ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only

• URL: http://arxiv.org/abs/2407.17197v1
• Date: Wed, 24 Jul 2024 11:58:31 GMT
• Title: ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only
• Authors: Saad Lahlali, Nicolas Granger, Hervé Le Borgne, Quoc-Cuong Pham,
• Abstract summary: 3D object detection plays a crucial role in various applications such as autonomous vehicles, robotics and augmented reality. We propose a weakly supervised 3D annotator that relies solely on 2D bounding box annotations from images, along with size priors.
• Score: 5.699475977818167
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 3D object detection plays a crucial role in various applications such as autonomous vehicles, robotics and augmented reality. However, training 3D detectors requires a costly precise annotation, which is a hindrance to scaling annotation to large datasets. To address this challenge, we propose a weakly supervised 3D annotator that relies solely on 2D bounding box annotations from images, along with size priors. One major problem is that supervising a 3D detection model using only 2D boxes is not reliable due to ambiguities between different 3D poses and their identical 2D projection. We introduce a simple yet effective and generic solution: we build 3D proxy objects with annotations by construction and add them to the training dataset. Our method requires only size priors to adapt to new classes. To better align 2D supervision with 3D detection, our method ensures depth invariance with a novel expression of the 2D losses. Finally, to detect more challenging instances, our annotator follows an offline pseudo-labelling scheme which gradually improves its 3D pseudo-labels. Extensive experiments on the KITTI dataset demonstrate that our method not only performs on-par or above previous works on the Car category, but also achieves performance close to fully supervised methods on more challenging classes. We further demonstrate the effectiveness and robustness of our method by being the first to experiment on the more challenging nuScenes dataset. We additionally propose a setting where weak labels are obtained from a 2D detector pre-trained on MS-COCO instead of human annotations.

Related papers

• Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance [72.6809373191638]
  We propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Third, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data.
  arXiv  Detail & Related papers  (2023-12-12T18:57:25Z)
• 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)
• Homography Loss for Monocular 3D Object Detection [54.04870007473932]
  A differentiable loss function, termed as Homography Loss, is proposed to achieve the goal, which exploits both 2D and 3D information. Our method yields the best performance compared with the other state-of-the-arts by a large margin on KITTI 3D datasets.
  arXiv  Detail & Related papers  (2022-04-02T03:48:03Z)
• FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection [81.79171905308827]
  We propose frustum-aware geometric reasoning (FGR) to detect vehicles in point clouds without any 3D annotations. Our method consists of two stages: coarse 3D segmentation and 3D bounding box estimation. It is able to accurately detect objects in 3D space with only 2D bounding boxes and sparse point clouds.
  arXiv  Detail & Related papers  (2021-05-17T07:29:55Z)
• FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection [78.00922683083776]
  It is non-trivial to make a general adapted 2D detector work in this 3D task. In this technical report, we study this problem with a practice built on fully convolutional single-stage detector. Our solution achieves 1st place out of all the vision-only methods in the nuScenes 3D detection challenge of NeurIPS 2020.
  arXiv  Detail & Related papers  (2021-04-22T09:35:35Z)
• PLUME: Efficient 3D Object Detection from Stereo Images [95.31278688164646]
  Existing methods tackle the problem in two steps: first depth estimation is performed, a pseudo LiDAR point cloud representation is computed from the depth estimates, and then object detection is performed in 3D space. We propose a model that unifies these two tasks in the same metric space. Our approach achieves state-of-the-art performance on the challenging KITTI benchmark, with significantly reduced inference time compared with existing methods.
  arXiv  Detail & Related papers  (2021-01-17T05:11:38Z)
• Move to See Better: Self-Improving Embodied Object Detection [35.461141354989714]
  We propose a method for improving object detection in testing environments. Our agent collects multi-view data, generates 2D and 3D pseudo-labels, and fine-tunes its detector in a self-supervised manner.
  arXiv  Detail & Related papers  (2020-11-30T19:16:51Z)
• Learning to Predict the 3D Layout of a Scene [0.3867363075280544]
  We propose a method that only uses a single RGB image, thus enabling applications in devices or vehicles that do not have LiDAR sensors. We use the KITTI dataset for training, which consists of street traffic scenes with class labels, 2D bounding boxes and 3D annotations with seven degrees of freedom. We achieve a mean average precision of 47.3% for moderately difficult data, measured at a 3D intersection over union threshold of 70%, as required by the official KITTI benchmark; outperforming previous state-of-the-art single RGB only methods by a large margin.
  arXiv  Detail & Related papers  (2020-11-19T17:23:30Z)
• 3D for Free: Crossmodal Transfer Learning using HD Maps [36.70550754737353]
  We leverage the large class-taxonomies of modern 2D datasets and the robustness of state-of-the-art 2D detection methods. We mine a collection of 1151 unlabeled, multimodal driving logs from an autonomous vehicle. We show that detector performance increases as we mine more unlabeled data.
  arXiv  Detail & Related papers  (2020-08-24T17:54:51Z)

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.