DocRevive: A Unified Pipeline for Document Text Restoration

TL;DR

This paper introduces a comprehensive pipeline for restoring damaged or incomplete document text using OCR, image analysis, language modeling, and diffusion techniques, supported by a synthetic dataset and a new similarity metric.

Contribution

It presents a novel unified document restoration pipeline combining multiple advanced models and introduces a synthetic dataset and a new evaluation metric for restoration quality.

Findings

Created a synthetic dataset of 30,078 degraded document images.

Developed a pipeline that detects, recognizes, and reconstructs text with semantic coherence.

Proposed UCSM, a new metric for evaluating restoration quality.

Abstract

In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent document understanding tasks can benefit from a document reconstruction process. In response, this paper presents a novel unified pipeline combining state-of-the-art Optical Character Recognition (OCR), advanced image analysis, masked language modeling, and diffusion-based models to restore and reconstruct text while preserving visual integrity. We create a synthetic dataset of 30{,}078 degraded document images that simulates diverse document degradation scenarios, setting a benchmark for restoration tasks. Our pipeline detects and recognizes text, identifies degradation with an occlusion detector, and uses an inpainting model for semantically coherent reconstruction. A diffusion-based module seamlessly reintegrates text, matching font, size, and alignment. To evaluate restoration quality, we propose a Unified Context Similarity Metric (UCSM), incorporating edit, semantic, and length similarities with a contextual predictability measure that penalizes deviations when the correct text is contextually obvious. Our work advances document restoration, benefiting archival research and digital preservation while setting a new standard for text reconstruction. The OPRB dataset and code are available at \href{https://huggingface.co/datasets/kpurkayastha/OPRB}{Hugging Face} and \href{https://github.com/kunalpurkayastha/DocRevive}{Github} respectively.