paper-with-me

Papers

LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes

2024-11-30 · Shing-Hei Ho, Bao Thach, Minghan Zhu

We present LiDAR-EDIT, a novel paradigm for generating synthetic LiDAR data for autonomous driving. Our framework edits real-world LiDAR scans by introducing new object layouts while preserving the realism of the background environment. Compared to end-to-end frameworks that generate LiDAR point clouds from scratch, LiDAR-EDIT offers users full control over the object layout, including the number, type, and pose of objects, while keeping most of the original real-world background. Our method also provides object labels for the generated data. Compared to novel view synthesis techniques, our framework allows for the creation of counterfactual scenarios with object layouts significantly different from the original real-world scene. LiDAR-EDIT uses spherical voxelization to enforce correct LiDAR projective geometry in the generated point clouds by construction. During object removal and insertion, generative models are employed to fill the unseen background and object parts that were occluded in the original real LiDAR scans. Experimental results demonstrate that our framework produces realistic LiDAR scans with practical value for downstream tasks.

📄 PDF Abstract BibTeX arXiv:2412.00592

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingcounterfactualNovel View SynthesisObjectPoint Cloud CompletionSynthetic Data Generation

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Similar Papers 제목 키워드 기반

LiDARCrafter: Dynamic 4D World Modeling from LiDAR Sequences

2025-08-05 · Ao Liang, Youquan Liu, Yu Yang, Dongyue Lu 외 arxiv

Generative world models have become essential data engines for autonomous driving, yet most existing efforts focus on videos or occupancy grids, overlooking the unique LiDAR properties. Extending LiDAR generation to dyna…

Autonomous DrivingData Augmentation

Range-Edit: Semantic Mask Guided Outdoor LiDAR Scene Editing

2025-11-21 · Suchetan G. Uppur, Hemant Kumar, Vaibhav Kumar arxiv

Training autonomous driving and navigation systems requires large and diverse point cloud datasets that capture complex edge case scenarios from various dynamic urban settings. Acquiring such diverse scenarios from real-…

Point Cloud GenerationAutonomous DrivingPoint Clouds

Learning to Generate 4D LiDAR Sequences

2025-09-15 · Ao Liang, Youquan Liu, Yu Yang, Dongyue Lu 외 arxiv

While generative world models have advanced video and occupancy-based data synthesis, LiDAR generation remains underexplored despite its importance for accurate 3D perception. Extending generation to 4D LiDAR data introd…

Data Augmentation

LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene Reconstruction

2024-12-19 · Pou-Chun Kung, Xianling Zhang, Katherine A. Skinner, Nikita Jaipuria

Photorealistic 3D scene reconstruction plays an important role in autonomous driving, enabling the generation of novel data from existing datasets to simulate safety-critical scenarios and expand training data without ad…

3D Scene ReconstructionAutonomous DrivingSensor Modeling

GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR

2024-06-15 · Bharat Singh, Viveka Kulharia, Luyu Yang, Avinash Ravichandran 외

Multimodal synthetic data generation is crucial in domains such as autonomous driving, robotics, augmented/virtual reality, and retail. We propose a novel approach, GenMM, for jointly editing RGB videos and LiDAR scans b…

Autonomous DrivingDepth EstimationMonocular Depth EstimationSemantic Segmentation+2