Drive-Through 3D Vehicle Exterior Reconstruction via Dynamic-Scene SfM and Distortion-Aware Gaussian Splatting

• URL: http://arxiv.org/abs/2603.26638v1
• Date: Fri, 27 Mar 2026 17:42:42 GMT
• Title: Drive-Through 3D Vehicle Exterior Reconstruction via Dynamic-Scene SfM and Distortion-Aware Gaussian Splatting
• Abstract summary: High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces.<n> generating these models in cluttered dealership drive-throughs presents severe technical challenges.<n>We propose an end-to-end pipeline utilizing a two-pillar camera rig.
• Score: 16.30721514005399
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-fidelity 3D reconstruction of vehicle exteriors improves buyer confidence in online automotive marketplaces, but generating these models in cluttered dealership drive-throughs presents severe technical challenges. Unlike static-scene photogrammetry, this setting features a dynamic vehicle moving against heavily cluttered, static backgrounds. This problem is further compounded by wide-angle lens distortion, specular automotive paint, and non-rigid wheel rotations that violate classical epipolar constraints. We propose an end-to-end pipeline utilizing a two-pillar camera rig. First, we resolve dynamic-scene ambiguities by coupling SAM 3 for instance segmentation with motion-gating to cleanly isolate the moving vehicle, explicitly masking out non-rigid wheels to enforce strict epipolar geometry. Second, we extract robust correspondences directly on raw, distorted 4K imagery using the RoMa v2 learned matcher guided by semantic confidence masks. Third, these matches are integrated into a rig-aware SfM optimization that utilizes CAD-derived relative pose priors to eliminate scale drift. Finally, we use a distortion-aware 3D Gaussian Splatting framework (3DGUT) coupled with a stochastic Markov Chain Monte Carlo (MCMC) densification strategy to render reflective surfaces. Evaluations on 25 real-world vehicles across 10 dealerships demonstrate that our full pipeline achieves a PSNR of 28.66 dB, an SSIM of 0.89, and an LPIPS of 0.21 on held-out views, representing a 3.85 dB improvement over standard 3D-GS, delivering inspection-grade interactive 3D models without controlled studio infrastructure.

