google / diffsegLinks
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.
☆311Updated 10 months ago
Alternatives and similar repositories for diffseg
Users that are interested in diffseg are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Code release for "Segment Anything without Supervision"☆470Updated last week
- [CVPR 2024] Code release for "Unsupervised Universal Image Segmentation"☆202Updated last year
- Official implementation of 'CLIP-DINOiser: Teaching CLIP a few DINO tricks' paper.☆248Updated 7 months ago
- [ECCV'24] Official Implementation of SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidance☆133Updated this week
- [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…☆526Updated last year
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆492Updated 7 months ago
- [NeurIPS'23] Emergent Correspondence from Image Diffusion☆695Updated last year
- RobustSAM: Segment Anything Robustly on Degraded Images (CVPR 2024 Highlight)☆350Updated 9 months ago
- This is the official code release for our work, Denoising Vision Transformers.☆361Updated 6 months ago
- 1-shot image segmentation using Stable Diffusion☆137Updated last year
- This is Pytorch Implementation Code for adding new features in code of Segment-Anything. Here, the features support batch-input on the fu…☆154Updated last year
- [NeurIPS2023] Code release for "Hierarchical Open-vocabulary Universal Image Segmentation"☆288Updated last year
- Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)☆566Updated last year
- Official PyTorch implementation of ODISE: Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models [CVPR 2023 Highlight]☆913Updated 10 months ago
- [CVPR 2023] Official repository of Generative Semantic Segmentation☆215Updated last year
- PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.☆429Updated last year
- Holds code for our CVPR'23 tutorial: All Things ViTs: Understanding and Interpreting Attention in Vision.☆192Updated last year
- Official Implementation of paper "A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence"☆309Updated last year
- A PyTorch implementation of the paper "ZigMa: A DiT-Style Mamba-based Diffusion Model" (ECCV 2024)☆314Updated 2 months ago
- CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks☆422Updated 3 months ago
- Connecting segment-anything's output masks with the CLIP model; Awesome-Segment-Anything-Works☆193Updated 7 months ago
- Learning from synthetic data - code and models☆315Updated last year
- Official implementation for the paper "Deep ViT Features as Dense Visual Descriptors".☆440Updated 2 years ago
- ☆157Updated 2 years ago
- A Simple Latent Diffusion Approach for Panoptic Segmentation and Mask Inpainting [ECCV 2024]☆87Updated last year
- Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation (NeurIPS2023)☆121Updated 8 months ago
- Combining Segment Anything (SAM) with Grounded DINO for zero-shot object detection and CLIPSeg for zero-shot segmentation☆409Updated last year
- Open source implementation of "Vision Transformers Need Registers"☆177Updated last month
- SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process☆188Updated last year
- Low rank adaptation for segmentation anything model (SAM)☆225Updated last year