Xianghui

dimos. Dimensional is the agentic operating system for physical space. Command humanoids, quadrupeds, drones, and other hardware platforms in natural language and build multi-agent systems that work seamlessly with physical input (cameras, lidar, actuators).

research-skills. Claude Code skills for AI/ML researchers

LoGeR. Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

nanochat. The best ChatGPT that $100 can buy.

FrankenMotion-Code. [CVPR 2026] FrankenMotion: Part-level Human Motion Generation and Composition

mega-sam. Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

awesome-humanoid-robot-learning. A Paper List for Humanoid Robot Learning.

coma. Official Repository for ECCV 2024 paper Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models

Phy-SIC. [SIGGGRAPHASIA2025] PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image

pixel-perfect-depth. [NeurIPS 2025] Pixel-Perfect Depth

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

InterMimic. [CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions

RollingDepth. [CVPR 2025] RollingDepth: Video Depth without Video Models

Video-Depth-Anything. [CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

m-niemeyer.github.io. A lightweight and responsive website template that automatically crawls papers and talks from bibtex files

AIMLInterviews. This repo is meant to serve as a guide for Machine Learning/AI technical interviews.

semantic-segmentation-editor. Web labeling tool for bitmap images and point clouds

SV3D-fine-tune. Fine-tuning code for SV3D

2d-gaussian-splatting. [SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields

instant-nsr-pl. Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!

PufferLib. Puffing up reinforcement learning

CenterPose. Single-Stage Keypoint-based Category-level Object Pose Estimation from an RGB Image (ICRA 2022)

OpenGlass. Turn any glasses into AI-powered smart glasses

FoundationPose. [CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

fiftyone. Refine high-quality datasets and visual AI models

pytorch-openpose. pytorch implementation of openpose including Hand and Body Pose Estimation.

diffusion-extensions. Reference implmentation of Diffusion models on SO(3)

threestudio. A unified framework for 3D content generation.

CHORUS. Python

BayesDiff. Python

PoseExaminer. [CVPR23] PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation

Grad-PU. This is the official PyTorch implementation of our paper "Grad-PU: Arbitrary-Scale Point Cloud Upsampling via Gradient Descent with Learned Distance Functions" (CVPR 2023).

shape_as_points. [NeurIPS'21] Shape As Points: A Differentiable Poisson Solver

awesome-neurips-for-graphics.

Manifold. Convert any Triangle Mesh to Watertight Manifold

bedlam_clothing. Python

point-cloud-utils. An easy-to-use Python library for processing and manipulating 3D point clouds and meshes.

Curriculum-DeepSDF. Implementation for Curriculum DeepSDF

blendify. Lightweight Python framework that provides a high-level API for creating and rendering scenes with Blender.

3DFuse. Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"

colmap_utils. Python scripts and functions to work with COLMAP

PIP. A real-time system that captures physically correct human motion, joint torques, and ground reaction forces with only 6 inertial measurement units

Anything-3D. Segment-Anything + 3D. Let's lift anything to 3D.

zero123. Zero-1-to-3: Zero-shot One Image to 3D Object (ICCV 2023)

Track-Anything. Track-Anything is a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything, XMem, and E2FGVI.

torch-ngp. A pytorch CUDA extension implementation of instant-ngp (sdf and nerf), with a GUI.

transformer-inertial-poser. Python implementation accompanying the Transformer Inertial Poser paper at SIGGRAPH Asia 2022

3dpw-eval. Evaluation code for the workshop "3D Pose Estimation in the Wild" held in conjunction with ECCV 2020

InterCap. Source code for the GCPR 2022 paper: <InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction>

multiperson. Code repository for the paper: "Coherent Reconstruction of Multiple Humans from a Single Image" in CVPR'20

Neighborhood-Attention-Transformer. Neighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022

averaging-quaternions. Python function for correct averaging of multiple quaternions

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

awesome-6d-object. Awesome work on object 6 DoF pose estimation

Awesome-Transformer-Attention. An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

RegTR. End-to-end Point Cloud Correspondences with Transformers

DPFM. Pytorch code for "DPFM: Deep Partial Functional Maps" - 3DV 2021 (Oral)

pyFM. Python implementation of Functional Maps

Diff-FMAPs-PyTorch. Jupyter Notebook

ClothWild_RELEASE. [ECCV 2022] This repo is official PyTorch implementation of 3D Clothed Human Reconstruction in the Wild.

FBCNN. Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"

occlusions-4d. Revealing Occlusions with 4D Neural Fields (CVPR 2022 Oral) - Official Implementation

gangealing. Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

OnePose. Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

BackgroundMattingV2. Real-Time High-Resolution Background Matting

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

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

ss3d. Code release for "Pre-train, Self-train, Distill A simple recipe for Supersizing 3D Reconstruction"

STCN. [NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

HMMN. Hierarchical Memory Matching Network for Video Object Segmentation (ICCV 2021)

GDR-Net. GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation. (CVPR 2021)

AdelaiDepth. This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.

awesome-semi-supervised-learning. 😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

tdw. ThreeDWorld simulation environment

BPnP. Back-propagatable PnP

blender-cli-rendering. Blender Python scripts for rendering images directly from command-line interface

pkget. Install packages on any Debian based Linux distro without root or installing it on the entire system

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

mesh-fusion. Python tool for obtaining watertight meshes using TSDF fusion.

awesome-implicit-representations. A curated list of resources on implicit neural representations.

