Tianshu Kuai

Claude-of-Duty. A Call of Duty-quality FPS in Three.js, built from a single prompt.

BS-Cloth. [SIGGRAPH 2026] Codebase for our paper "Efficient B-Spline Finite Elements for Cloth Simulation"

pymupdf4llm. PyMuPDF4LLM

GPU_IPC. This is the first fully GPU Optimized IPC framework

TensorMesh. A fast, differentiable, JIT-free, debugging-friendly finite element library for PyTorch.

one_shot_wn. C++

antipodal. C++

Matern-FM-data. Data generation scripts used in Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes

Matern-FM. [SIGGRAPH 2026] Matérn Noise for Triangulation-Agnostic Flow Matching on Meshes

Pixal3D. [SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images

LaTeX-Workshop. Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

Academic-project-page-template. A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

Paper2Code. Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

claude-howto. A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.

omages. [3DV 2025 Best Paper] We present Object Images (Omages): An homage to the classic Geometry Images.

autoresearch. AI agents running research on single-GPU nanochat training automatically

modern-software-dev-assignments. Assignments for CS146S: The Modern Software Dev (Stanford University Fall 2025)

Awesome-World-Models. A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

potpourri3d. An invigorating blend of 3D geometry tools in Python.

blender-mcp. Open-source MCP to use Blender with any LLM

TorchLeet. Leetcode for Pytorch

TRELLIS.2. Native and Compact Structured Latents for 3D Generation

LeetCUDA. LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.

anny. Anny, A Free and Interpretable Human Body Model for all ages, written in PyTorch.

sam-3d-objects. SAM 3D Objects

neural-function-distributions. Pytorch implementation of Generative Models as Distributions of Functions 🌿

fTetWild. Fast Tetrahedral Meshing in the Wild

riemannian-fm. code for "Riemannian Flow Matching on General Geometries".

mfem. C++

openpi. Python

embody-3d. Tools for the Embody 3D Dataset

composition_rendering. Python

RAE. Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

robot-learning-tutorial. All the source code for "Robot Learning: A Tutorial". Get involved to be featured in the next iteration!

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

MANO. A PyTorch Implementation of MANO hand model.

tinyworlds. A minimal implementation of DeepMind's Genie world model

Motion-X. [NeurIPS 2023] Official implementation of the paper "Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset"

Hunyuan3D-Omni. Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

Hunyuan3D-Part. Hunyuan 3D Part Segmentation and Generation Pipeline

torch_mesh_ops. PyTorch CUDA extension for fast construction of discrete differential operators on triangle meshes

poissonnet. Official repository for "PoissonNet: A Local-Global Approach for Learning on Surfaces"

HumanML3D. HumanML3D: A large and diverse 3d human motion-language dataset.

awesome-3d-4d-world-models. [TPAMI 2026] 3D and 4D World Modeling: A Survey

mesh2motion-app. Import a 3D Model and automatically assign and export animations

Puppeteer. [NeurIPS 2025 Spotlight] Official repository for “Puppeteer: Rig and Animate Your 3D Models”

dinov3. Reference PyTorch implementation and models for DINOv3

WorldGen. 🌍 WorldGen - Generate Any 3D Scene in Seconds

TexVerse. Official Repo of TexVerse: A Universe of 3D Objects with High-Resolution Textures

awesome-flow-matching. A summary of related works about flow matching, stochastic interpolants

ai-toolkit. The ultimate training toolkit for finetuning diffusion models

minFM. HTML

DT-BFR. [WACV 2025 (Oral)] Towards Unsupervised Blind Face Restoration using Diffusion Prior

HunyuanWorld-1.0. Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels with Hunyuan3D World Model

FLAME_PyTorch. This is a implementation of the 3D FLAME model in PyTorch

FLAME-Universe. Summary of publicly available ressources such as code, datasets, and scientific papers for the FLAME 3D head model

diffusion-pipe. A pipeline parallel training script for diffusion models.

torchtitan. A PyTorch native platform for training generative AI models

polyscope. A C++ & Python viewer for 3D data like meshes and point clouds

MotionMillion-Codes. Python

AnimateAnyMesh. [ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

panopti. Interactive 3D visualization in Python

robust-laplacians-py. Build high-quality Laplace matrices on meshes and point clouds in Python. Implements [Sharp & Crane SGP 2020].

minRF. Minimal implementation of scalable rectified flow transformers, based on SD3's approach

TripoSG. TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Anytop. Character Animation Diffusion with Any Topology

PnP-Flow. Code for PnP-Flow: Plug-and-Play image restoration with Flow Matching (ICLR 2025)

CSC417-physics-based-animation. Homepage for CSC417: Physics-based Animation

Vscode-Debug-Python-on-Slurm. An easy way for debug python for Slurm HPC users.

