Lists (19)
Starred repositories
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
Sharp Monocular View Synthesis in Less Than a Second
Optimized Whisper models for streaming and on-device use
Optimizing Monocular Depth Estimation with TensorRT: Model Conversion, Inference Acceleration, and 3D Reconstruction
Metric depth estimation from a single image
A Rust library integrated with ONNXRuntime, providing a collection of Computer Vison and Vision-Language models such as YOLO, FastVLM, and more.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
An open source library for multiview geometry and structure from motion
Universal Monocular Metric Depth Estimation
DINO-X: The World's Top-Performing Vision Model for Open-World Object Detection and Understanding
CUDA accelerated rasterization of gaussian splatting
The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
[TPAMI 2024 & CVPR 2022] Attention Concatenation Volume for Accurate and Efficient Stereo Matching
A web frontend for the motion daemon.
An extension of Open3D to address 3D Machine Learning tasks
The fundamental package for scientific computing with Python.
Published by Packt
Contains the "pycocotools" package on PyPI. Changes made to the official cocoapi about packaging.
Continuation of an abandoned project fast-coco-eval
A Rust HTTP server for Python applications
Multi-platform high-performance compute language extension for Rust.
Fast and Universal 3D reconstruction model for versatile tasks
A Python-embedded DSL that makes it easy to write fast, scalable ML kernels with minimal boilerplate.
GHUStereo models are novel real-time stereo matching architectures with a low computation complexity characterized by compact cost volumes and Guided Hourglass Up-sampling (GHU) modules.