Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics

• URL: http://arxiv.org/abs/2211.10580v3
• Date: Wed, 12 Feb 2025 02:27:20 GMT
• Title: Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics
• Authors: Ancheng Lin, Jun Li, Yusheng Xiang, Wei Bian, Mukesh Prasad,
• Abstract summary: We introduce a multi-modal technique that leverages 3D point clouds and 2D colour images obtained from LiDAR and camera sensors for surface normal estimation.<n>We present a novel transformer-based neural network architecture that proficiently fuses visual semantic and 3D geometric information.<n>It has been verified that the proposed model can learn from a simulated 3D environment that mimics a traffic scene.
• Score: 7.507853813361308
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: High-quality surface normal can help improve geometry estimation in problems faced by autonomous vehicles, such as collision avoidance and occlusion inference. While a considerable volume of literature focuses on densely scanned indoor scenarios, normal estimation during autonomous driving remains an intricate problem due to the sparse, non-uniform, and noisy nature of real-world LiDAR scans. In this paper, we introduce a multi-modal technique that leverages 3D point clouds and 2D colour images obtained from LiDAR and camera sensors for surface normal estimation. We present the Hybrid Geometric Transformer (HGT), a novel transformer-based neural network architecture that proficiently fuses visual semantic and 3D geometric information. Furthermore, we developed an effective learning strategy for the multi-modal data. Experimental results demonstrate the superior effectiveness of our information fusion approach compared to existing methods. It has also been verified that the proposed model can learn from a simulated 3D environment that mimics a traffic scene. The learned geometric knowledge is transferable and can be applied to real-world 3D scenes in the KITTI dataset. Further tasks built upon the estimated normal vectors in the KITTI dataset show that the proposed estimator has an advantage over existing methods.

