DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Suri, Manan, Mathur, Puneet, Dernoncourt, Franck, Jain, Rajiv, Morariu, Vlad I, Sawhney, Ramit, Nakov, Preslav, Manocha, Dinesh
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917812427030528
author Suri, Manan
Mathur, Puneet
Dernoncourt, Franck
Jain, Rajiv
Morariu, Vlad I
Sawhney, Ramit
Nakov, Preslav
Manocha, Dinesh
author_facet Suri, Manan
Mathur, Puneet
Dernoncourt, Franck
Jain, Rajiv
Morariu, Vlad I
Sawhney, Ramit
Nakov, Preslav
Manocha, Dinesh
contents Document structure editing involves manipulating localized textual, visual, and layout components in document images based on the user's requests. Past works have shown that multimodal grounding of user requests in the document image and identifying the accurate structural components and their associated attributes remain key challenges for this task. To address these, we introduce the DocEdit-v2, a novel framework that performs end-to-end document editing by leveraging Large Multimodal Models (LMMs). It consists of three novel components: (1) Doc2Command, which simultaneously localizes edit regions of interest (RoI) and disambiguates user edit requests into edit commands; (2) LLM-based Command Reformulation prompting to tailor edit commands originally intended for specialized software into edit instructions suitable for generalist LMMs. (3) Moreover, DocEdit-v2 processes these outputs via Large Multimodal Models like GPT-4V and Gemini, to parse the document layout, execute edits on grounded Region of Interest (RoI), and generate the edited document image. Extensive experiments on the DocEdit dataset show that DocEdit-v2 significantly outperforms strong baselines on edit command generation (2-33%), RoI bounding box detection (12-31%), and overall document editing (1-12\%) tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16472
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding
Suri, Manan
Mathur, Puneet
Dernoncourt, Franck
Jain, Rajiv
Morariu, Vlad I
Sawhney, Ramit
Nakov, Preslav
Manocha, Dinesh
Computation and Language
Document structure editing involves manipulating localized textual, visual, and layout components in document images based on the user's requests. Past works have shown that multimodal grounding of user requests in the document image and identifying the accurate structural components and their associated attributes remain key challenges for this task. To address these, we introduce the DocEdit-v2, a novel framework that performs end-to-end document editing by leveraging Large Multimodal Models (LMMs). It consists of three novel components: (1) Doc2Command, which simultaneously localizes edit regions of interest (RoI) and disambiguates user edit requests into edit commands; (2) LLM-based Command Reformulation prompting to tailor edit commands originally intended for specialized software into edit instructions suitable for generalist LMMs. (3) Moreover, DocEdit-v2 processes these outputs via Large Multimodal Models like GPT-4V and Gemini, to parse the document layout, execute edits on grounded Region of Interest (RoI), and generate the edited document image. Extensive experiments on the DocEdit dataset show that DocEdit-v2 significantly outperforms strong baselines on edit command generation (2-33%), RoI bounding box detection (12-31%), and overall document editing (1-12\%) tasks.
title DocEdit-v2: Document Structure Editing Via Multimodal LLM Grounding
topic Computation and Language
url https://arxiv.org/abs/2410.16472