From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving

• URL: http://arxiv.org/abs/2605.01995v1
• Date: Sun, 03 May 2026 17:54:34 GMT
• Title: From Concept to Capability: Evaluating 3D Gaussian Splatting for Synthetic Scene Editing in Autonomous Driving
• Abstract summary: 3D Gaussian Splatting (3DGS) has shown promising capabilities for the reconstruction and editing of scenes based on data collected by cameras and LiDAR sensors.<n>This paper proposes and implements a framework to systematically analyze the capabilities and limitations of 3DGS for use in the reconstruction of safety-related scenes.
• Score: 12.144026818846257
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The perception of an Autonomous Driving System (ADS) critically depends on relevant, comprehensive, and diverse datasets to ensure its safety while operating in the environment. Field data collection lacks completeness with respect to the list of rare but still possible safety-related scenarios needed for the development, verification, and validation of the ADS. 3D Gaussian Splatting (3DGS) has shown promising capabilities for the reconstruction and editing of scenes based on data collected by cameras and LiDAR sensors. However, the industrial fidelity evaluation of reconstructions is underexplored, which is crucial when employing such methods in safety-related systems, especially for ADS. This becomes more challenging as ADS operates in a dynamic, uncontrolled environment with limited viewpoints and often partially occluded objects. This paper addresses this gap by proposing and implementing a framework (Fig. 1) to systematically analyze the capabilities and limitations of 3DGS for use in the reconstruction of safety-related scenes. It focuses on the quality of reconstruction for vehicles and pedestrians, which are the two most critical object classes for ADS. Our findings provide industry insights into the fidelity degradation of reconstructions from multiple novel viewpoints, both lateral and longitudinal, enabling the integration of these methods into real-world industrial AD software development and testing pipelines.

