Research map / Image generation / Text-to-image diffusion
MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
Shitao Tang, Fuyang Zhang, Jiacheng Chen, Peng Wang, Yasutaka Furukawa
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add correspondence-aware attention across views to stable diffusion (ablation) | MVDiffusion panorama · Matterport3D panorama consistency | PSNR ratio: 0.28 -> 0.67 | Improved |
| add correspondence-aware attention across views to stable diffusion (ablation) | MVDiffusion depth-to-image · ScanNet consistency | PSNR ratio: 0.44 -> 0.76 | Improved |
| generate all views in parallel with CAA instead of iterative warping and inpainting | panorama generation · Matterport3D | FID: 42.13 -> 21.44 | Improved |
| generate all views in parallel with CAA instead of iterative warping and inpainting (RePaint) | depth-to-image generation · ScanNet | FID: 70.05 -> 23.10 | Improved |
| use frozen SD with CAA instead of fine-tuning SD on panoramas | panorama generation · Matterport3D | FID: 23.02 -> 21.44 | Improved |
| adapt SD for multi-view generation versus original perspective SD | MVDiffusion · Matterport3D panorama | FID: 25.59 -> 21.44 | No clear effect |
Later papers that compared with this method
7 later accepted papers report MVDiffusion as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.
- Arbitrary-Shaped Image Generation via Spherical Neural Field Diffusion (ICLR 2026 · better on 3 of 3 shared results)
- CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model (CVPR 2025 · better on 3 of 3 shared results)
- Spherical Manifold Guided Diffusion Model for Panoramic Image Generation (CVPR 2025 · better on 2 of 2 shared results)
- What Makes for Text to 360-degree Panorama Generation with Stable Diffusion? (ICCV 2025 · better on 1 of 2 shared results)
- StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces (ICLR 2025 · better on 0 of 1 shared result)
- Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion (CVPR 2024 · better on 6 of 8 shared results)
- Taming Stable Diffusion for Text to 360 Panorama Image Generation (CVPR 2024 · better on 4 of 8 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation (ICLR 2025 · similarity 0.90)
- MVDream: Multi-view Diffusion for 3D Generation (ICLR 2024 · similarity 0.89)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.89)
- MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model (CVPR 2025 · similarity 0.89)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.88)
- DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion (NeurIPS 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
