VCR: A Task for Pixel-Level Complex Reasoning in Vision Language Models via Restoring Occluded Text
This addresses a domain-specific challenge in vision-language understanding for applications like image captioning or document analysis, but it is incremental as it builds on existing tasks with a new focus on text restoration.
The paper tackles the problem of restoring partially obscured text in images by introducing the Visual Caption Restoration (VCR) task, which requires pixel-level reasoning, and results show that current vision-language models significantly underperform humans, with no notable improvements from fine-tuning on their dataset of 2.11M English and 346K Chinese entities.
We introduce Visual Caption Restoration (VCR), a novel vision-language task that challenges models to accurately restore partially obscured texts using pixel-level hints within images. This task stems from the observation that text embedded in images is intrinsically different from common visual elements and natural language due to the need to align the modalities of vision, text, and text embedded in images. While numerous works have integrated text embedded in images into visual question-answering tasks, approaches to these tasks generally rely on optical character recognition or masked language modeling, thus reducing the task to mainly text-based processing. However, text-based processing becomes ineffective in VCR as accurate text restoration depends on the combined information from provided images, context, and subtle cues from the tiny exposed areas of masked texts. We develop a pipeline to generate synthetic images for the VCR task using image-caption pairs, with adjustable caption visibility to control the task difficulty. With this pipeline, we construct a dataset for VCR called VCR-Wiki using images with captions from Wikipedia, comprising 2.11M English and 346K Chinese entities in both easy and hard split variants. Our results reveal that current vision language models significantly lag behind human performance in the VCR task, and merely fine-tuning the models on our dataset does not lead to notable improvements. We release VCR-Wiki and the data construction code to facilitate future research.