Research map / Video / Video generation
DimensionX: Create Any 3D and 4D Scenes from a Single Image with Decoupled Video Diffusion
Wenqiang Sun, Shuo Chen, Fangfu Liu, Zilong Chen, Yueqi Duan, Jun Zhu, Jun Zhang, Yikai Wang
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 S-Director (trajectory-aware) to sparse-view 3D generation (ablation) | DimensionX · Tanks and Temples sparse-view | PSNR: 17.32 -> 20.42 | Improved |
| add early-stopping training of S-Director (ablation) | DimensionX · Tanks and Temples sparse-view | PSNR: 17.93 -> 20.42 | Improved |
| add reference video latent sharing (ablation) | DimensionX 4D generation · 4D scene generation | Mat. Pix.(K): 563.7 -> 766.0 | Improved |
| add appearance refinement on top of reference video sharing (ablation) | DimensionX 4D generation · 4D scene generation | Mat. Pix.(K): 766.0 -> 834.3 | Improved |
| use decoupled ST-Director on CogVideoX video generation | CogVideoX · Decoupled video generation | Dynamic degree: 11.76 -> 47.06 | Improved |
| use DimensionX instead of ViewCrafter for single-view 3D | single-view 3D scene generation · Tanks and Temples | PSNR: 15.18 -> 17.11 | Improved |
| Switch-Once: start denoising with S-Director then switch to T-Director after 3 steps | ST-Director · hybrid-dimension video generation | qualitative | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SV4D — SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency (ICLR 2025) · better on 1 of 1 shared result
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
- 4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.91)
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.90)
- A 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale (NeurIPS 2026 · similarity 0.90)
- Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models (ICLR 2025 · similarity 0.90)
- 4Diffusion: Multi-view Video Diffusion Model for 4D Generation (NeurIPS 2024 · similarity 0.90)
- SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency (ICLR 2025 · similarity 0.89)
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.
