Research map / 3D vision / 3D generation
PASTEL: Panoramic Alignment for Monocular 4D Scene Reconstruction
Yuankun Yang, Yi Wei, Bo Bai, Wenyang Zhou, Li 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 panoramic trajectory planning instead of linear Cartesian extension (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 15.73 -> 18.54 | Improved |
| add panoramic planning instead of Cartesian-TopK sampling (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 17.31 -> 18.54 | Improved |
| add trajectory alignment (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 17.87 -> 18.54 | Improved |
| add comprehensive view expansion (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 17.44 -> 18.54 | Improved |
| add strategic supervision with invisible and unreliable masks (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 14.09 -> 18.54 | Improved |
| add view expansion, covisible metric (ablation) | PASTEL · DyCheck iPhone | mPSNR: 19.45 -> 19.75 | Improved |
| use TrajectoryCrafter instead of ReCamMaster as generative prior (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 17.95 -> 18.54 | Improved |
| use TrajectoryCrafter instead of ViewCrafter as prior (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 17.22 -> 18.54 | Improved |
| increase trajectory directions M from 2 to 8 (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 17.70 -> 18.54 | Improved |
| increase trajectory directions M from 8 to 32 (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 18.54 -> 17.98 | Hurt |
| increase interpolation steps L from 49 to 196 (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 18.54 -> 17.61 | Hurt |
| raise SSIM threshold from 0.3 to 0.5 (ablation) | PASTEL · DyCheck iPhone | full-image PSNR: 18.54 -> 18.06 | Hurt |
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.
- MoSca — MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds (CVPR 2025) · better on 4 of 4 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
- 4K4DGen: Panoramic 4D Generation at 4K Resolution (ICLR 2025 · similarity 0.89)
- Scene4U: Hierarchical Layered 3D Scene Reconstruction from Single Panoramic Image for Your Immerse Exploration (CVPR 2025 · similarity 0.88)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.87)
- SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints (ICLR 2025 · similarity 0.87)
- DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos (NeurIPS 2024 · similarity 0.86)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · 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.
