ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors

• URL: http://arxiv.org/abs/2508.15529v2
• Date: Sat, 23 Aug 2025 17:53:01 GMT
• Title: ExtraGS: Geometric-Aware Trajectory Extrapolation with Uncertainty-Guided Generative Priors
• Abstract summary: ExtraGS is a holistic framework for trajectory extrapolation that integrates both geometric and generative priors.<n>We show that ExtraGS significantly enhances the realism and geometric consistency of extrapolated views, while preserving high fidelity along the original trajectory.
• Score: 8.960814123058684
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Synthesizing extrapolated views from recorded driving logs is critical for simulating driving scenes for autonomous driving vehicles, yet it remains a challenging task. Recent methods leverage generative priors as pseudo ground truth, but often lead to poor geometric consistency and over-smoothed renderings. To address these limitations, we propose ExtraGS, a holistic framework for trajectory extrapolation that integrates both geometric and generative priors. At the core of ExtraGS is a novel Road Surface Gaussian(RSG) representation based on a hybrid Gaussian-Signed Distance Function (SDF) design, and Far Field Gaussians (FFG) that use learnable scaling factors to efficiently handle distant objects. Furthermore, we develop a self-supervised uncertainty estimation framework based on spherical harmonics that enables selective integration of generative priors only where extrapolation artifacts occur. Extensive experiments on multiple datasets, diverse multi-camera setups, and various generative priors demonstrate that ExtraGS significantly enhances the realism and geometric consistency of extrapolated views, while preserving high fidelity along the original trajectory.

Related papers

• PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis [16.51293833344591]
  We propose PRG-Fusion, a framework for driving view synthesis that uses reconstruction evidence to orchestrate generative priors across regions.<n>Specifically, we extract region-wise reconstruction evidence from reconstructed driving scenes and convert it into Preserve, Repair, and Generate (PRG) labels.<n>We then follow a two-stage training paradigm, first establish geometric control from sparse LiDAR projections and subsequently learning appearance control from dense 3DGS.
  arXiv  Detail & Related papers  (2026-09-07T02:34:51Z)
• GeoFlow: Efficient Driving Video Generation via Geometry-Aligned Priors [27.10799700736534]
  Generative models like Diffusion Models and Flow Matching have demonstrated remarkable capabilities in synthesizing high-fidelity driving videos.<n>We argue that this inefficiency stems from the prevailing reliance on a standard Gaussian source distribution, where consecutive frames are as independent Gaussian noise.<n>We propose GeoFlow, a novel framework designed to achieve efficient driving video generation by harnessing explicit geometric priors.
  arXiv  Detail & Related papers  (2026-08-12T15:57:08Z)
• ViPSim: Collaborating Visual and Parameter Spaces for Consistent Long-Horizon Embodied World Models [11.15585863355844]
  Embodied World Models (EWMs) have emerged as a scalable and risk-free paradigm for advancing embodied intelligence.<n>EWMs are often hindered by the representation gap between low-dimensional actions and high-dimensional video synthesis.<n>We propose ViPSim, a framework that achieves consistent long-horizon generation.
  arXiv  Detail & Related papers  (2026-06-27T08:18:09Z)
• LiAuto-GeoX: Efficient Grounded Driving Transformer [54.23823436153608]
  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.
  arXiv  Detail & Related papers  (2026-06-04T06:58:44Z)
• GVGS: Gaussian Visibility-Aware Multi-View Geometry for Accurate Surface Reconstruction [15.170414649311441]
  3D Gaussian Splatting enables efficient optimization and high-quality rendering, yet accurate surface reconstruction remains challenging.<n>We introduce a visibility-aware multi-view geometric consistency constraint that aggregates the visibility of shared Gaussian primitives across views.<n>We also propose a progressive quadtree-calibrated Monocular depth constraint that performs block-wise affine calibration from coarse to fine spatial scales.
  arXiv  Detail & Related papers  (2026-01-28T07:48:51Z)
• HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving [59.55918581964678]
  HybridWorldSim is a hybrid simulation framework that integrates multi-traversal neural reconstruction for static backgrounds with generative modeling for dynamic agents.<n>We release a new multi-traversal dataset MIRROR that captures a wide range of routes and environmental conditions across different cities.
  arXiv  Detail & Related papers  (2025-11-27T07:53:16Z)
• 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)
• R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulation [74.41728218960465]
  We propose a real-to-real 3D data generation framework (R2RGen) that directly augments the pointcloud observation-action pairs to generate real-world data.<n>R2RGen substantially enhances data efficiency on extensive experiments and demonstrates strong potential for scaling and application on mobile manipulation.
  arXiv  Detail & Related papers  (2025-10-09T17:55:44Z)
• PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving [12.699352594544166]
  We propose PriorFusion, a unified framework that integrates semantic, geometric, and generative priors to enhance road element perception.<n>We show that our method significantly improves perception accuracy, particularly under challenging conditions.
  arXiv  Detail & Related papers  (2025-07-31T07:43:19Z)
• RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors [54.81109375939306]
  RGE-GS is a novel expansive reconstruction framework that synergizes diffusion-based generation with reward-guided Gaussian integration.<n>We propose a reward network that learns to identify and prioritize consistently generated patterns prior to reconstruction phases.<n>During the reconstruction process, we devise a differentiated training strategy that automatically adjust Gaussian optimization progress according to scene converge metrics.
  arXiv  Detail & Related papers  (2025-06-28T08:02:54Z)
• GS-SDF: LiDAR-Augmented Gaussian Splatting and Neural SDF for Geometrically Consistent Rendering and Reconstruction [12.293953058837653]
  Digital twins are fundamental to the development of autonomous driving and embodied artificial intelligence.<n>We propose a unified LiDAR-visual system that synergizes Gaussian splatting with a neural signed distance field.<n> Experiments demonstrate superior reconstruction accuracy and rendering quality across diverse trajectories.
  arXiv  Detail & Related papers  (2025-03-13T08:53:38Z)
• EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation [55.26713167507132]
  We introduce a generative robotics foundation model that constructs and interprets embodied spaces.<n>EnerVerse employs an autoregressive video diffusion framework to predict future embodied spaces from instructions, enhanced by a sparse context memory for long-term reasoning.<n>We present EnerVerse-D, a data engine pipeline combining the generative model with 4D Gaussian Splatting, forming a self-reinforcing data loop to reduce the sim-to-real gap.
  arXiv  Detail & Related papers  (2025-01-03T17:00:33Z)
• MonoGSDF: Exploring Monocular Geometric Cues for Gaussian Splatting-Guided Implicit Surface Reconstruction [84.07233691641193]
  We introduce MonoGSDF, a novel method that couples primitives with a neural Signed Distance Field (SDF) for high-quality reconstruction.<n>To handle arbitrary-scale scenes, we propose a scaling strategy for robust generalization.<n>Experiments on real-world datasets outperforms prior methods while maintaining efficiency.
  arXiv  Detail & Related papers  (2024-11-25T20:07:07Z)
• DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes [71.61083731844282]
  We present DeSiRe-GS, a self-supervised gaussian splatting representation.<n>It enables effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.
  arXiv  Detail & Related papers  (2024-11-18T05:49:16Z)
• 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)
• STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction [22.553356096143734]
  We propose a novel generative flow based framework with dual graphormer for pedestrian trajectory prediction (STGlow) Our method can more precisely model the underlying data distribution by optimizing the exact log-likelihood of motion behaviors. Experimental results on several benchmarks demonstrate that our method achieves much better performance compared to previous state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-21T07:29:24Z)

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.