Lune

CVPR Findings2026

SurfaceGS: Dynamic Surface Gaussian Splatting for Urban Driving Scenes

Fudong Ge, Dingning Liu, Hanshi Wang, Yiwei Zhang, Jin Gao, Weiming Hu, Zhipeng Zhang

Abstract

Reconstructing dynamic scenes with 3D Gaussian Splatting is fundamentally challenged by motion and geometric inconsistencies, which often lead to visual artifacts like unnatural stretching. These issues stem from the unconstrained nature of individual Gaussians, which lack an explicit underlying surface to guide their movement. To address this, we introduce SurfaceGS, a novel paradigm that structurally embeds geometric priors into the reconstruction process through a dual-layer surface-Gaussian representation. This core innovation explicitly anchors the radiance-carrying Gaussians to a set of learnable, dynamic surfaces, ensuring that they move and deform coherently with the object's true geometry. We model complex scene dynamics via a hybrid approach, using Bézier curves for global trajectories and efficient B-spline surfaces for local, non-rigid deformations. To ensure scalability for large-scale scenes, we introduce a suite of optimizations, including a patch-wise decomposition and a new adaptive control mechanism tailored for our dynamic surface paradigm. Extensive experiments on challenging urban driving benchmarks validate our approach, demonstrating that SurfaceGS achieves new state-of-the-art results in photorealistic rendering. In addition, our method enables controllable simulation, such as editing and extrapolation for autonomous driving scenes, facilitating safe self-driving systems research.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • GaussianPro: 3D Gaussian Splatting with Progressive Propagation cites 3D Gaussian Splatting for Real-Time Radiance Field Rendering
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on31

  1. Segment AnythingAlexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao et al.ICCV 2023 · 13,211 citations
  2. 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 5,687 citations
  3. Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D ScansAinaz Eftekhar, Alexander Sax, Jitendra Malik, Amir ZamirICCV 2021 · 422 citations
  4. GaussianPro: 3D Gaussian Splatting with Progressive PropagationKai Cheng, Xiaoxiao Long, Kaizhi Yang, Yao Yao et al.ICML 2024 · 241 citations
  5. EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-SupervisionJiawei Yang, Boris Ivanovic, Or Litany, Xinshuo Weng et al.ICLR 2024 · 225 citations

Related papers

  1. BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian SplattingZipei Ma, Junzhe Jiang, Yurui Chen, Li ZhangICCV 2025 · 4 citations
  2. DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving ScenesChensheng Peng, Chengwei Zhang, Yixiao Wang, Chenfeng Xu et al.CVPR 2025
  3. 3D Geometry-aware Deformable Gaussian Splatting for Dynamic View SynthesisZhicheng Lu, Xiang Guo, Le Hui, Tianrui Chen et al.CVPR 2024 · 33 citations
  4. SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular VideoJongmin Park, Minh-Quan Viet Bui, Juan Luis Gonzalez Bello, Jaeho Moon et al.CVPR 2025
  5. HDGS: Hierarchical Dynamic Gaussian Splatting for Urban Driving ScenesFudong Ge, Jin Gao, Hanshi Wang, Yiwei Zhang et al.AAAI 2026
Dusk over the sea between two cliffs drawn in fine vertical lines