yeungchenwa / OCR-SAM
Combining MMOCR with Segment Anything & Stable Diffusion. Automatically detect, recognize and segment text instances, with serval downstream tasks, e.g., Text Removal and Text Inpainting
☆533Updated 9 months ago
Related projects ⓘ
Alternatives and complementary repositories for OCR-SAM
- Grounded Segment Anything: From Objects to Parts☆388Updated last year
- [ECCV 2024] Tokenize Anything via Prompting☆534Updated 4 months ago
- The official repo for [CVPR'23] "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting" & [ArXiv'23] "DeepSolo++:…☆248Updated 3 months ago
- Simple static web-based mask drawer, supporting semantic segmentation and video segmentation with interactive Segment Anything Model 2 (S…☆357Updated 3 months ago
- On the Hidden Mystery of OCR in Large Multimodal Models (OCRBench)☆473Updated last month
- Segment-anything related awesome extensions/projects/repos.☆343Updated last year
- This is the official PyTorch implementation of the paper Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP.☆690Updated last year
- [TPAMI'24] Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation☆209Updated this week
- [ICLR'24] Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching☆448Updated 3 months ago
- Tracking and collecting papers/projects/others related to Segment Anything.☆1,546Updated 3 months ago
- Experiment on combining CLIP with SAM to do open-vocabulary image segmentation.☆342Updated last year
- [ICCV 2023] Official implementation of the paper "A Simple Framework for Open-Vocabulary Segmentation and Detection"☆653Updated 9 months ago
- Fine-tune SAM (Segment Anything Model) for computer vision tasks such as semantic segmentation, matting, detection ... in specific scena…☆787Updated last year
- Faster Arbitrarily-Shaped Text Detector with Minimalist Kernel Representation☆166Updated 8 months ago
- Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds☆1,521Updated 3 months ago
- ☆156Updated 8 months ago
- A paper collection of recent diffusion models for text-image generation tasks, e,g., visual text generation, font generation, text remova…☆204Updated 3 months ago
- Relate Anything Model is capable of taking an image as input and utilizing SAM to identify the corresponding mask within the image.☆441Updated last year
- Matting Anything Model (MAM), an efficient and versatile framework for estimating the alpha matte of any instance in an image with flexib…☆618Updated last year
- This is an implementation of zero-shot instance segmentation using Segment Anything.☆300Updated last year
- Scene Text Recognition with Permuted Autoregressive Sequence Models (ECCV 2022)☆586Updated 5 months ago
- [CVPR 2024] Official implementation of the paper "Visual In-context Learning"☆393Updated 7 months ago
- A collection of project, papers, and source code for Meta AI's Segment Anything Model (SAM) and related studies.☆328Updated this week
- [ICCV2023] VLPart: Going Denser with Open-Vocabulary Part Segmentation☆357Updated last year
- The official code of CornerTransformer (ECCV 2022, Oral) on top of MMOCR.☆138Updated last year
- The official implementation of SPTS v2: Single-Point Text Spotting☆126Updated last year
- [CVPR 2023] Official implementation of the paper "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segme…☆1,205Updated 11 months ago
- Segment Anything combined with CLIP☆331Updated 9 months ago
- The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and p…☆265Updated last week
- CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks☆361Updated last year