Research map / 3D vision / 3D generation
MVDD: Multi-View Depth Diffusion Models
Zhen Wang, Qiangeng Xu, Feitong Tan, Menglei Chai, Shichen Liu, Rohit Pandey, Sean Fanello, Achuta Kadambi, Yinda Zhang
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 epipolar line segment cross attention across views (ablation) | MVDD · ShapeNet Chair | 1-NNA (EMD): 90.00 -> 59.65 | Improved |
| add depth concatenation to attention values (ablation) | MVDD · ShapeNet Chair | 1-NNA (EMD): 59.65 -> 59.00 | Improved |
| add cross attention thresholding (ablation) | MVDD · ShapeNet Chair | 1-NNA (EMD): 59.00 -> 57.75 | Improved |
| add denoising depth fusion (ablation) | MVDD · ShapeNet Chair | 1-NNA (EMD): 57.75 -> 54.51 | Improved |
| increase number of points by upsampling LION output versus MVDD native dense points | LION vs MVDD · ShapeNet Chair | 1-NNA | Hurt |
| use MVDD as 3D prior (SDS regularization) in GAN inversion | EG3D PTI inversion · FFHQ 3D GAN inversion | qualitative novel-view quality | Improved |
Closest papers by meaning
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · similarity 0.90)
- MVD-Fusion: Single-view 3D via Depth-consistent Multi-view Generation (CVPR 2024 · similarity 0.89)
- MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model (CVPR 2025 · similarity 0.89)
- DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model (ICLR 2024 · similarity 0.89)
- Denoising Diffusion via Image-Based Rendering (ICLR 2024 · similarity 0.88)
- Cycle3D: High-quality and Consistent Image-to-3D Generation via Generation-Reconstruction Cycle (AAAI 2025 · 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.
