[CVPR'26] Official code for the paper "VGG-T³: Offline Feed-Forward 3D Reconstruction at Scale"

[ICLR 2026] A simple state update rule to enhance length generalization for CUT3R

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

[CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

An MIT License of YOLOv9, YOLOv7, YOLO-RD

The official repository for the paper "Optimal Flow Matching: Learning Straight Trajectories in Just One Step" (NeurIPS 2024)

ncnn is a high-performance neural network inference framework optimized for the mobile platform

My arr stack. Hardened Docker Compose config for Jellyfin + Sonarr/Radarr + qBittorrent with VPN namespace isolation and zero-trust ingress.

[ICCV-2025] TurboReg: TurboClique for Robust and Efficient Point Cloud Registration

Volumetric structures such as voxels and SDFs implemented in pytorch

Simple, lightweight, extensible DAG framework for Python with a Kubeflow-like API

[CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

Build a version works on cuda 12.x with RTX 50 series GPU. [SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconst…

A set of lightweight Docker images for building LaTeX documents

Real Spherical Harmonics for PyTorch

Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.

Computer Vision ML inference in C++

PanSt3R: Multi-view Consistent Panoptic Segmentation (official code)

Simple routing over OpenStreetMap data

Low cost motion capture system for room scale tracking

The CImg Library is a small and open-source C++ toolkit for image processing

Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

Dr.Jit — A Just-In-Time-Compiler for Differentiable Rendering

Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

Draw any shape from an image by Fourier transform using only Matplotlib.

Inference Vision Transformer (ViT) in plain C/C++ with ggml

Super Strong and Fast Othello AI / Computer Othello Reversi