haibingtown / segment-mattingLinks
Segment Matting is a project aimed at improving the quality and performance of image matting using the SAM (Segment Anything Model) model. It focuses on optimizing the matting process to reduce jagged edges and improve the overall accuracy of the segmentation.
☆68Updated last year
Alternatives and similar repositories for segment-matting
Users that are interested in segment-matting are comparing it to the libraries listed below
Sorting:
- Image Editing Anything☆116Updated 2 years ago
- Codebase for the Recognize Anything Model (RAM)☆85Updated last year
- ☆69Updated last year
- A simple Segment Anything WebUI based on Gradio.☆81Updated 2 years ago
- Simple static web-based mask drawer, supporting semantic segmentation and video segmentation with interactive Segment Anything Model 2 (S…☆390Updated last year
- Another matter.☆64Updated 7 months ago
- Meta's Segment Anything Model (SAM) Demo Site☆151Updated 2 years ago
- ☆104Updated last year
- Diffusers training with mmengine☆101Updated last year
- Matting by Generation☆36Updated last year
- Multi-view Aggregation Network for Dichotomous Image Segmentation (CVPR24, Highlight)☆176Updated 7 months ago
- [CVPR 2025] Official code repository for "MaSS13K: A Matting-level Semantic Segmentation Benchmark"☆46Updated 4 months ago
- One-Trimap Video Matting (ECCV 2022)☆83Updated last year
- VimTS: A Unified Video and Image Text Spotter☆78Updated 11 months ago
- Image Prompter for Gradio☆91Updated last year
- TEED: Tiny and Efficient Edge Detector☆227Updated 2 years ago
- Add MobileSAM support for Inpaint anything using Segment Anything and inpainting models.☆54Updated 2 years ago
- MuLan: Adapting Multilingual Diffusion Models for 110+ Languages (无需额外训练为任意扩散模型支持多语言能力)☆140Updated 8 months ago
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆24Updated 2 years ago
- [CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting☆75Updated 9 months ago
- This is an implementation of zero-shot instance segmentation using Segment Anything.☆312Updated 2 years ago
- [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces☆237Updated 8 months ago
- 🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022☆147Updated last year
- The official repo for [IJCV'23] "Rethinking Portrait Matting with Privacy Preserving"☆110Updated last year
- Original Inference Repository of the Paper: "Domain-Adaptive Self-Supervised Pre-training for Face & Body Detection in Drawings"☆32Updated 5 months ago
- ☆15Updated 2 months ago
- This method uses Segment Anything and CLIP to ground and count any object that matches a custom text prompt, without requiring any point …☆171Updated 2 years ago
- [ICCV 2025, Highlight] ZIM: Zero-Shot Image Matting for Anything☆352Updated last month
- ☆46Updated 9 months ago
- DesignEdit: Unify Spatial-Aware Image Editing via Training-free Inpainting with a Multi-Layered Latent Diffusion Framework☆352Updated 10 months ago