MonoSOWA: Scalable monocular 3D Object detector Without human Annotations

• URL: http://arxiv.org/abs/2501.09481v2
• Date: Mon, 10 Mar 2025 12:27:10 GMT
• Title: MonoSOWA: Scalable monocular 3D Object detector Without human Annotations
• Authors: Jan Skvrna, Lukas Neumann,
• Abstract summary: We present a novel method to train a 3D object detector from a single RGB camera without domain-specific human annotations.<n>The method is evaluated on three public datasets, where despite using no human labels, it outperforms prior work by a significant margin.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inferring object 3D position and orientation from a single RGB camera is a foundational task in computer vision with many important applications. Traditionally, 3D object detection methods are trained in a fully-supervised setup, requiring LiDAR and vast amounts of human annotations, which are laborious, costly, and do not scale well with the ever-increasing amounts of data being captured. We present a novel method to train a 3D object detector from a single RGB camera without domain-specific human annotations, making orders of magnitude more data available for training. The method uses newly proposed Local Object Motion Model to disentangle object movement source between subsequent frames, is approximately 700 times faster than previous work and compensates camera focal length differences to aggregate multiple datasets. The method is evaluated on three public datasets, where despite using no human labels, it outperforms prior work by a significant margin. It also shows its versatility as a pre-training tool for fully-supervised training and shows that combining pseudo-labels from multiple datasets can achieve comparable accuracy to using human labels from a single dataset. The source code and model will be published soon.

Related papers

• Shelf-Supervised Cross-Modal Pre-Training for 3D Object Detection [52.66283064389691]
  State-of-the-art 3D object detectors are often trained on massive labeled datasets. Recent works demonstrate that self-supervised pre-training with unlabeled data can improve detection accuracy with limited labels. We propose a shelf-supervised approach for generating zero-shot 3D bounding boxes from paired RGB and LiDAR data.
  arXiv  Detail & Related papers  (2024-06-14T15:21:57Z)
• MDT3D: Multi-Dataset Training for LiDAR 3D Object Detection Generalization [3.8243923744440926]
  3D object detection models trained on a source dataset with a specific point distribution have shown difficulties in generalizing to unseen datasets. We leverage the information available from several annotated source datasets with our Multi-Dataset Training for 3D Object Detection (MDT3D) method. We show how we managed the mix of datasets during training and finally introduce a new cross-dataset augmentation method: cross-dataset object injection.
  arXiv  Detail & Related papers  (2023-08-02T08:20:00Z)
• MonoNext: A 3D Monocular Object Detection with ConvNext [69.33657875725747]
  This paper introduces a new Multi-Tasking Learning approach called MonoNext for 3D Object Detection. MonoNext employs a straightforward approach based on the ConvNext network and requires only 3D bounding box data. In our experiments with the KITTI dataset, MonoNext achieved high precision and competitive performance comparable with state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-08-01T15:15:40Z)
• 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)
• Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency [78.76508318592552]
  Monocular 3D object detection has become a mainstream approach in automatic driving for its easy application. Most current methods still rely on 3D point cloud data for labeling the ground truths used in the training phase. We propose a new weakly supervised monocular 3D objection detection method, which can train the model with only 2D labels marked on images.
  arXiv  Detail & Related papers  (2023-03-15T15:14:00Z)
• Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving [91.39625612027386]
  We propose a novel task, called generalized few-shot 3D object detection, where we have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes. Specifically, we analyze in-depth differences between images and point clouds, and then present a practical principle for the few-shot setting in the 3D LiDAR dataset. To solve this task, we propose an incremental fine-tuning method to extend existing 3D detection models to recognize both common and rare objects.
  arXiv  Detail & Related papers  (2023-02-08T07:11:36Z)
• MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation [55.96577490779591]
  Methods need to have a degree of 'camera independence' in order to benefit from large and heterogeneous training data. We show that more data does not automatically guarantee a better performance, but rather, methods need to have a degree of 'camera independence' in order to benefit from large and heterogeneous training data.
  arXiv  Detail & Related papers  (2021-10-01T14:56:37Z)
• 3D Annotation Of Arbitrary Objects In The Wild [0.0]
  We propose a data annotation pipeline based on SLAM, 3D reconstruction, and 3D-to-2D geometry. The pipeline allows creating 3D and 2D bounding boxes, along with per-pixel annotations of arbitrary objects. Our results showcase almost 90% Intersection-over-Union (IoU) agreement on both semantic segmentation and 2D bounding box detection.
  arXiv  Detail & Related papers  (2021-09-15T09:00:56Z)
• MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision [72.5863451123577]
  We show how to train a neural model that can perform accurate 3D pose and camera estimation. Our method outperforms both classical bundle adjustment and weakly-supervised monocular 3D baselines.
  arXiv  Detail & Related papers  (2021-08-10T18:39:56Z)
• Monocular Quasi-Dense 3D Object Tracking [99.51683944057191]
  A reliable and accurate 3D tracking framework is essential for predicting future locations of surrounding objects and planning the observer's actions in numerous applications such as autonomous driving. We propose a framework that can effectively associate moving objects over time and estimate their full 3D bounding box information from a sequence of 2D images captured on a moving platform.
  arXiv  Detail & Related papers  (2021-03-12T15:30:02Z)
• CanonPose: Self-Supervised Monocular 3D Human Pose Estimation in the Wild [31.334715988245748]
  We propose a self-supervised approach that learns a single image 3D pose estimator from unlabeled multi-view data. In contrast to most existing methods, we do not require calibrated cameras and can therefore learn from moving cameras. Key to the success are new, unbiased reconstruction objectives that mix information across views and training samples.
  arXiv  Detail & Related papers  (2020-11-30T10:42:27Z)
• BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View [117.44028458220427]
  On-board 3D object detection in autonomous vehicles often relies on geometry information captured by LiDAR devices. We present a fully end-to-end 3D object detection framework that can infer oriented 3D boxes solely from BEV images.
  arXiv  Detail & Related papers  (2020-03-09T15:08:40Z)

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.