3d-bat. 3D Bounding Box Annotation Tool (3D-BAT) Point cloud and Image Labeling

scalabel. Scalabel: A versatile web-based visual data annotation tool

PRML-Solution-Manual. My Own Solution Manual of PRML

human_body_prior. VPoser: Variational Human Pose Prior

PIFu. This repository contains the code for the paper "PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization"

ndf. Neural Unsigned Distance Fields (NDF) - Codebase

holistic_scene_human. Python

frankmocap. A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator

smplify-x. Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

neural_renderer. "Neural 3D Mesh Renderer" (CVPR 2018) by H. Kato, Y. Ushiku, and T. Harada.

bps. Efficient Learning on Point Clouds with Basis Point Sets

torch-mesh-isect. Cuda

smplx. SMPL-X

IPNet. Repo for "Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction, ECCV'20(Oral)""

cs-video-courses. List of Computer Science courses with video lectures.

prox. Resolving 3D Human Pose Ambiguities with 3D Scene Constraints https://prox.is.tue.mpg.de

DenseDepth. High Quality Monocular Depth Estimation via Transfer Learning

monodepth2. [ICCV 2019] Monocular depth estimation from a single image

crfasrnn_pytorch. CRF-RNN PyTorch version http://crfasrnn.torr.vision

GrabNet. GrabNet: A Generative model to generate realistic 3D hands grasping unseen objects (ECCV2020)

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

Recent-Stars-2025. 🔥SLAM, VIsual localization, keypoint detection, Image matching, Pose/Object tracking, Depth/Disparity/Flow Estimation, 3D-graphic, etc. related papers and code

VolumetricCapture. A multi-sensor capture system for free viewpoint video.

probreg. Python package for point cloud registration using probabilistic model (Coherent Point Drift, GMMReg, SVR, GMMTree, FilterReg, Bayesian CPD)

PointGroup. PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation

jsis3d. [CVPR'19] JSIS3D: Joint Semantic-Instance Segmentation of 3D Point Clouds

Total3DUnderstanding. Implementation of CVPR'20 Oral: Total3DUnderstanding: Joint Layout, Object Pose and Mesh Reconstruction for Indoor Scenes from a Single Image

meshrcnn. code for Mesh R-CNN, ICCV 2019

LoopReg. Python

RGBD-to-Mesh. Converts RGBD images from Kinect sensor to a triangle mesh representation.Final Project for CIS565.

cvpr2018-shape-completion. CVPR 2018 paper "Learning 3D Shape Completion from Laser Scan Data with Weak Supervision".

phosa. Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild

CS251. This contains the source code examples and programming assignments for my CS 251 class

algorithms-sedgewick-wayne. Solutions to all the exercises of the Algorithms book by Robert Sedgewick and Kevin Wayne

DeployDjango. Instantly deploy your Django Apps!

fullstack-course4. Example code for HTML, CSS, and Javascript for Web Developers Coursera Course

pi4j-v1. DEPRECATED Java I/O library for Raspberry Pi (GPIO, I2C, SPI, UART)

mir_eval. Evaluation functions for music/audio information retrieval/signal processing algorithms.

voice-splitting. A Java project which is able to split MIDI performance data into monophonic voices.

1.1. MIDI toolbox 1.1 (2016) is a collection of Matlab functions to analyse MIDI files

met-align. A model for meter detection and alignment from live performance MIDI data.

madmom. Python audio and music signal processing library

BTrack. A Real-Time Beat Tracker

CSAPP-Labs. :computer: Computer Systems: A Programmer's Perspective, Lab Assignments Solutions

PConv-Keras. Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai

Apollo-11. Original Apollo 11 Guidance Computer (AGC) source code for the command and lunar modules.

scrcpy. Display and control your Android device

UnityNativeShare. A Unity plugin to natively share files (images, videos, documents, etc.) and/or plain text on Android & iOS

oidv4-toolkit-tfrecord-generator. Generate TFRecord for images downloaded using EscVM/OIDv4_ToolKit

tfrecords. Functions for creating tfrecords for TensorFlow models.

OIDv4_ToolKit. Download and visualize single or multiple classes from the huge Open Images v4 dataset

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.

zoomage. A simple pinch-to-zoom ImageView library for Android

OCRTextRecognitionAndroidApp. Java

cs231n. cs231n assignments sovled by https://ghli.org

cs231n.github.io. Public facing notes page

Java-Text-To-Speech-Tutorial. Java+MaryTTS=Java Text To Speech

java-google-speech-api. 🙊 Speech Recognition , Text To Speech , Google Translate