Related papers

• DecoupleGS: Interactive 3D Gaussian Splatting for End-to-End Autonomous Driving Testing [37.82194951319459]
  End-to-end (E2E) autonomous driving algorithms require rigorous closed-loop validation in simulation environments.<n>Existing approaches, from game engines to static neural rendering, inherently trade off these requirements.<n>We propose a novel decoupled 3D Gaussian Splatting (3DGS) framework tailored for large-scale E2E evaluation.
  arXiv  Detail & Related papers  (2026-08-03T06:32:00Z)
• One World, Dual Timeline: Decoupled Spatio-Temporal Gaussian Scene Graph for 4D Cooperative Driving Reconstruction [24.030187603322076]
  We propose Dust (DecoUpled Spatio-Temporal) Gaussian Scene Graph for 4D Cooperative Driving Reconstruction.<n>DUST achieves state-of-the-art performance, improving dynamic-area PSNR by 3.2 dB over the strongest baseline.<n>We show that DUST reduces Fréchet Video Distance by 37.7%, with keeping under larger temporal asynchrony.
  arXiv  Detail & Related papers  (2026-05-08T15:48:57Z)
• Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation [19.45064081855758]
  Simulation is essential for autonomous driving, yet current frameworks often model vehicles as rigid assets and fail to capture part-level articulation.<n>We propose a generative framework that synthesizes an animatable 3D Gaussian vehicle from a single image or sparse multi-view input.<n>Our method addresses two challenges: (i) large 3D asset generators are optimized for static quality but not articulation, leading to distortions at part boundaries when animated; and (ii) segmentation alone cannot provide the kinematic parameters required for motion.
  arXiv  Detail & Related papers  (2026-04-06T18:16:12Z)
• ReinDriveGen: Reinforcement Post-Training for Out-of-Distribution Driving Scene Generation [61.64162666162948]
  ReinDriveGen is a framework that enables full controllability over dynamic driving scenes.<n>Our approach constructs a dynamic 3D point cloud scene from multi-frame LiDAR data.<n>Our approach renders the edited scene into 2D condition images that guide a video diffusion model to synthesize realistic driving videos.
  arXiv  Detail & Related papers  (2026-04-01T16:48:20Z)
• HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles [63.88996084630768]
  Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation.<n>We introduce HorizonForge, a unified framework that reconstructs scenes as editable Gaussian Splats and Meshes.<n>Experiments show that Gaussian-Mesh representation delivers substantially higher fidelity than alternative 3D representations.
  arXiv  Detail & Related papers  (2026-02-24T20:03:47Z)
• Rig-Aware 3D Reconstruction of Vehicle Undercarriages using Gaussian Splatting [15.633861502167663]
  We present an end-to-end pipeline that utilizes a three-camera rig to capture videos of the undercarriage as the vehicle drives over it.<n>The 3D model enables inspectors and customers to rotate, zoom, and slice through the undercarriage, allowing them to detect rust, leaks, or impact damage in seconds.<n>Our method overcomes the challenges of wide-angle lens distortion and low-parallax scenes by integrating precise camera calibration, synchronized video streams, and strong geometric priors from the camera rig.
  arXiv  Detail & Related papers  (2026-01-20T18:13:03Z)
• DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images [36.562825380568384]
  We introduce textbfDriving Gaussian Grounded Transformer (DGGT), a unified framework for pose-free dynamic scene reconstruction.<n>Our approach jointly predicts per-frame 3D Gaussian maps and camera parameters, disentangles dynamics with a lightweight dynamic head.<n>A diffusion-based rendering refinement further reduces motion/interpolation artifacts and improves novel-view quality under sparse inputs.
  arXiv  Detail & Related papers  (2025-12-02T18:29:18Z)
• RoCo-Sim: Enhancing Roadside Collaborative Perception through Foreground Simulation [30.744548212616007]
  We present the first simulation framework RoCo-Sim for road-side collaborative perception.<n>RoCo-Sim is capable of generating diverse, multi-view consistent simulated roadside data.<n>Code and pre-trained models will be released soon.
  arXiv  Detail & Related papers  (2025-03-13T14:33:42Z)
• OG-Gaussian: Occupancy Based Street Gaussians for Autonomous Driving [12.47557991785691]
  We propose OG-Gaussian, a novel approach that replaces LiDAR point clouds with Occupancy Grids (OGs) generated from surround-view camera images.<n>Our method leverages the semantic information in OGs to separate dynamic vehicles from static street background, converting these grids into two distinct sets of initial point clouds for reconstructing both static and dynamic objects.<n>Experiments on the Open dataset demonstrate that OG-Gaussian is on par with the current state-of-the-art in terms of reconstruction quality and rendering speed, achieving an average PSNR of 35.13 and a rendering speed of 143 FPS
  arXiv  Detail & Related papers  (2025-02-20T04:00:47Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions.<n>We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• AutoSplat: Constrained Gaussian Splatting for Autonomous Driving Scene Reconstruction [17.600027937450342]
  AutoSplat is a framework employing Gaussian splatting to achieve highly realistic reconstructions of autonomous driving scenes. Our method enables multi-view consistent simulation of challenging scenarios including lane changes.
  arXiv  Detail & Related papers  (2024-07-02T18:36:50Z)
• DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes [57.12439406121721]
  We present DrivingGaussian, an efficient and effective framework for surrounding dynamic autonomous driving scenes. For complex scenes with moving objects, we first sequentially and progressively model the static background of the entire scene. We then leverage a composite dynamic Gaussian graph to handle multiple moving objects. We further use a LiDAR prior for Gaussian Splatting to reconstruct scenes with greater details and maintain panoramic consistency.
  arXiv  Detail & Related papers  (2023-12-13T06:30:51Z)
• Recovering and Simulating Pedestrians in the Wild [81.38135735146015]
  We propose to recover the shape and motion of pedestrians from sensor readings captured in the wild by a self-driving car driving around. We incorporate the reconstructed pedestrian assets bank in a realistic 3D simulation system. We show that the simulated LiDAR data can be used to significantly reduce the amount of real-world data required for visual perception tasks.
  arXiv  Detail & Related papers  (2020-11-16T17:16:32Z)
• Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera [74.45649274085447]
  We propose a robust method for estimating road curb 3D parameters using a calibrated monocular camera equipped with a fisheye lens. Our approach is able to estimate the vehicle to curb distance in real time with mean accuracy of more than 90%.
  arXiv  Detail & Related papers  (2020-02-28T00:24:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.