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

Input Rendered from Generated 3DGS Input Rendered from Generated 3DGS * Equal contribution † Corresponding author feedback mechanism, our multi-view generative model leverages the explicit 3D geometric information (e.g. texture, position) from the feedback of reconstruction results of the previous process as conditions, thus modeling consistency at the 3D geometric level. Furthermore, through joint training of both the multi-view generative and reconstruction models, we alleviate reconstruction stage domain gap and enable mutual enhancement within the 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. Please see the project page at https://costwen.github.io/Ouroboros3D/ This CVPR paper is the Open Access version, provided by the Computer Vision Foundation. Except for this watermark, it is identical to the accepted version; the final published version of the proceedings is available on IEEE Xplore.