ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins

• URL: http://arxiv.org/abs/2601.13706v1
• Date: Tue, 20 Jan 2026 08:03:58 GMT
• Title: ParkingTwin: Training-Free Streaming 3D Reconstruction for Parking-Lot Digital Twins
• Abstract summary: ParkingTwin is a training-free, lightweight system for online streaming 3D reconstruction.<n>It runs at 30+ FPS on an entry-level GTX 1660.
• Score: 8.681741531117366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-fidelity parking-lot digital twins provide essential priors for path planning, collision checking, and perception validation in Automated Valet Parking (AVP). Yet robot-oriented reconstruction faces a trilemma: sparse forward-facing views cause weak parallax and ill-posed geometry; dynamic occlusions and extreme lighting hinder stable texture fusion; and neural rendering typically needs expensive offline optimization, violating edge-side streaming constraints. We propose ParkingTwin, a training-free, lightweight system for online streaming 3D reconstruction. First, OSM-prior-driven geometric construction uses OpenStreetMap semantic topology to directly generate a metric-consistent TSDF, replacing blind geometric search with deterministic mapping and avoiding costly optimization. Second, geometry-aware dynamic filtering employs a quad-modal constraint field (normal/height/depth consistency) to reject moving vehicles and transient occlusions in real time. Third, illumination-robust fusion in CIELAB decouples luminance and chromaticity via adaptive L-channel weighting and depth-gradient suppression, reducing seams under abrupt lighting changes. ParkingTwin runs at 30+ FPS on an entry-level GTX 1660. On a 68,000 m^2 real-world dataset, it achieves SSIM 0.87 (+16.0%), delivers about 15x end-to-end speedup, and reduces GPU memory by 83.3% compared with state-of-the-art 3D Gaussian Splatting (3DGS) that typically requires high-end GPUs (RTX 4090D). The system outputs explicit triangle meshes compatible with Unity/Unreal digital-twin pipelines. Project page: https://mihoutao-liu.github.io/ParkingTwin/

Related papers

• Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object Detection [54.03436243843709]
  This report presents a multi-source collaborative training and class-aware fusion framework for Sim2Real 3D detection.<n>The method organizes digital-twin scans, diffusion-redrawn scans, density-stabilized scans, and pedestrian morphology-aligned samples into a unified training pool with complementary roles.
  arXiv  Detail & Related papers  (2026-09-07T15:16:15Z)
• SHIFT: Surface-aware High-speed Integration For TSDFs [1.253312107729806]
  Real-time 3D mapping is fundamental for autonomous robotic navigation.<n>Currently, Euclidean Signed Distance Fields (ESDFs) serve as the standard representation for online motion planning.<n>We present SHIFT, an efficient mapping framework designed to reduce this per-frame update cost.
  arXiv  Detail & Related papers  (2026-09-06T11:36:19Z)
• Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations [8.600397756762495]
  3D scene representations like NeRF and 3D Gaussian Splatting suffer severe artifacts in sparse-view settings.<n>We propose 3D Morphological Perturbations as an optimization-free regularizer that preserves spatial consistency.<n>Our approach maintains visual fidelity while reducing mean depth error by 12.5% over state-of-the-art image-to-image 3D artifact refiners.
  arXiv  Detail & Related papers  (2026-09-03T10:54:49Z)
• Differentiable Voronoi Ray Tracing Beyond Rasterization Speeds [14.722946445988262]
  Real-time novel view synthesis is dominated by explicit primitives.<n>These primitives require specialized extensions for non-pinhole effects such as distortion, rolling shutter, and depth of field.<n>Ray-based rendering expresses these effects naturally but is generally assumed too slow for competitive real-time rendering.<n>We introduce VoroTracing, which co-designs the scene representation, optimization, and GPU execution to reduce these costs.
  arXiv  Detail & Related papers  (2026-08-18T11:55:58Z)
• FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation [72.38727895659405]
  We introduce FLAT, which decodes triangle splats directly from video diffusion latents.<n>On standard benchmarks, FLAT achieves significantly better geometric accuracy compared to state-of-the-art feedforward baselines.<n>We show that a lightweight test-time refinement step converts the predicted triangle soup into a fully opaque, game-engine-ready representation.
  arXiv  Detail & Related papers  (2026-06-23T17:53:41Z)
• Drive-Through 3D Vehicle Exterior Reconstruction via Dynamic-Scene SfM and Distortion-Aware Gaussian Splatting [16.30721514005399]
  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.
  arXiv  Detail & Related papers  (2026-03-27T17:42:42Z)
• End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction [74.31251139839047]
  THO is an end-to-end Spatial-Temporal Transformer that predicts human motion and coordinated object motion in a forward fashion from the given video and 3D template.<n> experiments demonstrate that THO operates at an inference speed of 31.5 FPS on a single 4090 GPU, achieving a >600x speedup over prior optimization-based methods.
  arXiv  Detail & Related papers  (2026-03-15T15:21:36Z)
• Scalable Generative Game Engine: Breaking the Resolution Wall via Hardware-Algorithm Co-Design [17.941176878609337]
  We bridge the gap between generative models and high-resolution neural simulations by introducing a scalable textitHardware-Algorithm Co-Design framework.<n>Our system delivers fluid 26.4 FPS and 48.3 FPS respectively, with an amortized effective latency of 2.7 ms.
  arXiv  Detail & Related papers  (2026-01-31T08:52:51Z)
• AutoScape: Geometry-Consistent Long-Horizon Scene Generation [69.2451355181344]
  AutoScape is a long-horizon driving scene generation framework.<n>It generates realistic and geometrically consistent driving videos of over 20 seconds.<n>It improves the long-horizon FID and FVD scores over the prior state-of-the-art by 48.6% and 43.0%, respectively.
  arXiv  Detail & Related papers  (2025-10-23T16:44:34Z)
• DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion [62.589889759543446]
  DriveGen3D is a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes.<n>Our work bridges this methodological gap by integrating accelerated long-term video generation with large-scale dynamic scene reconstruction.
  arXiv  Detail & Related papers  (2025-10-17T03:00:08Z)
• RAP: 3D Rasterization Augmented End-to-End Planning [104.52778241744522]
  Imitation learning for end-to-end driving trains policies only on expert demonstrations.<n>We propose 3D Rasterization, which replaces costly rendering with lightweightization of annotated primitives.<n>RAP achieves state-of-the-art closed-loop and long-tail robustness, ranking first on four major benchmarks.
  arXiv  Detail & Related papers  (2025-10-05T19:31:24Z)
• Trans${^2}$-CBCT: A Dual-Transformer Framework for Sparse-View CBCT Reconstruction [10.744510913722817]
  Cone-beam computed tomography (CBCT) using only a few X-ray projection views enables faster scans with lower radiation dose, but the resulting severe under-sampling causes strong artifacts and poor spatial coverage.<n>We address these challenges in a unified framework. First, we replace conventional UNet/ResNet encoders with TransUNet, a hybrid CNN-Transformer model.<n>Experiments on LUNA16 and ToothFairy show consistent gains from six to ten views, validating the effectiveness of combining CNN-Transformer features with point-based geometry reasoning for sparse-view CBCT reconstruction.
  arXiv  Detail & Related papers  (2025-06-20T18:45:12Z)
• StableGS: A Floater-Free Framework for 3D Gaussian Splatting [9.935869165752283]
  3D Gaussian Splatting (3DGS) reconstructions are plagued by stubborn floater" artifacts that degrade their geometric and visual fidelity.<n>We propose StableGS, a novel framework that decouples geometric regularization from final appearance rendering.<n> Experiments on multiple benchmarks show StableGS not only eliminates floaters but also resolves the common blur-artifact trade-off.
  arXiv  Detail & Related papers  (2025-03-24T09:02:51Z)
• Delta-Triplane Transformers as Occupancy World Models [57.16979927973973]
  Occupancy World Models (OWMs) aim to predict future scenes via 3D voxelized representations of the environment to support intelligent motion planning.<n>We propose Delta-Triplane Transformers (DTT), a novel 4D OWM for autonomous driving, that introduces two key innovations.<n>DTT delivers a 1.44$times$ speedup (26 FPS) over the state of the art, improves mean IoU to 30.85, and reduces the mean absolute planning error to 1.0 meters.
  arXiv  Detail & Related papers  (2025-03-10T13:50:23Z)
• InstantSplat: Sparse-view Gaussian Splatting in Seconds [91.77050739918037]
  We introduce InstantSplat, a novel approach for addressing sparse-view 3D scene reconstruction at lightning-fast speed.<n>InstantSplat employs a self-supervised framework that optimize 3D scene representation and camera poses.<n>It achieves an acceleration of over 30x in reconstruction and improves visual quality (SSIM) from 0.3755 to 0.7624 compared to traditional SfM with 3D-GS.
  arXiv  Detail & Related papers  (2024-03-29T17:29:58Z)
• Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection [19.321076175294902]
  Voxel-based methods have achieved state-of-the-art performance for 3D object detection in autonomous driving. Their significant computational and memory costs pose a challenge for their application to resource-constrained vehicles. We propose an adaptive inference framework called Ada3D, which focuses on exploiting the input-level spatial redundancy.
  arXiv  Detail & Related papers  (2023-07-17T02:58:51Z)
• PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark [109.03773439461615]
  PersFormer is an end-to-end monocular 3D lane detector with a novel Transformer-based spatial feature transformation module. We release one of the first large-scale real-world 3D lane datasets, called OpenLane, with high-quality annotation and scenario diversity.
  arXiv  Detail & Related papers  (2022-03-21T16:12:53Z)

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.