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.
☆256Updated 2 months ago
Related projects: ⓘ
- [CVPR 2024] Code release for "Unsupervised Universal Image Segmentation"☆163Updated 4 months ago
- [NeurIPS'23] Emergent Correspondence from Image Diffusion☆586Updated 4 months ago
- Code release for "Segment Anything without Supervision"☆278Updated 2 months ago
- This is the official code release for our work, Denoising Vision Transformers.☆275Updated last month
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆435Updated 2 months ago
- DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight)☆343Updated last week
- PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.☆371Updated 4 months ago
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆274Updated 3 weeks ago
- Learning from synthetic data - code and models☆293Updated 8 months ago
- [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"☆260Updated 6 months ago
- 1-shot image segmentation using Stable Diffusion☆118Updated 6 months ago
- ☆189Updated 10 months ago
- Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.☆168Updated 2 months ago
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆504Updated 4 months ago
- SlimSAM: 0.1% Data Makes Segment Anything Slim☆270Updated 6 months ago
- Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders☆86Updated last month
- Official repository for "AM-RADIO: Reduce All Domains Into One"☆605Updated this week
- When do we not need larger vision models?☆314Updated last month
- A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)☆252Updated 3 weeks ago
- Open source implementation of "Vision Transformers Need Registers"☆126Updated last week
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆371Updated 5 months ago
- Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]☆846Updated 2 months ago
- Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".☆375Updated 2 years ago
- ☆55Updated 3 months ago
- [ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance☆93Updated 3 weeks ago
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆292Updated 3 months ago
- [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…☆500Updated 9 months ago
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆365Updated 4 months ago
- Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.☆166Updated last year
- [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation☆349Updated last year