Rethinking Supervision in Document Unwarping: A Self-consistent Flow-free Approach
cs.CV
Submitted: 2026-10-11
Updated: 2026-10-11
Comments: Accepted by TCSVT 2023
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Visual Instruction Tuning
- Geometric Rectification of Creased Document Images based on Isometric Mapping
- DocScanner: Robust Document Image Rectification with Progressive Learning
- UVDoc: Neural Grid-based Document Unwarping
- Deep Unrestricted Document Image Rectification
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- MataDoc: Margin and Text Aware Document Dewarping for Arbitrary Boundary
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models