Related papers

• CoRE-VLA: Towards Scalable and Robust Vision-Language-Action Modeling via Conditional Routing of Experts [79.70951193831506]
  Vision-language-action (VLA) models have advanced generalist robotic manipulation, yet real-world deployment reveals a fundamental challenge.<n>We propose CoRE-VLA, a scalable computation and robust VLA framework that formulates action generation as context-conditioned sparse computation.<n>Experiments on LIBERO, RoboCasa GR1 Tabletop, and real-world dual-arm manipulation show that CoRE-VLA achieves strong results on long-horizon and multi-task benchmarks.
  arXiv  Detail & Related papers  (2026-07-04T03:58:09Z)
• iVISION-2DCD: A Long-Term Change Detection Dataset for Large-Scale Outdoor Construction Monitoring [50.60358463714119]
  We present iVISION-2DCD, a large-scale synthetically generated dataset from dense LiDAR point clouds.<n>Our dataset formally defines the problem of viewpoint-robust 2DCD at construction sites.<n> Benchmark evaluations using state-of-the-art 2DCD algorithms demonstrate that iVISION-2DCD poses novel research challenges.
  arXiv  Detail & Related papers  (2026-07-03T18:29:13Z)
• IEC3D-AD: A 3D Dataset of Industrial Equipment Components for Unsupervised Point Cloud Anomaly Detection [16.60482902001866]
  3D anomaly detection (3D-AD) plays a critical role in industrial manufacturing, particularly in ensuring the reliability and safety of core equipment components.<n>Existing 3D datasets like Real3D-AD and MVTec 3D-AD offer broad application support, but fall short in capturing the complexities and subtle defects found in real industrial environments.<n>We have developed a point cloud anomaly detection dataset ( IEC3D-AD) specific to real industrial scenarios.<n>This dataset is directly collected from actual production lines, ensuring high fidelity and relevance.
  arXiv  Detail & Related papers  (2025-11-05T08:01:23Z)
• Occluded nuScenes: A Multi-Sensor Dataset for Evaluating Perception Robustness in Automated Driving [4.60199848319746]
  Occluded nuScenes dataset is a novel extension of the widely used nuScenes benchmark.<n>This resource supports consistent, reproducible evaluation of perception models under partial sensor failures and environmental interference.<n>We aim to advance research on robust sensor fusion, resilience analysis, and safety-critical perception in automated driving.
  arXiv  Detail & Related papers  (2025-10-21T12:02:26Z)
• Safe-Construct: Redefining Construction Safety Violation Recognition as 3D Multi-View Engagement Task [2.0811729303868005]
  We introduce Safe-Construct, a framework that reformulates violation recognition as a 3D multi-view engagement task.<n>Safe-Construct achieves a 7.6% improvement over state-of-the-art methods across four violation types.
  arXiv  Detail & Related papers  (2025-04-15T05:21:09Z)
• InScope: A New Real-world 3D Infrastructure-side Collaborative Perception Dataset for Open Traffic Scenarios [13.821143687548494]
  This paper introduces a new 3D infrastructure-side collaborative perception dataset, abbreviated as inscope. InScope encapsulates a 20-day capture duration with 303 tracking trajectories and 187,787 3D bounding boxes annotated by experts.
  arXiv  Detail & Related papers  (2024-07-31T13:11:14Z)
• Towards Unified 3D Object Detection via Algorithm and Data Unification [70.27631528933482]
  We build the first unified multi-modal 3D object detection benchmark MM- Omni3D and extend the aforementioned monocular detector to its multi-modal version. We name the designed monocular and multi-modal detectors as UniMODE and MM-UniMODE, respectively.
  arXiv  Detail & Related papers  (2024-02-28T18:59:31Z)
• Camera-Radar Perception for Autonomous Vehicles and ADAS: Concepts, Datasets and Metrics [77.34726150561087]
  This work aims to carry out a study on the current scenario of camera and radar-based perception for ADAS and autonomous vehicles. Concepts and characteristics related to both sensors, as well as to their fusion, are presented. We give an overview of the Deep Learning-based detection and segmentation tasks, and the main datasets, metrics, challenges, and open questions in vehicle perception.
  arXiv  Detail & Related papers  (2023-03-08T00:48:32Z)
• USC: Uncompromising Spatial Constraints for Safety-Oriented 3D Object Detectors in Autonomous Driving [7.355977594790584]
  We consider the safety-oriented performance of 3D object detectors in autonomous driving contexts.<n>We present uncompromising spatial constraints (USC), which characterize a simple yet important localization requirement.<n>We incorporate the quantitative measures into common loss functions to enable safety-oriented fine-tuning for existing models.
  arXiv  Detail & Related papers  (2022-09-21T14:03:08Z)
• Cycle and Semantic Consistent Adversarial Domain Adaptation for Reducing Simulation-to-Real Domain Shift in LiDAR Bird's Eye View [110.83289076967895]
  We present a BEV domain adaptation method based on CycleGAN that uses prior semantic classification in order to preserve the information of small objects of interest during the domain adaptation process. The quality of the generated BEVs has been evaluated using a state-of-the-art 3D object detection framework at KITTI 3D Object Detection Benchmark.
  arXiv  Detail & Related papers  (2021-04-22T12:47:37Z)
• Towards robust sensing for Autonomous Vehicles: An adversarial perspective [82.83630604517249]
  It is of primary importance that the resulting decisions are robust to perturbations. Adversarial perturbations are purposefully crafted alterations of the environment or of the sensory measurements. A careful evaluation of the vulnerabilities of their sensing system(s) is necessary in order to build and deploy safer systems.
  arXiv  Detail & Related papers  (2020-07-14T05:25:15Z)
• siaNMS: Non-Maximum Suppression with Siamese Networks for Multi-Camera 3D Object Detection [65.03384167873564]
  A siamese network is integrated into the pipeline of a well-known 3D object detector approach. associations are exploited to enhance the 3D box regression of the object. The experimental evaluation on the nuScenes dataset shows that the proposed method outperforms traditional NMS approaches.
  arXiv  Detail & Related papers  (2020-02-19T15:32:38Z)

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.