[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
OTHER License
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
SenseTime Research platform for single object tracking, implementing algorithms like SiamRPN and ...
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
[CVPR 2024 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Te...
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at...
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
[CVPR2024 Highlight]GLEE: General Object Foundation Model for Images and Videos at Scale
Background Matting: The World is Your Green Screen
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多...
Automated dense category annotation engine that serves as the initial semantic labeling for the S...
Track-Anything is a flexible and interactive tool for video object tracking and segmentation, bas...
Segment Anything in High Quality [NeurIPS 2023]
Stable Video Diffusion Training Code and Extensions.
Official repo for VGen: a holistic video generation ecosystem for video generation building on di...