Research map / 3D vision / Gaussian splatting
EAGS: Error-Aware Gaussian Splatting with Dual-Confidence-Guided Modeling for Uncalibrated Driving Scenes
Cen Zhigang, Ningyan Guo, Yulan Guo, Yifan Ge, Zhiyong Feng
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 soft gating (ablation) | EAGS · Waymo | PSNR: 27.43 -> 28.02 | Improved |
| add voxelization (ablation) | EAGS · Waymo | PSNR: 27.18 -> 28.02 | Improved |
| add depth-guided loss L_gp (ablation) | EAGS · Waymo | PSNR: 27.83 -> 28.02 | Improved |
| add distillation consistency loss (ablation) | EAGS · Waymo | PSNR: 13.04 -> 28.02 | Improved |
| add error encoder (ablation) | EAGS · Waymo | PSNR: 26.95 -> 28.02 | Improved |
| add error encoder (ablation) | EAGS · Waymo | Gaussians per view: 80229 -> 49556 | Improved |
| increase input frames from 4 to 8 (ablation) | EAGS · Waymo | PSNR: 28.02 -> 28.32 | Improved |
| increase input frames from 4 to 16 (ablation) | EAGS · Waymo | PSNR: 28.02 -> 28.11 | Improved |
| flip 20% of dynamic masks randomly (ablation) | EAGS · Waymo | PSNR: minor PSNR decrease of 0.12 dB | No clear effect |
| EAGS vs DGGT zero-shot on nuScenes | EAGS · nuScenes | PSNR: 25.31 -> 26.14 | Improved |
| EAGS vs DGGT zero-shot on Argoverse2 | EAGS · Argoverse2 | PSNR: 26.34 -> 27.41 | Improved |
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.
- UniSplat — UniSplat: Unified Spatio-Temporal Fusion via 3D Latent Scaffolds for Dynamic Driving Scene Reconstruction (ICLR 2026) · better on 3 of 3 shared results
- VGGT++ — VGGT: Visual Geometry Grounded Transformer (CVPR 2025) · better on 2 of 2 shared results
- DepthSplat — DepthSplat: Connecting Gaussian Splatting and Depth (CVPR 2025) · better on 1 of 1 shared result
- EVolSplat — EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis (CVPR 2025) · better on 1 of 1 shared result
- MVSplat — MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images (ECCV 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
- DrivingForward: Feed-forward 3D Gaussian Splatting for Driving Scene Reconstruction from Flexible Surround-view Input (AAAI 2025 · similarity 0.90)
- DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes (CVPR 2024 · similarity 0.90)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.89)
- FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views (NeurIPS 2026 · similarity 0.89)
- CompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene Reconstruction (NeurIPS 2026 · similarity 0.88)
- PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting (CVPR 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.