BlenderToolbox. Some simple Blender scripts for rendering paper figures

cholespy. An easily integrable Cholesky solver on CPU and GPU

csGraduateFellowships. A curated list of fellowships for graduate students in Computer Science and related fields.

discretization-robust-correspondence-benchmark. Benchmark for the generalization of 3D machine learning models across different remeshing/samplings of a surface.

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

bpy-renderer. Python package for rendering 3D scenes and animations using blender.

GaussianAnything. High-quality and editable surfel 3D Gaussian generation through native 3D diffusion (ICLR 2025)

SiT. Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

visionbook. <Foundations of Computer Vision> Book

wandb. The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

MeshUp. Python

torch_sparse_solve. A sparse KLU solver for PyTorch.

perception_models. State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!

omegaconf. Flexible Python configuration system. The last one you will ever need.

3DTopia-XL. [CVPR 2025 Highlight] 3DTopia-XL: High-Quality 3D PBR Asset Generation via Primitive Diffusion

NeuralJacobianFields. Python

InstantMesh. InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

diffusion-net. Pytorch implementation of DiffusionNet for fast and robust learning on 3D surfaces like meshes or point clouds.

PointFlowRenderer. Code for rendering the point cloud figures in paper: "PointFlow : 3D Point Cloud Generation with Continuous Normalizing Flows"

MeshXL. [NeurIPS 2024] MeshXL: Neural Coordinate Field for Generative 3D Foundation Models, a 3D fundamental model for mesh generation

zombie. Grid-Free Monte Carlo Solvers for Physics Simulations Involving Partial Differential Equations

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

OpenLRM. An open-source impl. of Large Reconstruction Models

diffvg. Differentiable Vector Graphics Rasterization

vtracer. Raster to Vector Graphics Converter

Awesome-AIGC-3D. A curated list of awesome AIGC 3D papers

cosmos. NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

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

flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

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

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

ST-SLidR. Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss (CVPR 2023)

siren. Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

gpytoolbox. A collection of utility functions to prototype geometry processing research in python

meshes. A repository with a variety of meshes with minimal licensing requirements.

geometry-processing. Course material for a grad-level course in Geometry Processing.

common-3d-test-models. Repository containing common 3D test models in original format with original source if known and obj mesh

libigl-python-bindings. libigl python bindings

TextDeformer. Python

nvdiffrast. Nvdiffrast - Modular Primitives for High-Performance Differentiable Rendering

APAP. The reference implementation of As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors (CVPR 2024).

sgi-introduction-course. A course for getting started with geometry processing using Python, Gpytoolbox, and Polyscope

geometry-processing-research-in-python. Geometry processing research tutorial in python - as presented at SGP 2024.

objaverse-xl. 🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

MeshAnything. [ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

meshgpt-pytorch. Implementation of MeshGPT, SOTA Mesh generation using Attention, in Pytorch

IF. Python

learning_research. 本人的科研经验

kaolin. A PyTorch Library for Accelerating 3D Deep Learning Research

awesome-3d-diffusion. A collection of papers on diffusion models for 3D generation.

MeshDiffusion. Official implementation of "MeshDiffusion: Score-based Generative 3D Mesh Modeling" (ICLR 2023 Spotlight)

GShell. Official implentation of "Ghost on the Shell: An Expressive Representation of General 3D Shapes" (ICLR 2024 Oral)

nvdiffrec. Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and Lighting From Images".

