Research map / Video / Video generation
World Reconstruction From Inconsistent Views
Lukas Höllein, Matthias Niessner
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 |
|---|---|---|---|
| use non-rigid alignment and non-rigid aware Gaussian Splatting instead of DA3 reconstruction | DA3 · Single video 3D reconstruction (avg over source video models) | 3D consistency: 69.53 -> 79.29 | Improved |
| use non-rigid alignment and non-rigid aware Gaussian Splatting instead of DA3 reconstruction | DA3 · Single video 3D reconstruction (avg over source video models) | photometric consistency: 71.62 -> 86.59 | Improved |
| use non-rigid alignment instead of VGGT-X | VGGT-X · Single video 3D reconstruction (avg over source video models) | CLIP-IQA+: 38.21 -> 46.56 | Improved |
| use non-rigid alignment instead of VGGT-X dagger variant | VGGT-X dagger · Single video 3D reconstruction (avg over source video models) | 3D consistency: 69.66 -> 79.29 | Improved |
| use non-rigid alignment instead of 3DGS-MCMC | 3DGS-MCMC · Single video 3D reconstruction (avg over source video models) | photometric consistency: 69.58 -> 86.59 | Improved |
| use non-rigid alignment instead of VGGT-X dagger variant | VGGT-X dagger · Single video 3D reconstruction (avg over source video models) | CLIP Aesthetic: 37.53 -> 37.61 | No clear effect |
Closest papers by meaning
- SimVS: Simulating World Inconsistencies for Robust View Synthesis (CVPR 2025 · similarity 0.88)
- World-consistent Video Diffusion with Explicit 3D Modeling (CVPR 2025 · similarity 0.87)
- GeoVideo: Introducing Geometric Regularization into Video Generation Model (NeurIPS 2025 · similarity 0.87)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.87)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.87)
- Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models (NeurIPS 2024 · similarity 0.86)
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.
