VRSO: Visual-Centric Reconstruction for Static Object Annotation

• URL: http://arxiv.org/abs/2403.15026v3
• Date: Fri, 30 Aug 2024 03:10:59 GMT
• Title: VRSO: Visual-Centric Reconstruction for Static Object Annotation
• Authors: Chenyao Yu, Yingfeng Cai, Jiaxin Zhang, Hui Kong, Wei Sui, Cong Yang,
• Abstract summary: This paper introduces VRSO, a visual-centric approach for static object annotation. VRSO is distinguished in low cost, high efficiency, and high quality. It recovers static objects in 3D space with only camera images as input.
• Score: 21.70421057949981
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As a part of the perception results of intelligent driving systems, static object detection (SOD) in 3D space provides crucial cues for driving environment understanding. With the rapid deployment of deep neural networks for SOD tasks, the demand for high-quality training samples soars. The traditional, also reliable, way is manual labelling over the dense LiDAR point clouds and reference images. Though most public driving datasets adopt this strategy to provide SOD ground truth (GT), it is still expensive and time-consuming in practice. This paper introduces VRSO, a visual-centric approach for static object annotation. Experiments on the Waymo Open Dataset show that the mean reprojection error from VRSO annotation is only 2.6 pixels, around four times lower than the Waymo Open Dataset labels (10.6 pixels). VRSO is distinguished in low cost, high efficiency, and high quality: (1) It recovers static objects in 3D space with only camera images as input, and (2) manual annotation is barely involved since GT for SOD tasks is generated based on an automatic reconstruction and annotation pipeline.

Related papers

• VESPA: Towards un(Human)supervised Open-World Pointcloud Labeling for Autonomous Driving [1.623951368574041]
  We introduce VESPA, a multimodal autolabeling pipeline that fuses the geometric precision of LiDAR with the semantic richness of camera images.<n> VESPA supports the discovery of novel categories and produces high-quality 3D pseudolabels without requiring ground-truth annotations or HD maps.<n>On Nuscenes dataset, VESPA achieves an AP of 52.95% for object discovery and up to 46.54% for multiclass object detection.
  arXiv  Detail & Related papers  (2025-07-27T19:39:29Z)
• EGSRAL: An Enhanced 3D Gaussian Splatting based Renderer with Automated Labeling for Large-Scale Driving Scene [19.20846992699852]
  We propose EGSRAL, a 3D GS-based method that relies solely on training images without extra annotations. EGSRAL enhances 3D GS's capability to model both dynamic objects and static backgrounds. We also propose a grouping strategy for vanilla 3D GS to address perspective issues in rendering large-scale, complex scenes.
  arXiv  Detail & Related papers  (2024-12-20T04:21:54Z)
• Street Gaussians without 3D Object Tracker [86.62329193275916]
  Existing methods rely on labor-intensive manual labeling of object poses to reconstruct dynamic objects in canonical space. We propose a stable object tracking module by leveraging associations from 2D deep trackers within a 3D object fusion strategy. We address inevitable tracking errors by further introducing a motion learning strategy in an implicit feature space that autonomously corrects trajectory errors and recovers missed detections.
  arXiv  Detail & Related papers  (2024-12-07T05:49:42Z)
• Vision-Language Guidance for LiDAR-based Unsupervised 3D Object Detection [16.09503890891102]
  We propose an unsupervised 3D detection approach that operates exclusively on LiDAR point clouds. We exploit the inherent CLI-temporal knowledge of LiDAR point clouds for clustering, tracking, as well as boxtext and label refinement. Our approach outperforms state-of-the-art unsupervised 3D object detectors on the Open dataset.
  arXiv  Detail & Related papers  (2024-08-07T14:14:53Z)
• Neural Rendering based Urban Scene Reconstruction for Autonomous Driving [8.007494499012624]
  We propose a multimodal 3D scene reconstruction using a framework combining neural implicit surfaces and radiance fields. Dense 3D reconstruction has many applications in automated driving including automated annotation validation. We demonstrate qualitative and quantitative results on challenging automotive scenes.
  arXiv  Detail & Related papers  (2024-02-09T23:20:23Z)
• 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)
• View-to-Label: Multi-View Consistency for Self-Supervised 3D Object Detection [46.077668660248534]
  We propose a novel approach to self-supervise 3D object detection purely from RGB sequences alone. Our experiments on KITTI 3D dataset demonstrate performance on par with state-of-the-art self-supervised methods.
  arXiv  Detail & Related papers  (2023-05-29T09:30:39Z)
• Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection [90.32180043449263]
  State-of-the-art 3D object detectors are usually trained on large-scale datasets with high-quality 3D annotations. A natural remedy is to adopt semi-supervised learning (SSL) by leveraging a limited amount of labeled samples and abundant unlabeled samples. This paper introduces a novel approach of Hierarchical Supervision and Shuffle Data Augmentation (HSSDA), which is a simple yet effective teacher-student framework.
  arXiv  Detail & Related papers  (2023-04-04T02:09:32Z)
• ALSO: Automotive Lidar Self-supervision by Occupancy estimation [70.70557577874155]
  We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information.
  arXiv  Detail & Related papers  (2022-12-12T13:10:19Z)
• BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios [51.285561119993105]
  We present BEV-MAE, an efficient masked autoencoder pre-training framework for LiDAR-based 3D object detection in autonomous driving. Specifically, we propose a bird's eye view (BEV) guided masking strategy to guide the 3D encoder learning feature representation. We introduce a learnable point token to maintain a consistent receptive field size of the 3D encoder.
  arXiv  Detail & Related papers  (2022-12-12T08:15:03Z)
• Learnable Online Graph Representations for 3D Multi-Object Tracking [156.58876381318402]
  We propose a unified and learning based approach to the 3D MOT problem. We employ a Neural Message Passing network for data association that is fully trainable. We show the merit of the proposed approach on the publicly available nuScenes dataset by achieving state-of-the-art performance of 65.6% AMOTA and 58% fewer ID-switches.
  arXiv  Detail & Related papers  (2021-04-23T17:59:28Z)
• SESS: Self-Ensembling Semi-Supervised 3D Object Detection [138.80825169240302]
  We propose SESS, a self-ensembling semi-supervised 3D object detection framework. Specifically, we design a thorough perturbation scheme to enhance generalization of the network on unlabeled and new unseen data. Our SESS achieves competitive performance compared to the state-of-the-art fully-supervised method by using only 50% labeled data.
  arXiv  Detail & Related papers  (2019-12-26T08:48:04Z)

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.