Lune

CVPR2025Top-tier venue

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

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

Abstract

Input Rendered from Generated 3DGS Input Rendered from Generated 3DGS 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/

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

11 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Repurposing 3D Generative Model for Autoregressive Layout Generation cites Mv-Adapter: Multi-View Consistent Image Generation Made Easy
  • MaterialMVP: Illumination-Invariant Material Generation via Multi-View PBR Diffusion cites High-Resolution Image Synthesis with Latent Diffusion Models
  • MaterialMVP: Illumination-Invariant Material Generation via Multi-View PBR Diffusion cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
  • MaterialMVP: Illumination-Invariant Material Generation via Multi-View PBR Diffusion cites Denoising Diffusion Probabilistic Models
  • High-Resolution Image Synthesis with Latent Diffusion Models cites Denoising Diffusion Probabilistic Models
  • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites High-Resolution Image Synthesis with Latent Diffusion Models
  • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites Denoising Diffusion Probabilistic Models
  • SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis cites Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
  • Mv-Adapter: Multi-View Consistent Image Generation Made Easy cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Mv-Adapter: Multi-View Consistent Image Generation Made Easy cites SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
  • Mv-Adapter: Multi-View Consistent Image Generation Made Easy cites Denoising Diffusion Probabilistic Models
  • AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites High-Resolution Image Synthesis with Latent Diffusion Models
  • Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding cites Denoising Diffusion Probabilistic Models
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers11

  1. Mv-Adapter: Multi-View Consistent Image Generation Made EasyZehuan Huang, Yuan-Chen Guo, Haoran Wang, Ran Yi et al.ICCV 2025 · 14 citations
  2. PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual WorldYunhan Yang, Chunshi Wang, Junliang Ye, YANG LI et al.ICML 2026 · 6 citations
  3. Repurposing 3D Generative Model for Autoregressive Layout GenerationHaoran Feng, Yifan Niu, Zehuan Huang, Yangtian Sun et al.CVPR 2026 · 3 citations
  4. MaterialMVP: Illumination-Invariant Material Generation via Multi-View PBR DiffusionZebin He, Mingxin Yang, Shuhui Yang, Yixuan Tang et al.ICCV 2025 · 3 citations
  5. AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D GenerationXinyue Liang, Zhiyuan Ma, Lingchen Sun, Yanjun Guo et al.AAAI 2026 · 1 citation

Builds on37

  1. Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  3. Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
  4. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  5. SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann et al.ICLR 2024 · 4,569 citations

Related papers

  1. Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction CycleZhenyu Tang, Junwu Zhang, Xinhua Cheng, Wangbo Yu et al.AAAI 2025 · 43 citations
  2. G4Splat: Geometry-Guided Gaussian Splatting with Generative PriorJunfeng Ni, Yixin Chen, Zhifei Yang, Yu Liu et al.ICLR 2026 · 10 citations
  3. Ouroboros: Single-Step Diffusion Models for Cycle-Consistent Forward and Inverse RenderingShanlin Sun, Yifan Wang, Hanwen Zhang, Yifeng Xiong et al.ICCV 2025 · 3 citations
  4. Hi3D: Pursuing High-Resolution Image-to-3D Generation with Video Diffusion ModelsHaibo Yang, Yang Chen, Yingwei Pan, Ting Yao et al.ACM MM 2024 · 22 citations
  5. Gen3R: 3D Scene Generation Meets Feed-Forward ReconstructionJiaxin Huang, Yuanbo Yang, Bangbang Yang, Lin Ma et al.CVPR 2026 · 24 citations
Dusk over the sea between two cliffs drawn in fine vertical lines