L3DR: 3D-aware LiDAR Diffusion and Rectification

• URL: http://arxiv.org/abs/2602.19064v1
• Date: Sun, 22 Feb 2026 06:31:58 GMT
• Title: L3DR: 3D-aware LiDAR Diffusion and Rectification
• Authors: Quan Liu, Xiaoqin Zhang, Ling Shao, Shijian Lu,
• Abstract summary: Range-view (RV) based LiDAR diffusion has recently made huge strides towards 2D photo-realism.<n>However, it neglects 3D geometry realism and often generates various RV artifacts such as depth bleeding and wavy surfaces.<n>We design L3DR, a 3D-aware LiDAR Diffusion and Rectification framework that can regress and cancel RV artifacts in 3D space.
• Score: 85.5914944339043
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Range-view (RV) based LiDAR diffusion has recently made huge strides towards 2D photo-realism. However, it neglects 3D geometry realism and often generates various RV artifacts such as depth bleeding and wavy surfaces. We design L3DR, a 3D-aware LiDAR Diffusion and Rectification framework that can regress and cancel RV artifacts in 3D space and restore local geometry accurately. Our theoretical and empirical analysis reveals that 3D models are inherently superior to 2D models in generating sharp and authentic boundaries. Leveraging such analysis, we design a 3D residual regression network that rectifies RV artifacts and achieves superb geometry realism by predicting point-level offsets in 3D space. On top of that, we design a Welsch Loss that helps focus on local geometry and ignore anomalous regions effectively. Extensive experiments over multiple benchmarks including KITTI, KITTI360, nuScenes and Waymo show that the proposed L3DR achieves state-of-the-art generation and superior geometry-realism consistently. In addition, L3DR is generally applicable to different LiDAR diffusion models with little computational overhead.

Related papers

• Robust Mesh Saliency GT Acquisition in VR via View Cone Sampling and Geometric Smoothing [59.12032628787018]
  3D mesh saliency ground truth is essential for human-centric visual modeling in virtual reality (VR)<n>Current VR eye-tracking pipelines rely on single ray sampling and Euclidean smoothing, triggering texture attention and signal leakage across gaps.<n>This paper proposes a robust framework to address these limitations.
  arXiv  Detail & Related papers  (2026-01-06T05:20:12Z)
• Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors [17.544733016978928]
  3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture. We propose bridging the gap between 2D and 3D diffusion models to address this limitation.
  arXiv  Detail & Related papers  (2024-10-12T10:14:11Z)
• R3D-AD: Reconstruction via Diffusion for 3D Anomaly Detection [12.207437451118036]
  3D anomaly detection plays a crucial role in monitoring parts for localized inherent defects in precision manufacturing. Embedding-based and reconstruction-based approaches are among the most popular and successful methods. We propose R3D-AD, reconstructing anomalous point clouds by diffusion model for precise 3D anomaly detection.
  arXiv  Detail & Related papers  (2024-07-15T16:10:58Z)
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking.<n>We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images.<n>We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
  arXiv  Detail & Related papers  (2024-03-26T17:21:24Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception [122.53774221136193]
  State-of-the-art methods for driving-scene LiDAR-based perception often project the point clouds to 2D space and then process them via 2D convolution. A natural remedy is to utilize the 3D voxelization and 3D convolution network. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern.
  arXiv  Detail & Related papers  (2021-09-12T06:25:11Z)
• Learning to Drop Points for LiDAR Scan Synthesis [5.132259673802809]
  Generative modeling of 3D scenes is a crucial topic for aiding mobile robots to improve unreliable observations. Most existing studies on point clouds have focused on small and uniform-density data. 3D LiDAR point clouds widely used in mobile robots are non-trivial to be handled because of the large number of points and varying-density. This paper proposes a novel framework based on generative adversarial networks to synthesize realistic LiDAR data as an improved 2D representation.
  arXiv  Detail & Related papers  (2021-02-23T21:53:14Z)
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation [81.02742110604161]
  State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. We propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pat-tern. Our method achieves the 1st place in the leaderboard of Semantic KITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%.
  arXiv  Detail & Related papers  (2020-11-19T18:53:11Z)
• Cylinder3D: An Effective 3D Framework for Driving-scene LiDAR Semantic Segmentation [87.54570024320354]
  State-of-the-art methods for large-scale driving-scene LiDAR semantic segmentation often project and process the point clouds in the 2D space. A straightforward solution to tackle the issue of 3D-to-2D projection is to keep the 3D representation and process the points in the 3D space. We develop a 3D cylinder partition and a 3D cylinder convolution based framework, termed as Cylinder3D, which exploits the 3D topology relations and structures of driving-scene point clouds.
  arXiv  Detail & Related papers  (2020-08-04T13:56:19Z)

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.