Completing Visual Objects via Bridging Generation and Segmentation

Xiang Li, Yinpeng Chen, Chung-Ching Lin, Rita Singh, Bhiksha Raj, Zicheng Liu

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Object Completion, Segmentation, Mask Denoising

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: This paper presents a novel approach to object completion, with the primary goal of reconstructing a complete object from its partially visible components. Our method, named MaskComp, delineates the completion process through iterative stages of generation and segmentation. In each iteration, the object mask is provided as an additional condition to boost image generation, and, in return, the generated images can lead to a more accurate mask by fusing the segmentation of images. We demonstrate that the combination of one generation and one segmentation stage effectively functions as a mask denoiser. Through alternation between the generation and segmentation stages, the partial object mask is progressively refined, providing precise shape guidance and yielding superior object completion results. Our experiments demonstrate the superiority of MaskComp over existing approaches, e.g., ControlNet and Stable Diffusion, establishing it as an effective solution for object completion.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 739