Research map / 3D vision / Gaussian splatting
Unified Panoramic–Gaussian Representation for Monocular 4D Scene Synthesis
Yuankun Yang, Yi Wei, 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 |
|---|---|---|---|
| use panoramic expansion instead of planar expansion (ablation) | PanoGaussian · DyCheck iPhone | uPSNR: 14.25 -> 16.72 | Improved |
| add Gaussian refinement to panoramic expansion (ablation) | PanoGaussian · DyCheck iPhone | uPSNR: 15.08 -> 16.72 | Improved |
| add Gaussian Splatting representation (ablation) | PanoGaussian · DyCheck iPhone | PSNR: 14.67 -> 18.71 | Improved |
| add Gaussian Splatting representation (ablation) | PanoGaussian · DyCheck iPhone | uPSNR: 12.61 -> 16.72 | Improved |
| add progressive expansion (ablation) | PanoGaussian · DyCheck iPhone | uPSNR: 15.22 -> 16.72 | Improved |
| add progressive expansion (ablation) | PanoGaussian · DyCheck iPhone | PSNR: 17.51 -> 18.71 | Improved |
| add panoramic trajectory training (ablation) | PanoGaussian · DyCheck iPhone | uPSNR: 16.32 -> 16.72 | Improved |
| add panoramic trajectory training (ablation) | PanoGaussian · DyCheck iPhone | PSNR: 18.46 -> 18.71 | Improved |
| increase expansion steps from 6 to 24 | PanoGaussian · DyCheck iPhone | PSNR / uPSNR: 18.71 / 16.72 -> 18.68 / 16.66 | No clear effect |
| use PanoGaussian instead of MoSca | PanoGaussian · Nvidia Dynamic | PSNR: 26.72 -> 26.75 | No clear effect |
| use PanoGaussian instead of MoSca | PanoGaussian · DyCheck iPhone | uPSNR: 14.23 -> 16.72 | Improved |
| use PanoGaussian instead of MoSca | PanoGaussian · Kubric-4D | uPSNR: 10.86 -> 17.19 | 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.
- MoSca — MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds (CVPR 2025) · better on 12 of 12 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 0.90)
- PanoWorld: Geometry-Consistent Panoramic Video World Modeling (NeurIPS 2026 · similarity 0.89)
- 4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos (NeurIPS 2025 · similarity 0.88)
- CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models (CVPR 2025 · similarity 0.88)
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video (NeurIPS 2026 · similarity 0.88)
- ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models (NeurIPS 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.
