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.
☆269Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for diffseg
- [CVPR 2024] Code release for "Unsupervised Universal Image Segmentation"☆175Updated 6 months ago
- [NeurIPS 2024] Code release for "Segment Anything without Supervision"☆420Updated last month
- Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.☆214Updated 3 weeks ago
- 1-shot image segmentation using Stable Diffusion☆127Updated 8 months ago
- PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.☆393Updated 6 months ago
- [NeurIPS'23] Emergent Correspondence from Image Diffusion☆618Updated 6 months ago
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆457Updated 3 weeks ago
- Learning from synthetic data - code and models☆303Updated 10 months ago
- This is the official code release for our work, Denoising Vision Transformers.☆319Updated last week
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆312Updated 2 months ago
- DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data (NeurIPS 2023 Spotlight) / / / / When Does Perceptual A…☆394Updated last week
- Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]☆858Updated 4 months ago
- Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think. Accepted to WACV 2025 and NeurIPS AFM Workshop.☆334Updated this week
- ☆196Updated last year
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆526Updated 6 months ago
- Official Implementation of the CrossMAE paper: Rethinking Patch Dependence for Masked Autoencoders☆93Updated 3 months ago
- Open-vocabulary Object Segmentation with Diffusion Models☆172Updated last year
- [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"☆271Updated 8 months ago
- Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"☆312Updated this week
- A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)☆275Updated this week
- [ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance☆111Updated 2 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…☆509Updated 11 months ago
- Official PyTorch implementation of the paper "In-Context Learning Unlocked for Diffusion Models"☆379Updated 7 months ago
- [ICML 2024 Spotlight] FiT: Flexible Vision Transformer for Diffusion Model☆389Updated last week
- PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.☆97Updated 7 months ago
- Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆664Updated this week
- Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch☆250Updated 3 months ago
- The official implementation of DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis☆158Updated 4 months ago
- Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works☆178Updated last month
- Open source implementation of "Vision Transformers Need Registers"☆143Updated last week