Diffusion-Models-Papers-Survey-Taxonomy. Diffusion model papers, survey, and taxonomy

libcom. Image composition toolbox: everything you want to know about image composition/compositing or object/subject insertion/addition/compositing.

viser. Web-based 3D visualization in Python

dreamgaussian. [ICLR 2024 Oral] Generative Gaussian Splatting for Efficient 3D Content Creation

Awesome-Video-Diffusion. A curated list of recent diffusion models for video generation, editing, and various other applications.

awesome-grad-school. 🎓 Advice and resources for thriving and surviving graduate school

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

GaussianEditor. [CVPR 2024] GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

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.

awesome_lists. Awesome Lists for Tenure-Track Assistant Professors and PhD students. (助理教授/博士生生存指南)

SegmentAnythingin3D. Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)

GAMES-105. Python

Awesome-diffusion-model-for-image-processing. one summary of diffusion-based image processing, including restoration, enhancement, coding, quality assessment

DMRF. Dynamic Mesh-Aware Radiance Fields (ICCV2023): Raytracing rendering and interactive simulating mesh with NeRF

awesome-nerf-editing. 🧙🏻‍♂️A list of papers curated for you to dive into the Awesome Radiance Field-based 3D Editing.

nerf_and_beyond_docs.

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

awesome-scene-representation. A curated list of awesome scene representation(NeRFs) papers, code, and resources.

prompt-to-prompt. Jupyter Notebook

threestudio. A unified framework for 3D content generation.

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

InverseRenderingOfIndoorScene. Python

phd-master-application-docs. A collection of the application documents I used to apply to universities in the US.

TensoIR. [CVPR 2023] TensoIR: Tensorial Inverse Rendering

nerfactor. Neural Factorization of Shape and Reflectance Under an Unknown Illumination

guided-diffusion. Python

KAIR. Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

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

co3d. Tooling for the Common Objects In 3D dataset.

Inpaint-Anything. Inpaint anything using Segment Anything and inpainting models.

instruct-nerf2nerf. Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

lerf. Code for LERF: Language Embedded Radiance Fields

dinov2. PyTorch code and models for the DINOv2 self-supervised learning method.

camm. CAMM: Building Category-Agnostic and Animatable 3D Models from Monocular Videos

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.

debugpy. An implementation of the Debug Adapter Protocol for Python

nerf_template. a simple template for practicing NeRF.

gpt_academic. 为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, moss等。

awesome-tips.

nerfshop. NeRFshop: Interactive Editing of Neural Radiance Fields

Awesome-CVPR2024-Low-Level-Vision. A Collection of Papers and Codes in CVPR2023/2022 about low level vision

nerf2mesh. [ICCV2023] Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement

composer. Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

d2nerf. Jupyter Notebook

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

STEGO. Unsupervised Semantic Segmentation by Distilling Feature Correspondences

DriveAndSegment. JavaScript

pix2pix3D. pix2pix3D: Generating 3D Objects from 2D User Inputs

ControlNet. Let us control diffusion models!

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

PaddleSeg. Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

HDNet. This is the implementation of paper 'Hierarchical Dynamic Image Harmonization' (ACM MM'2023, Oral).

DSNeRF. Code release for DS-NeRF (Depth-supervised Neural Radiance Fields)

CutLER. Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

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

instruct-pix2pix. Python

S2CRNet. Python

DCCF. Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization (ECCV 22)

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

TensoRF. [ECCV 2022] Tensorial Radiance Fields, a novel approach to model and reconstruct radiance fields

DirectVoxGO. Direct voxel grid optimization for fast radiance field reconstruction.

ngp_pl. Instant-ngp in pytorch+cuda trained with pytorch-lightning (high quality with high speed, with only few lines of legible code)

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

sparsefusion. [CVPR 2023] SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction

sdfstudio. A Unified Framework for Surface Reconstruction

diffusion-models-class. Materials for the Hugging Face Diffusion Models Course

NeRF-Art. NeRF-Art: Text-Driven Neural Radiance Fields Stylization

latent-nerf. Official Implementation for "Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures"

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

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

nerfstudio. A collaboration friendly studio for NeRFs

stable-dreamfusion. Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

A-Survey-on-Generative-Diffusion-Model.

nerfies.github.io. JavaScript

MotionDiffuse. MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model

NSDP. The official implementation for NeurIPS 2022 Spotlight Neural Shape Deformation Priors