Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion

Hao Wen, Zehuan Huang, Yaohui Wang, Xinyuan Chen, Lu Sheng

Keywords: 3D; Video Diffusion Model; 3D generation

TL;DR: A unified framework that intergrates multi-view generation and 3D reconstruction into a recursive diffusion process.

Abstract: Existing image-to-3D creation methods typically split the task into multi-view image generation and 3D reconstruction, leading to two main limitations: (1) multi-view bias, where geometric inconsistencies arise because multi-view diffusion models ensure image-level rather than 3D consistency; (2) misaligned reconstruction data, since reconstruction models trained on mostly synthetic data misalign when processing generated multi-view images during inference. To address these issues, we propose Ouroboros3D, a unified framework that integrates multi-view generation and 3D reconstruction into a recursive diffusion process. By incorporating a 3D-aware feedback mechanism, our multi-view diffusion model leverages the explicit 3D information from the reconstruction results of the previous denoising process as conditions, thus modeling consistency at the 3D geometric level. Furthermore, through joint training of both the multi-view diffusion and reconstruction models, we alleviate reconstruction bias due to data misalignment and enable mutual enhancement within the multi-step recursive process. Experimental results demonstrate that Ouroboros3D outperforms methods that treat these stages separately and those that combine them only during inference, achieving superior multi-view consistency and producing 3D models with higher geometric realism.

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 4779