fidelity / sim2real-docs
Synthesize image datasets of documents in natural scenes with Python+Blender3D
☆56Updated 2 years ago
Related projects: ⓘ
- Official PyTorch Implementation of DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis - ICDAR 2021☆69Updated 3 years ago
- ☆17Updated 4 years ago
- An open source implementation of CLIP.☆32Updated last year
- Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch☆59Updated 3 years ago
- A Unet based deeplearning model to line/box/spurious artifacts from text images. Unsupervised training.☆56Updated 5 years ago
- A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.☆71Updated 2 years ago
- A non-JIT version implementation / replication of CLIP of OpenAI in pytorch☆34Updated 3 years ago
- Code for the ICDAR2021 paper "Visual FUDGE: Form Understanding via Dynamic Graph Editing"☆33Updated 2 years ago
- Official repository of the paper "GPR1200: A Benchmark for General-PurposeContent-Based Image Retrieval"☆23Updated 3 weeks ago
- ☆27Updated 3 years ago
- ☆15Updated last year
- ☆25Updated 4 years ago
- Load any clip model with a standardized interface☆21Updated 4 months ago
- ☆15Updated 2 years ago
- ☆75Updated last year
- code and data for paper "One-shot Text Field Labeling using Attention and BeliefPropagation for Structure Information Extraction"☆61Updated 4 years ago
- Pytorch augmentation☆118Updated 9 months ago
- Code for CVPR21 paper A Multiplexed Network for End-to-End, Multilingual OCR☆79Updated last year
- ☆37Updated 3 years ago
- ☆81Updated last year
- document image degradation☆155Updated 4 years ago
- Script and models for clustering LAION-400m CLIP embeddings.☆25Updated 2 years ago
- [NeurIPS 2022] Official PyTorch implementation of Optimizing Relevance Maps of Vision Transformers Improves Robustness. This code allows …☆124Updated last year
- CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks☆184Updated 11 months ago
- Public implementation of our CVPR Paper "OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page TextRecognition by learnin…☆142Updated 2 years ago
- Official PyTorch implementation of RIO☆18Updated 3 years ago
- ☆40Updated this week
- Representation for Handwritten Word Images☆24Updated 4 years ago
- Data and implementation of ECCV2020 paper 'Adaptive Text Recognition through Visual Matching'☆121Updated last year