haibingtown / segment-matting
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.
☆67Updated last year
Alternatives and similar repositories for segment-matting:
Users that are interested in segment-matting are comparing it to the libraries listed below
- Meta's Segment Anything Model (SAM) Demo Site☆149Updated last year
- Codebase for the Recognize Anything Model (RAM)☆76Updated last year
- A simple Segment Anything WebUI based on Gradio.☆77Updated last year
- Image Editing Anything☆113Updated last year
- ☆93Updated 9 months ago
- ☆65Updated last year
- Another matter.☆62Updated 3 weeks ago
- Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts (CVPR 2024)☆76Updated 6 months ago
- Simple static web-based mask drawer, supporting semantic segmentation and video segmentation with interactive Segment Anything Model 2 (S…☆373Updated 8 months ago
- Multi-view Aggregation Network for Dichotomous Image Segmentation (CVPR24, Highlight)☆146Updated last month
- MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆37Updated last year
- TEED: Tiny and Efficient Edge Detector☆200Updated last year
- ☆40Updated 2 months ago
- Matting by Generation☆37Updated 7 months ago
- ☆37Updated 6 months ago
- SSA + FastSAM/Semantic Fast Segment Anything , or Fast Semantic Segment Anything☆94Updated last year
- ZIM: Zero-Shot Image Matting for Anything☆267Updated 4 months ago
- ☆13Updated 2 months ago
- [NeurIPS 2024] Official Implementation of CLIPAway☆96Updated 3 months ago
- [ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces☆237Updated last month
- [CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting☆61Updated 3 months ago
- ☆58Updated 7 months ago
- Diffusers training with mmengine☆99Updated last year
- ☆54Updated 8 months ago
- [ECCV 2024] AnyControl, a multi-control image synthesis model that supports any combination of user provided control signals. 一个支持 用户自由输入控…☆124Updated 8 months ago
- ☆91Updated 8 months ago
- ☆50Updated last year
- Yet another SAM webui + CLIP☆255Updated 5 months ago
- ☆24Updated 2 months ago
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆88Updated last year