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

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

The code contains updated files to sucessfully compile Minkowski engine to latest cuda and pytorch versions

The reference implementaiton for the paper "Deep Geometric Prior for Surface Reconstruction"

Official Implementation for "Pivotal Tuning for Latent-based editing of Real Images" (ACM TOG 2022) https://arxiv.org/abs/2106.05744

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

[arXiv 2025] ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models

Code release of "Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion".

[ICLR 2026] PartSAM: A Scalable Promptable Part Segmentation Model Trained on Native 3D Data

[ICCV 2025] From anything to mesh like human artists. Official impl. of "MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization"

A curated list of awesome 3D generation resources, papers, and tools for AI-powered 3D content creation.

A header-only, very efficient 2D rectangle packing library. Used in Assassin's Creed, Snapchat and Skydio drones. 2 scientific references.

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Tool for robust segmentation of >100 important anatomical structures in CT and MR images

Spec-driven development (SDD) for AI coding assistants.

An elegant PyTorch deep reinforcement learning library.

dcm2nii DICOM to NIfTI converter: compiled versions available from NITRC

Native and Compact Structured Latents for 3D Generation

Mesh tools.

Cuda mesh utils.

[PG2025] PaMO: Parallel Mesh Optimization for Intersection-Free Low-Poly Modeling on the GPU

Pose estimation refiner

C++ Implementation of the SQPnP algorithm

[CVPR 2022 Best Student Paper] EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation

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

[ICLR 2026] Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models