google / diffseg
DiffSeg is an unsupervised zero-shot segmentation method using attention information from a stable-diffusion model. This repo implements the main DiffSeg algorithm and additionally includes an experimental feature to add semantic labels to the masks based on a generated caption.
☆308Updated 9 months ago
Alternatives and similar repositories for diffseg:
Users that are interested in diffseg are comparing it to the libraries listed below
- [NeurIPS 2024] Code release for "Segment Anything without Supervision"☆461Updated 7 months ago
- [CVPR 2024] Code release for "Unsupervised Universal Image Segmentation"☆199Updated 11 months ago
- Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.☆244Updated 6 months ago
- This is the official code release for our work, Denoising Vision Transformers.☆362Updated 5 months ago
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆348Updated 8 months ago
- 1-shot image segmentation using Stable Diffusion☆138Updated last year
- [ICCV 2023] VPD is a framework that leverages the high-level and low-level knowledge of a pre-trained text-to-image diffusion model to do…☆524Updated last year
- Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]☆901Updated 10 months ago
- [ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance☆130Updated 2 weeks ago
- Low rank adaptation for segmentation anything model (SAM)☆222Updated last year
- [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"☆286Updated last year
- Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"☆402Updated last month
- [CVPR 2023] Official repository of Generative Semantic Segmentation☆213Updated last year
- [NeurIPS'23] Emergent Correspondence from Image Diffusion☆684Updated 11 months ago
- Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works☆192Updated 6 months ago
- [NeurIPS 2024] SlimSAM: 0.1% Data Makes Segment Anything Slim☆328Updated 2 months ago
- PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.☆427Updated 11 months ago
- SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)☆229Updated last month
- Official Implementation of Semantic Image Synthesis via Diffusion Models☆244Updated 2 years ago
- Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.☆186Updated last year
- A collection of project, papers, and source code for Meta AI's Segment Anything Model (SAM) and related studies.☆351Updated 4 months ago
- DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual A…☆479Updated last month
- Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders☆108Updated 3 weeks ago
- Open-vocabulary Semantic Segmentation☆342Updated 6 months ago
- CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks☆415Updated 2 months ago
- Learning from synthetic data - code and models☆315Updated last year
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆408Updated last year
- Official code for "TOAST: Transfer Learning via Attention Steering"☆189Updated last year
- [CVPR 2025 Highlight] Official code and models for Encoder-only Mask Transformer (EoMT).☆125Updated this week
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆404Updated last year