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.
☆62Updated 10 months ago
Related projects ⓘ
Alternatives and complementary repositories for segment-matting
- Meta's Segment Anything Model (SAM) Demo Site☆143Updated last year
- Rethinking Interactive Image Segmentation with Low Latency, High Quality, and Diverse Prompts (CVPR 2024)☆65Updated last month
- A simple Segment Anything WebUI based on Gradio.☆70Updated last year
- ☆81Updated 4 months ago
- Codebase for the Recognize Anything Model (RAM)☆64Updated 11 months ago
- ☆60Updated last year
- Image Editing Anything☆112Updated last year
- TEED: Tiny and Efficient Edge Detector☆178Updated last year
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆82Updated last year
- Another matter.☆58Updated 4 months ago
- ☆29Updated 3 weeks ago
- Simple static web-based mask drawer, supporting semantic segmentation and video segmentation with interactive Segment Anything Model 2 (S…☆357Updated 3 months ago
- MobileSAM already integrated into Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆34Updated last year
- The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoi…☆23Updated last year
- SSA + FastSAM/Semantic Fast Segment Anything , or Fast Semantic Segment Anything☆85Updated last year
- Deep Interactive Thin Object Selection☆86Updated 3 years ago
- The official repo for [IJCV'23] "Rethinking Portrait Matting with Privacy Preserving"☆94Updated 7 months ago
- VimTS: A Unified Video and Image Text Spotter☆72Updated last week
- ☆109Updated 2 weeks ago
- Matting by Generation☆33Updated 3 months ago
- SimpleClick: Interactive Image Segmentation with Simple Vision Transformers (ICCV 2023)☆214Updated 6 months ago
- This repo contains extensions to DINO V2 model by Meta, and awesome applications built on top of it.☆38Updated last year
- This is an implementation of zero-shot instance segmentation using Segment Anything.☆300Updated last year
- [CVPR24] MaGGIe: Mask Guided Gradual Human Instance Matting☆43Updated 4 months ago
- Diffusers training with mmengine☆95Updated 9 months ago
- Demonstration of MobileSAM in the browser enabled through ONNX runtime web☆91Updated last year
- Export Segment Anything Models to ONNX☆273Updated 3 months ago
- Int8 StableFusion model☆41Updated 2 years ago
- Add MobileSAM support for Inpaint anything using Segment Anything and inpainting models.☆48Updated last year