Stars
Open-source NURBS surface modeller — a Rhino-style freeform modeller on the OpenCASCADE kernel, with AI-native MCP integration
Formally verified 3D mesh intersection - trust 93 lines of spec, not 1000+ lines of AI-written code
Download and decode functions for NEXRAD radar data.
Open-source and extensible radar mosaic creation in Python
A benchmark for AI-driven CAD generation and editing
A very fast SIMD-first image comparison library (with nodejs API)
A library of agent skills for CAD, CAE and CAM
Javascript implementation of Slug font loading and rendering, for THREEJS
Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.
Public code release associated with SceneScript.
[CVPR 2023] RoomFormer: Two-level Queries for Single-stage Floorplan Reconstruction
This repository is an official implementation of the paper "SymPoint Revolutionized: Boosting Panoptic Symbol Spotting with Layer Feature Enhancement".
A tiny, single-header <canvas>-like 2D rasterizer for C++
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
[CVPR 2025] Official code repository for "MaSS13K: A Matting-level Semantic Segmentation Benchmark"
Awesome-LLM-3D: a curated list of Multi-modal Large Language Model in 3D world Resources
Exploring variational-autoencoder-based semantic segmentation for analyzing CT-scans.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
[CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).
The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .
This repo is the official implementation of iSeg: An Iterative Refinement-based Framework for Training-free Segmentation.
A Node JS module to read music files from iRealPro.
[CVPR 2023] OneFormer: One Transformer to Rule Universal Image Segmentation