A Benchmark for Gaussian Splatting Compression and Quality Assessment Study"

Meshroom. Node-based Visual Programming Toolbox

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

ACRF. Python

camp_zipnerf. Python

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

PoissonRecon. Poisson Surface Reconstruction

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ControlNet. Let us control diffusion models!

DROID-SLAM. Python

instant-ngp. Instant neural graphics primitives: lightning fast NeRF and more

KinectFusionLib. Implementation of the KinectFusion approach in modern C++14 and CUDA

O-CNN. O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis

PoSFeat. [CVPR2022] Decoupling Makes Weakly Supervised Local Feature Better

LanguageGroundedSemseg. Implementation for ECCV 2022 paper Language-Grounded Indoor 3D Semantic Segmentation in the Wild

3D-point-capsule-networks. 3D Point Capsule Networks

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

ThreeDAC. Python

openmlsys. 《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）

Awesome-SLAM. A curated list of SLAM resources

spsg. C++

freemocap. Free Motion Capture for Everyone 💀✨

StyleSDF. Python

hmr-survey. [TPAMI 2023] Recovering 3D Human Mesh from Monocular Images: A Survey

resume. My resume in LaTeX (template suited for new graduates; 应届生简历模板)

neural-rgbd-surface-reconstruction. Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

banmo. BANMo Building Animatable 3D Neural Models from Many Casual Videos

best_AI_papers_2022. A curated list of the latest breakthroughs in AI (in 2022) by release date with a clear video explanation, link to a more in-depth article, and code.

ADOP. C++

dsrv-data. [ICPR 2022] Data, code and pretrained models for Deep Surface Reconstruction from Point Clouds with Visibility Information

panoptic-reconstruction. Official implementation of the NeurIPS 2021 paper "Panoptic 3D Scene Reconstruction from a Single RGB Image"

best_AI_papers_2021. A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.

OctField. Code for "OctField: Hierarchical Implicit Functions for 3D Modeling (NeurIPS 2021)"

GCN-Denoiser. Mesh denoising with graph convolutional networks

bolei_awesome_posters. CVPR and NeurIPS poster examples and templates

mmhuman3d. OpenMMLab 3D Human Parametric Model Toolbox and Benchmark

boundary-iou-api. Boundary IoU API (Beta version)

mix3d. Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)

meteornet. MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences (ICCV 2019 Oral)

SOAT. Official PyTorch repo for StyleGAN of All Trades: Image Manipulation with Only Pretrained StyleGAN.

psicnn. Octree guided cnn with spherical kernels for 3D point clouds

LOD_ordering_for_patches_of_points. This short project propose to order patches of points with a quad tree ordering, so as to permit instant and free level of details use of patch of points

SparsePadding. code release for paper "Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks"(ICCV 2021)

adaptive-surface-reconstruction. Adaptive Surface Reconstruction for 3D Data Processing

EasyMocap. Make human motion capture easier.

soma. Solving Optical MoCap Automatically

Reconstrution_Through_Moving_Water. Source code for 2021 ICCV paper "In-the-Wild Single Camera 3D Reconstruction Through Moving Water Surfaces"

mediapipe. Cross-platform, customizable ML solutions for live and streaming media.

vis2mesh. Vis2Mesh: Efficient Mesh Reconstruction from Unstructured Point Clouds of Large Scenes with Learned Virtual View Visibility ICCV2021

pixel-perfect-sfm. Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

snarf. Official code release for ICCV 2021 paper SNARF: Differentiable Forward Skinning for Animating Non-rigid Neural Implicit Shapes.

tsdf-fusion-python. Python code to fuse multiple RGB-D images into a TSDF voxel volume.

LastOrder-Dota2. Dota2 AI bot

dynamicfusion. Implementation of Newcombe et al. CVPR 2015 DynamicFusion paper

CV_Notes. 「3D视觉(三维重建、SLAM、AR/VR) + 传统图像处理 + 计算机视觉(偏AI) 」重要知识点和面试问题。

depth_clustering. :taxi: Fast and robust clustering of point clouds generated with a Velodyne sensor.

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

Awesome-CV. :page_facing_up: Awesome CV is LaTeX template for your outstanding job application

NeuralGraph. Official implementation for CVPR'2021 paper Neural Deformation Graphs

AffordanceNet. Python

rangecoder. a fast range coder in C++, using SSE

WaveCNet. the code for WaveCNet

integer_discrete_flows. Code release for Hoogeboom, Emiel, Jorn WT Peters, Rianne van den Berg, and Max Welling. "Integer Discrete Flows and Lossless Compression." Conference on Neural Information Processing Systems (2019).

RC-PyTorch. PyTorch code for the CVPR'20 paper "Learning Better Lossless Compression Using Lossy Compression"

taichi. Productive, portable, and performant GPU programming in Python.

RA-GFT. region adaptive graph fourier transform for 3d point clouds

transfuser. [PAMI'23] TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving; [CVPR'21] Multi-Modal Fusion Transformer for End-to-End Autonomous Driving

cwi-pcl-codec. Point Cloud Codec invented by Rufael Mekuria, based on PCL (Point Cloud Library)

deep-point-map-compression. Python

draco. Draco is a library for compressing and decompressing 3D geometric meshes and point clouds. It is intended to improve the storage and transmission of 3D graphics.

Point-cloud-compression-by-RNN. Implementation of Point Cloud Compression for 3D LiDAR Sensor using Recurrent Neural Network with Residual Blocks

map_compression. Implementation of: 3D LiDAR Map Compression for Efficient Localization on Resource Constrained Vehicles

Real-Time-Spatio-Temporal-LiDAR-Point-Cloud-Compression. This is a compression technique that targets for LiDAR-generated point cloud

read-learn-research.

RAHT. This code implements an improved version of the RAHT-rlgr coder and decoder as described by Queiroz and Chou.

raytracing.github.io. Main Web Site (Online Books)

Peter-Shirley-Ray-Tracing-in-one-weenkend. Ray Tracing 学习笔记

Tex-An_Mesh. Fully textured and animatable human body mesh reconstruction from a single image

Open-PIFuhd. This is an implementation of PIFuHD based on PyTorch

CVPR-2021-Papers.

SQN. SQN in Tensorflow (ECCV'2022)

nglod. Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapes (CVPR 2021 Oral)

SpinNet. [CVPR 2021] SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

pytorch_geometric. Graph Neural Network Library for PyTorch

blensor. Blender Sensor Simulation

SensatUrban. 🔥Urban-scale point cloud dataset (CVPR 2021 & IJCV 2022)

kitti_object_vis. KITTI Object Visualization (Birdview, Volumetric LiDar point cloud )

qec_net. Python

3D-CODED. Pytorch Implementation for the project : `3D-CODED` and `Learning Elementary Structure`

ToricCNN. Code for the SIGGRAPH 2017 paper "Convolutional Neural Networks on Surfaces via Seamless Toric Covers"

deepul. Jupyter Notebook

superpoint_graph. Large-scale Point Cloud Semantic Segmentation with Superpoint Graphs

leetcode. Provide all my solutions and explanations in Chinese for all the Leetcode coding problems.

pointnet. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation