LiAuto-GeoX: Efficient Grounded Driving Transformer

• URL: http://arxiv.org/abs/2606.05774v1
• Date: Thu, 04 Jun 2026 06:58:44 GMT
• Title: LiAuto-GeoX: Efficient Grounded Driving Transformer
• Abstract summary: We present textbfLiAuto-GeoX, an efficient grounded driving transformer for deployable, ego-centric 3D scene understanding.<n>We show that textbfLiAuto-GeoX runs at 220 FPS on KITTI while maintaining high-fidelity dense reconstruction, enabling real-time deployment.
• Score: 54.23823436153608
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Dense 3D reconstruction has demonstrated immense potential for spatial understanding, yet its viability as a real-time, onboard representation for autonomous driving remains an open challenge. Existing large-scale visual geometry models typically require substantial computational resources and lack the long-range geometric fidelity, surround-view consistency, and real-time efficiency demanded by dynamic driving environments. To bridge this gap, we present \textbf{LiAuto-GeoX}, an efficient grounded driving transformer designed for deployable, ego-centric 3D scene understanding. Our approach begins by learning a high-capacity driving geometry model from large-scale surround-view data, utilizing sparse LiDAR priors to provide robust geometric grounding in distant, ambiguous, or structure-sparse regions. We then instantiate this capability into a highly compact 155M-parameter onboard model through a novel geometry-preserving distillation framework. This framework employs mask-guided depth-aware distillation to retain fine-grained metric structures by emphasizing geometrically informative regions, and relative-pose relational distillation to enforce cross-view spatial consistency through pose-induced geometric relations. Extensive evaluations reveal that \textbf{LiAuto-GeoX} runs at 220 FPS on KITTI while maintaining high-fidelity dense reconstruction, enabling real-time deployment. The learned geometry transfers seamlessly to downstream autonomy tasks, achieving 90.6 PDMS in trajectory prediction, 24.63 mIoU in occupancy prediction, and 47.67 IoU in future-frame prediction. These all demonstrate that efficient dense 3D reconstruction can transcend its traditional role as a perception target to serve as a scalable, foundational geometric representation for next-generation autonomous driving.

Related papers

• GeoWorldAD: Geometry World Action Model for Autonomous Driving [45.0114703918243]
  We propose GeoWorldAD, a geometry world action model that grounds trajectory planning in ego-aligned 3D space.<n>Present geometry provides essential spatial constraints for safe planning, while future geometry reveals how surrounding agents and ego-centric free space may evolve.<n>Experiments on NAVSIM v1 and v2 demonstrate state-of-the-art performance, highlighting the effectiveness of explicit 3D geometry grounding.
  arXiv  Detail & Related papers  (2026-07-20T03:56:07Z)
• TRIG: Trajectory-Rig Decoupled Metric Geometry Learning [33.69899077340302]
  Trajectory-Rig Decoupled Metric Geometry Learning (TRIG) is a geometry perception framework for autonomous driving.<n>We introduce decoupled pose encoding and supervision, which separately constrain trajectory evolution and rig geometry for metric-consistent learning.<n>Experiments on five autonomous driving benchmarks show that TRIG achieves state-of-the-art performance in pose estimation, metric depth prediction, and 3D reconstruction.
  arXiv  Detail & Related papers  (2026-07-07T03:55:13Z)
• Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces [18.19675060489249]
  We propose S$2$VAE, a geometry-first latent learning framework that focuses on compressing and representing the latent 3D state of a scene.<n>In depth estimation, camera pose recovery, and point cloud reconstruction, we show that geometry-aligned hyperspherical latents consistently outperform conventional Gaussian bottlenecks.
  arXiv  Detail & Related papers  (2026-04-30T17:12:31Z)
• Cross-Vehicle 3D Geometric Consistency for Self-Supervised Surround Depth Estimation on Articulated Vehicles [3.512352303010361]
  We propose a self-supervised framework for surround-view depth estimation on articulated vehicles.<n>We introduce multi-view spatial context enrichment strategy and a cross-view surface normal constraint to improve structural coherence.<n>To validate our proposed method, an articulated vehicle experiment platform was established with a dataset collected over it.
  arXiv  Detail & Related papers  (2026-04-03T02:10:11Z)
• DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale [63.05446464787182]
  We propose an alternative Vision-Geometry-Action paradigm that advocates dense 3D geometry as the critical cue for autonomous driving.<n>We introduce a streaming Driving Visual Geometry Transformer (DVGT-2), which processes inputs in an online manner and jointly outputs dense geometry and trajectory planning for the current frame.<n>Despite the faster speed, DVGT-2 achieves superior geometry reconstruction performance on various datasets.
  arXiv  Detail & Related papers  (2026-04-01T12:21:26Z)
• SpatialFly: Geometry-Guided Representation Alignment for UAV Vision-and-Language Navigation in Urban Environments [49.966170814478915]
  We propose a geometry-guided spatial representation framework for UAV VLN.<n>Running on RGB observations without explicit 3D reconstruction, SpatialFly introduces a geometry-guided 2D representation alignment mechanism.<n> Experimental results show that SpatialFly consistently outperforms state-of-the-art UAV VLN baselines across both seen and unseen environments.
  arXiv  Detail & Related papers  (2026-03-22T03:56:58Z)
• GeoSurDepth: Spatial Geometry-Consistent Self-Supervised Depth Estimation for Surround-View Cameras [3.072321170197384]
  GeoSurDepth is a framework that leverages geometry consistency as the primary cue for surround-view depth estimation.<n>Our framework highlights the importance of exploiting geometry coherence and consistency for robust self-supervised multi-view depth estimation.
  arXiv  Detail & Related papers  (2026-01-09T15:13:28Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting [31.53981556612888]
  Occupancy is crucial for autonomous driving, providing essential geometric priors for perception and planning.<n>Existing methods predominantly rely on LiDAR-based occupancy annotations.<n>We propose GS-Occ3D, a scalable vision-only framework that directly reconstructs occupancy.
  arXiv  Detail & Related papers  (2025-07-25T17:33:23Z)
• GeoDrive: 3D Geometry-Informed Driving World Model with Precise Action Control [50.67481583744243]
  We introduce GeoDrive, which explicitly integrates robust 3D geometry conditions into driving world models.<n>We propose a dynamic editing module during training to enhance the renderings by editing the positions of the vehicles.<n>Our method significantly outperforms existing models in both action accuracy and 3D spatial awareness.
  arXiv  Detail & Related papers  (2025-05-28T14:46:51Z)
• GASP: Unifying Geometric and Semantic Self-Supervised Pre-training for Autonomous Driving [12.889523014369884]
  We propose a geometric and semantic self-supervised pre-training method, GASP, that learns a unified representation by predicting, at any queried future point in spacetime.<n>By modeling geometric and semantic 4D occupancy fields instead of raw sensor measurements, the model learns a structured, general representation of the environment and its evolution through time.
  arXiv  Detail & Related papers  (2025-03-19T20:00:27Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• Outdoor Scene Extrapolation with Hierarchical Generative Cellular Automata [70.9375320609781]
  We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV) We propose hierarchical Generative Cellular Automata (hGCA), a spatially scalable 3D generative model, which grows geometry with local kernels following, in a coarse-to-fine manner, equipped with a light-weight planner to induce global consistency.
  arXiv  Detail & Related papers  (2024-06-12T14:56:56Z)

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.