代码库
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
Python
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 model.
Python
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Python
[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"
Jupyter Notebook
on-device-aisam2segment-anything
WybeCoder Verified Generation of Imperative Code with LLMs
Python
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
Python
PyTorch code and models for the DINOv2 self-supervised learning method.
Jupyter Notebook
A Python framework for AI-driven character animation using neural networks.
Python
Library for fast text representation and classification.
HTML
TestGenEval A Real World Unit Test Generation and Test Completion Benchmark
Python
Official repository for PALM, a scan-based dataset with 263 subjects, including 13k registered 3dMD scans and 90k calibrated multiview RGB images.
Python
Code for the Boxer research paper
Python
Official implementation of the paper "Watermark Anything with Localized Messages"
Jupyter Notebook
imageimage-watermarkingwatermarking
SAM 3D Objects
Python
An Open-source Streaming High-fidelity Neural Audio Codec
Python
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Python
3d-reconstructionaicalibrationdepth-completiondepth-estimationimage-to-3dmulti-view-stereoroboticssfm
Per-Pixel Classification is Not All You Need for Semantic Segmentation (NeurIPS 2021, spotlight)
Python
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Jupyter Notebook
Reference PyTorch implementation and models for DINOv3
Jupyter Notebook
Efficient 3D human pose estimation in video using 2D keypoint trajectories
Python