Papers
arxiv:2501.00740

RORem: Training a Robust Object Remover with Human-in-the-Loop

Published on Jan 1
Authors:
,
,
,

Abstract

A semi-supervised learning approach with human feedback is used to create a large dataset for training a robust object removal model, improving performance over existing methods.

AI-generated summary

Despite the significant advancements, existing object removal methods struggle with incomplete removal, incorrect content synthesis and blurry synthesized regions, resulting in low success rates. Such issues are mainly caused by the lack of high-quality paired training data, as well as the self-supervised training paradigm adopted in these methods, which forces the model to in-paint the masked regions, leading to ambiguity between synthesizing the masked objects and restoring the background. To address these issues, we propose a semi-supervised learning strategy with human-in-the-loop to create high-quality paired training data, aiming to train a Robust Object Remover (RORem). We first collect 60K training pairs from open-source datasets to train an initial object removal model for generating removal samples, and then utilize human feedback to select a set of high-quality object removal pairs, with which we train a discriminator to automate the following training data generation process. By iterating this process for several rounds, we finally obtain a substantial object removal dataset with over 200K pairs. Fine-tuning the pre-trained stable diffusion model with this dataset, we obtain our RORem, which demonstrates state-of-the-art object removal performance in terms of both reliability and image quality. Particularly, RORem improves the object removal success rate over previous methods by more than 18\%. The dataset, source code and trained model are available at https://github.com/leeruibin/RORem.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2501.00740 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2501.00740 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2501.00740 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.