Research map / 3D vision / Gaussian splatting
UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction
Chen Shi, Shaoshuai Shi, Xiaoyang Lyu, Chunyang Liu, Kehua Sheng, Bo Zhang, Li Jiang
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 semantic (DINOv2) features to geometric scaffold features (ablation) | UniSplat · Waymo NVS | LPIPS: 0.35 -> 0.30 | Improved |
| add geometric features to semantic features (ablation) | UniSplat · Waymo NVS | PSNR: 24.85 -> 25.08 | Improved |
| add spatial scaffold fusion (ablation) | UniSplat · Waymo NVS | PSNR: 24.14 -> 24.50 | Improved |
| add temporal scaffold fusion (ablation) | UniSplat · Waymo NVS | PSNR: 24.50 -> 25.08 | Improved |
| add voxel branch to point-only decoder (ablation) | UniSplat · Waymo NVS | LPIPS: 0.38 -> 0.30 | Improved |
| replace pi^3 with MoGe-2 geometry model (ablation) | UniSplat · Waymo NVS | PSNR: 25.08 -> 24.98 | No clear effect |
| use dynamic filtering in Gaussian memory (ablation) | UniSplat · Waymo scene completion | qualitative ghosting | Improved |
Later papers that compared with this method
1 later accepted paper reports UniSplat as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- EAGS: Error-Aware Gaussian Splatting with Dual-Confidence-Guided Modeling for Uncalibrated Driving Scenes (ECCV 2026 · better on 3 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 5 of 5 on most shared results.
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 2024) · better on 5 of 5 shared results
- DepthSplat — DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025) · better on 4 of 4 shared results
- Omni-Scene — Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction (CVPR 2025) · better on 2 of 3 shared results
- EvolSplat — EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025) · better on 1 of 1 shared result
- PixelSplat — pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction (CVPR 2024) · 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
- FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views (NeurIPS 2026 · similarity 0.90)
- DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input (AAAI 2025 · similarity 0.88)
- Flux4D: Flow-based Unsupervised 4D Reconstruction (NeurIPS 2025 · similarity 0.88)
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos (NeurIPS 2025 · similarity 0.88)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.87)
- One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction (NeurIPS 2026 · similarity 0.87)
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.
