An extremely fast Python type checker and language server, written in Rust.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"

View a Git Graph of your repository in Visual Studio Code, and easily perform Git actions from the graph.

Automated TDD enforcement for Claude Code

[CVPR 2025] DEFOM-Stereo: Depth foundation model based stereo matching

[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching

An extremely fast Python package and project manager, written in Rust.

Productive, portable, and performant GPU programming in Python.

CUDA accelerated rasterization of gaussian splatting

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Eglcr: Edge Structure Guidance and Scale Adaptive Attention for Iterative Stereo Matching(ACM MM24)

[TPAMI 2025 & CVPR 2023] Iterative Geometry Encoding Volume for Stereo Matching

Non-official Pytorch implementation of the CREStereo(CVPR 2022 Oral).

An extremely fast Python linter and code formatter, written in Rust.

[CVPR 2024 Highlight] Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching

An evaluation framework for machine learning models simulating high-throughput materials discovery.

Svelte masonry component with SSR support and column balancing

Sticky responsive table of contents component

Interactive browser visualizations for materials science: crystal structures/molecules, trajectories, convex hulls, phase diagrams, Fermi surfaces, bands+DOS, Brillouin zones, etc.

A toolkit for visualizations in materials informatics.

Accompanying library for the Record3D iOS app (https://record3d.app/). Allows you to receive RGBD stream from iOS devices with TrueDepth camera(s).

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8…

Using ARKit and LiDAR to save depth data and export point cloud, based on WWDC20-10611 sample code

Running large language models on a single GPU for throughput-oriented scenarios.

A latent text-to-image diffusion model