Related papers

• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• The Oxford Spires Dataset: Benchmarking Large-Scale LiDAR-Visual Localisation, Reconstruction and Radiance Field Methods [10.265865092323041]
  This paper introduces a large-scale multi-modal dataset captured in and around well-known landmarks in Oxford. We also establish benchmarks for tasks involving localisation, reconstruction, and novel-view synthesis. Our dataset and benchmarks are intended to facilitate better integration of radiance field methods and SLAM systems.
  arXiv  Detail & Related papers  (2024-11-15T19:43:24Z)
• LLMI3D: MLLM-based 3D Perception from a Single 2D Image [77.13869413871028]
  multimodal large language models (MLLMs) excel in general capacity but underperform in 3D tasks. In this paper, we propose solutions for weak 3D local spatial object perception, poor text-based geometric numerical output, and inability to handle camera focal variations. We employ parameter-efficient fine-tuning for a pre-trained MLLM and develop LLMI3D, a powerful 3D perception MLLM.
  arXiv  Detail & Related papers  (2024-08-14T10:00:16Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• 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)
• Single-Stage 3D Geometry-Preserving Depth Estimation Model Training on Dataset Mixtures with Uncalibrated Stereo Data [4.199844472131922]
  We propose GP$2$, General-Purpose and Geometry-Preserving training scheme for single-view depth estimation. We show that GP$2$-trained models outperform methods relying on PCM in both accuracy and speed. We also show that SVDE models can learn to predict geometrically correct depth even when geometrically complete data comprises the minor part of the training set.
  arXiv  Detail & Related papers  (2023-06-05T13:49:24Z)
• 3D Harmonic Loss: Towards Task-consistent and Time-friendly 3D Object Detection on Edge for Intelligent Transportation System [28.55894241049706]
  We propose a 3D harmonic loss function to relieve the pointcloud based inconsistent predictions. Our proposed method considerably improves the performance than benchmark models. Our code is open-source and publicly available.
  arXiv  Detail & Related papers  (2022-11-07T10:11:48Z)
• Large-Scale 3D Semantic Reconstruction for Automated Driving Vehicles with Adaptive Truncated Signed Distance Function [9.414880946870916]
  We propose a novel 3D reconstruction and semantic mapping system using LiDAR and camera sensors. An Adaptive Truncated Function is introduced to describe surfaces implicitly, which can deal with different LiDAR point sparsities. An optimal image patch selection strategy is proposed to estimate the optimal semantic class for each triangle mesh.
  arXiv  Detail & Related papers  (2022-02-28T15:11:25Z)
• Geometry-Contrastive Transformer for Generalized 3D Pose Transfer [95.56457218144983]
  The intuition of this work is to perceive the geometric inconsistency between the given meshes with the powerful self-attention mechanism. We propose a novel geometry-contrastive Transformer that has an efficient 3D structured perceiving ability to the global geometric inconsistencies. We present a latent isometric regularization module together with a novel semi-synthesized dataset for the cross-dataset 3D pose transfer task.
  arXiv  Detail & Related papers  (2021-12-14T13:14:24Z)
• RandomRooms: Unsupervised Pre-training from Synthetic Shapes and Randomized Layouts for 3D Object Detection [138.2892824662943]
  A promising solution is to make better use of the synthetic dataset, which consists of CAD object models, to boost the learning on real datasets. Recent work on 3D pre-training exhibits failure when transfer features learned on synthetic objects to other real-world applications. In this work, we put forward a new method called RandomRooms to accomplish this objective.
  arXiv  Detail & Related papers  (2021-08-17T17:56:12Z)
• Learning Geometry-Guided Depth via Projective Modeling for Monocular 3D Object Detection [70.71934539556916]
  We learn geometry-guided depth estimation with projective modeling to advance monocular 3D object detection. Specifically, a principled geometry formula with projective modeling of 2D and 3D depth predictions in the monocular 3D object detection network is devised. Our method remarkably improves the detection performance of the state-of-the-art monocular-based method without extra data by 2.80% on the moderate test setting.
  arXiv  Detail & Related papers  (2021-07-29T12:30:39Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)
• DEF: Deep Estimation of Sharp Geometric Features in 3D Shapes [43.853000396885626]
  We propose a learning-based framework for predicting sharp geometric features in sampled 3D shapes. By fusing the result of individual patches, we can process large 3D models, which are impossible to process for existing data-driven methods.
  arXiv  Detail & Related papers  (2020-11-30T18:21:00Z)
• Exploring Deep 3D Spatial Encodings for Large-Scale 3D Scene Understanding [19.134536179555102]
  We propose an alternative approach to overcome the limitations of CNN based approaches by encoding the spatial features of raw 3D point clouds into undirected graph models. The proposed method achieves on par state-of-the-art accuracy with improved training time and model stability thus indicating strong potential for further research.
  arXiv  Detail & Related papers  (2020-11-29T12:56:19Z)
• 3D Dense Geometry-Guided Facial Expression Synthesis by Adversarial Learning [54.24887282693925]
  We propose a novel framework to exploit 3D dense (depth and surface normals) information for expression manipulation. We use an off-the-shelf state-of-the-art 3D reconstruction model to estimate the depth and create a large-scale RGB-Depth dataset. Our experiments demonstrate that the proposed method outperforms the competitive baseline and existing arts by a large margin.
  arXiv  Detail & Related papers  (2020-09-30T17:12:35Z)
• Towards General Purpose Geometry-Preserving Single-View Depth Estimation [1.9573380763700712]
  Single-view depth estimation (SVDE) plays a crucial role in scene understanding for AR applications, 3D modeling, and robotics. Recent works have shown that a successful solution strongly relies on the diversity and volume of training data. Our work shows that a model trained on this data along with conventional datasets can gain accuracy while predicting correct scene geometry.
  arXiv  Detail & Related papers  (2020-09-25T20:06:13Z)
• Stereo RGB and Deeper LIDAR Based Network for 3D Object Detection [40.34710686994996]
  3D object detection has become an emerging task in autonomous driving scenarios. Previous works process 3D point clouds using either projection-based or voxel-based models. We propose the Stereo RGB and Deeper LIDAR framework which can utilize semantic and spatial information simultaneously.
  arXiv  Detail & Related papers  (2020-06-09T11:19:24Z)

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.