Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.
APACHE-2.0 License
Benchmarking Panoptic Scene Graph Generation (PSG), ECCV'22
PyTorch codes for "Progressive Semantic-Aware Style Transformation for Blind Face Restoration", C...
[ICCV 2023] Tracking Anything with Decoupled Video Segmentation
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
The Most Faithful Implementation of Segment Anything (SAM) in 3D
[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at...
[CVPR 2024 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Te...
Automated dense category annotation engine that serves as the initial semantic labeling for the S...
Segment-Anything + 3D. Let's lift anything to 3D.
Code release for "Masked-attention Mask Transformer for Universal Image Segmentation"
Group R-CNN for Point-based Weakly Semi-supervised Object Detection (CVPR2022)
Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)
Segment Anything in High Quality [NeurIPS 2023]
Inpaint Anything performs stable diffusion inpainting on a browser UI using masks from Segment An...
Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"