A Vision-Centric Approach for Static Map Element Annotation

• URL: http://arxiv.org/abs/2309.11754v2
• Date: Sat, 17 Feb 2024 04:37:28 GMT
• Title: A Vision-Centric Approach for Static Map Element Annotation
• Abstract summary: We present CAMA: a vision-centric approach for Consistent Map and Accurate. Without LiDAR inputs, our proposed framework can still generate high-quality 3D annotations of static map elements. We apply our proposed framework to the popular nuScenes dataset to provide efficient and highly accurate annotations.
• Score: 9.905900964784564
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The recent development of online static map element (a.k.a. HD Map) construction algorithms has raised a vast demand for data with ground truth annotations. However, available public datasets currently cannot provide high-quality training data regarding consistency and accuracy. To this end, we present CAMA: a vision-centric approach for Consistent and Accurate Map Annotation. Without LiDAR inputs, our proposed framework can still generate high-quality 3D annotations of static map elements. Specifically, the annotation can achieve high reprojection accuracy across all surrounding cameras and is spatial-temporal consistent across the whole sequence. We apply our proposed framework to the popular nuScenes dataset to provide efficient and highly accurate annotations. Compared with the original nuScenes static map element, models trained with annotations from CAMA achieve lower reprojection errors (e.g., 4.73 vs. 8.03 pixels).

Related papers

• Interacted Planes Reveal 3D Line Mapping [73.60851338875962]
  LiP-Map is a line-plane joint optimization framework for 3D line mapping.<n>On more than 100 scenes from ScanNetV2, ScanNet++, Hypersim, 7Scenes, and Tanks&Temple, LiP-Map improves both accuracy and completeness over state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-01T15:52:55Z)
• Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping [9.016750201407897]
  HD mapping approaches outsource the projection to standard mapping techniques, such as attention-based ones.<n>Our key idea is to start with a geometric mapping based on camera parameters and adapt it to the scene to extract relevant map information.<n> Experiments on new splits of the nuScenes and Argoverse2 datasets demonstrate improved performance over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-08-29T14:55:33Z)
• Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images [56.134885746889026]
  semantic scene graph estimation methods utilize ground truth 3D annotations to accurately predict target objects, predicates, and relationships.<n>We overcome the noisy reconstructed pseudo point-based geometry from predicted depth maps and reduce the amount of background noise present in multi-view image features.<n>Our method outperforms current methods purely using multi-view images as the initial input.
  arXiv  Detail & Related papers  (2025-08-05T21:25:50Z)
• Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation [14.480713752871521]
  MapUnveiler is a novel paradigm of clip-level vectorized HD map construction. It unveils the occluded map elements within a clip input by relating dense image representations with efficient clip tokens. MapUnveiler associates inter-clip information through clip token propagation, effectively utilizing long-term temporal map information.
  arXiv  Detail & Related papers  (2024-11-17T08:38:18Z)
• SCRREAM : SCan, Register, REnder And Map:A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark [43.88114765730359]
  SCRREAM allows annotation of fully dense meshes of objects in the scene and registers camera poses on the real image sequence. We show the details of the dataset annotation pipeline and showcase four possible variants of datasets. Recent pipelines for indoor reconstruction and SLAM serve as new benchmarks.
  arXiv  Detail & Related papers  (2024-10-30T05:53:07Z)
• CAMAv2: A Vision-Centric Approach for Static Map Element Annotation [15.764785952277931]
  We present CAMAv2, a vision-centric approach for Consistent and Accurate Map. We apply our proposed framework to the popular nuScenes dataset to provide efficient and highly accurate annotations. Compared with the original nuScenes static map element, our CAMAv2 annotations achieve lower reprojection errors.
  arXiv  Detail & Related papers  (2024-07-31T04:41:49Z)
• 3D LiDAR Mapping in Dynamic Environments Using a 4D Implicit Neural Representation [33.92758288570465]
  Building accurate maps is a key building block to enable reliable localization, planning, and navigation of autonomous vehicles. We propose encoding the 4D scene into a novel implicit neural map representation. Our method is capable of removing the dynamic part of the input point clouds while reconstructing accurate and complete 3D maps.
  arXiv  Detail & Related papers  (2024-05-06T11:46:04Z)
• Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud? [72.40353149833109]
  Current state-of-the-art (SOTA) 3D object detection methods often require a large amount of 3D bounding box annotations for training. We propose a novel sparsely-annotated framework, in which we just annotate one 3D object per scene. We develop the SS3D++ method that alternatively improves 3D detector training and confident fully-annotated scene generation.
  arXiv  Detail & Related papers  (2024-03-05T09:38:11Z)
• Volumetric Semantically Consistent 3D Panoptic Mapping [77.13446499924977]
  We introduce an online 2D-to-3D semantic instance mapping algorithm aimed at generating semantic 3D maps suitable for autonomous agents in unstructured environments. It introduces novel ways of integrating semantic prediction confidence during mapping, producing semantic and instance-consistent 3D regions. The proposed method achieves accuracy superior to the state of the art on public large-scale datasets, improving on a number of widely used metrics.
  arXiv  Detail & Related papers  (2023-09-26T08:03:10Z)
• Neural Semantic Surface Maps [52.61017226479506]
  We present an automated technique for computing a map between two genus-zero shapes, which matches semantically corresponding regions to one another. Our approach can generate semantic surface-to-surface maps, eliminating manual annotations or any 3D training data requirement.
  arXiv  Detail & Related papers  (2023-09-09T16:21:56Z)
• MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction [40.07726377230152]
  High-definition (HD) map provides abundant and precise static environmental information of the driving scene. We present textbfMap textbfTRansformer, an end-to-end framework for online vectorized HD map construction.
  arXiv  Detail & Related papers  (2023-08-10T17:56:53Z)
• PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking [90.29143475328506]
  We introduce PointOdyssey, a large-scale synthetic dataset, and data generation framework. Our goal is to advance the state-of-the-art by placing emphasis on long videos with naturalistic motion. We animate deformable characters using real-world motion capture data, we build 3D scenes to match the motion capture environments, and we render camera viewpoints using trajectories mined via structure-from-motion on real videos.
  arXiv  Detail & Related papers  (2023-07-27T17:58:11Z)
• Weakly Supervised 3D Object Detection with Multi-Stage Generalization [62.96670547848691]
  We introduce BA$2$-Det, encompassing pseudo label generation and multi-stage generalization. We develop three stages of generalization: progressing from complete to partial, static to dynamic, and close to distant. BA$2$-Det can achieve a 20% relative improvement on the KITTI dataset.
  arXiv  Detail & Related papers  (2023-06-08T17:58:57Z)
• SCFusion: Real-time Incremental Scene Reconstruction with Semantic Completion [86.77318031029404]
  We propose a framework that performs scene reconstruction and semantic scene completion jointly in an incremental and real-time manner. Our framework relies on a novel neural architecture designed to process occupancy maps and leverages voxel states to accurately and efficiently fuse semantic completion with the 3D global model.
  arXiv  Detail & Related papers  (2020-10-26T15:31:52Z)

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.