Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts

• URL: http://arxiv.org/abs/2407.11382v2
• Date: Wed, 17 Jul 2024 06:32:53 GMT
• Title: Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts
• Authors: Jianhao Li, Tianyu Sun, Zhongdao Wang, Enze Xie, Bailan Feng, Hongbo Zhang, Ze Yuan, Ke Xu, Jiaheng Liu, Ping Luo,
• Abstract summary: This paper proposes an algorithm for automatically labeling 3D objects from 2D point or box prompts. Unlike previous arts, our auto-labeler predicts 3D shapes instead of bounding boxes and does not require training on a specific dataset.
• Score: 50.181870446016376
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper proposes an algorithm for automatically labeling 3D objects from 2D point or box prompts, especially focusing on applications in autonomous driving. Unlike previous arts, our auto-labeler predicts 3D shapes instead of bounding boxes and does not require training on a specific dataset. We propose a Segment, Lift, and Fit (SLF) paradigm to achieve this goal. Firstly, we segment high-quality instance masks from the prompts using the Segment Anything Model (SAM) and transform the remaining problem into predicting 3D shapes from given 2D masks. Due to the ill-posed nature of this problem, it presents a significant challenge as multiple 3D shapes can project into an identical mask. To tackle this issue, we then lift 2D masks to 3D forms and employ gradient descent to adjust their poses and shapes until the projections fit the masks and the surfaces conform to surrounding LiDAR points. Notably, since we do not train on a specific dataset, the SLF auto-labeler does not overfit to biased annotation patterns in the training set as other methods do. Thus, the generalization ability across different datasets improves. Experimental results on the KITTI dataset demonstrate that the SLF auto-labeler produces high-quality bounding box annotations, achieving an AP@0.5 IoU of nearly 90\%. Detectors trained with the generated pseudo-labels perform nearly as well as those trained with actual ground-truth annotations. Furthermore, the SLF auto-labeler shows promising results in detailed shape predictions, providing a potential alternative for the occupancy annotation of dynamic objects.

Related papers

• Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking [6.599971425078935]
  Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks. This challenge arises from their unsupervised merging approach, where dense 2D masks are lifted across frames into point clouds to form 3D candidate proposals without direct supervision. We propose a 3D-Aware 2D Mask Tracking module that uses robust 3D priors from a 2D mask segmentation and tracking foundation model (SAM-2) to ensure consistent object masks across video frames.
  arXiv  Detail & Related papers  (2024-11-25T08:26:31Z)
• TrajSSL: Trajectory-Enhanced Semi-Supervised 3D Object Detection [59.498894868956306]
  Pseudo-labeling approaches to semi-supervised learning adopt a teacher-student framework. We leverage pre-trained motion-forecasting models to generate object trajectories on pseudo-labeled data. Our approach improves pseudo-label quality in two distinct manners.
  arXiv  Detail & Related papers  (2024-09-17T05:35:00Z)
• ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only [5.699475977818167]
  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.
  arXiv  Detail & Related papers  (2024-07-24T11:58:31Z)
• Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation [67.07112533415116]
  We present a novel framework that adapts various foundational models for the 3D point cloud segmentation task. Our approach involves making initial predictions of 2D semantic masks using different large vision models. To generate robust 3D semantic pseudo labels, we introduce a semantic label fusion strategy that effectively combines all the results via voting.
  arXiv  Detail & Related papers  (2023-11-03T15:41:15Z)
• Segment Anything in 3D with Radiance Fields [83.14130158502493]
  This paper generalizes the Segment Anything Model (SAM) to segment 3D objects. We refer to the proposed solution as SA3D, short for Segment Anything in 3D. We show in experiments that SA3D adapts to various scenes and achieves 3D segmentation within seconds.
  arXiv  Detail & Related papers  (2023-04-24T17:57:15Z)
• Panoptic Lifting for 3D Scene Understanding with Neural Fields [32.59498558663363]
  We propose a novel approach for learning panoptic 3D representations from images of in-the-wild scenes. Our method requires only machine-generated 2D panoptic segmentation masks inferred from a pre-trained network. Experimental results validate our approach on the challenging Hypersim, Replica, and ScanNet datasets.
  arXiv  Detail & Related papers  (2022-12-19T19:15:36Z)
• Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders [52.91248611338202]
  We propose an alternative to obtain superior 3D representations from 2D pre-trained models via Image-to-Point Masked Autoencoders, named as I2P-MAE. By self-supervised pre-training, we leverage the well learned 2D knowledge to guide 3D masked autoencoding. I2P-MAE attains the state-of-the-art 90.11% accuracy, +3.68% to the second-best, demonstrating superior transferable capacity.
  arXiv  Detail & Related papers  (2022-12-13T17:59:20Z)
• Multimodal Transformer for Automatic 3D Annotation and Object Detection [27.92241487946078]
  We propose an end-to-end multimodal transformer (MTrans) autolabeler to generate precise 3D box annotations from weak 2D bounding boxes. With a multi-task design, MTrans segments the foreground/background, densifies LiDAR point clouds, and regresses 3D boxes simultaneously. By enriching the sparse point clouds, our method achieves 4.48% and 4.03% better 3D AP on KITTI moderate and hard samples, respectively.
  arXiv  Detail & Related papers  (2022-07-20T10:38:29Z)
• 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)
• 3D Guided Weakly Supervised Semantic Segmentation [27.269847900950943]
  We propose a weakly supervised 2D semantic segmentation model by incorporating sparse bounding box labels with available 3D information. We manually labeled a subset of the 2D-3D Semantics(2D-3D-S) dataset with bounding boxes, and introduce our 2D-3D inference module to generate accurate pixel-wise segment proposal masks.
  arXiv  Detail & Related papers  (2020-12-01T03:34:15Z)

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.