Label-efficient Semantic Scene Completion with Scribble Annotations

• URL: http://arxiv.org/abs/2405.15170v1
• Date: Fri, 24 May 2024 03:09:50 GMT
• Title: Label-efficient Semantic Scene Completion with Scribble Annotations
• Authors: Song Wang, Jiawei Yu, Wentong Li, Hao Shi, Kailun Yang, Junbo Chen, Jianke Zhu,
• Abstract summary: We build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance.
• Score: 29.88371368606911
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic scene completion aims to infer the 3D geometric structures with semantic classes from camera or LiDAR, which provide essential occupancy information in autonomous driving. Prior endeavors concentrate on constructing the network or benchmark in a fully supervised manner. While the dense occupancy grids need point-wise semantic annotations, which incur expensive and tedious labeling costs. In this paper, we build a new label-efficient benchmark, named ScribbleSC, where the sparse scribble-based semantic labels are combined with dense geometric labels for semantic scene completion. In particular, we propose a simple yet effective approach called Scribble2Scene, which bridges the gap between the sparse scribble annotations and fully-supervision. Our method consists of geometric-aware auto-labelers construction and online model training with an offline-to-online distillation module to enhance the performance. Experiments on SemanticKITTI demonstrate that Scribble2Scene achieves competitive performance against the fully-supervised counterparts, showing 99% performance of the fully-supervised models with only 13.5% voxels labeled. Both annotations of ScribbleSC and our full implementation are available at https://github.com/songw-zju/Scribble2Scene.

Related papers

• You Only Click Once: Single Point Weakly Supervised 3D Instance Segmentation for Autonomous Driving [11.277350927584147]
  YoCo framework generates 3D pseudo labels using minimal coarse click annotations. A temporal and spatial-based label updating module is designed to generate reliable updated labels. An IoU-guided enhancement module is proposed, replacing pseudo labels with high-confidence and high-IoU predictions.
  arXiv  Detail & Related papers  (2025-02-27T02:33:51Z)
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label [16.745019028033518]
  We propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision. Experiments on the ScribbleSup dataset with different qualities of scribble annotations outperform all the previous methods, demonstrating the superiority and robustness of our method.
  arXiv  Detail & Related papers  (2024-02-27T14:51:56Z)
• You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding [107.06117227661204]
  We propose One Thing One Click'', meaning that the annotator only needs to label one point per object. We iteratively conduct the training and label propagation, facilitated by a graph propagation module. Our model can be compatible to 3D instance segmentation equipped with a point-clustering strategy.
  arXiv  Detail & Related papers  (2023-03-26T13:57:00Z)
• LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
  We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds. Our method co-designs an efficient labeling process with semi/weakly supervised learning. Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
  arXiv  Detail & Related papers  (2022-10-14T19:13:36Z)
• Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning [59.64695628433855]
  We propose a novel cross-modality weakly supervised method for 3D segmentation, incorporating complementary information from unlabeled images. Basically, we design a dual-branch network equipped with an active labeling strategy, to maximize the power of tiny parts of labels. Our method even outperforms the state-of-the-art fully supervised competitors with less than 1% actively selected annotations.
  arXiv  Detail & Related papers  (2022-09-16T07:59:04Z)
• Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision [65.19589997822155]
  We introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision. We show that the proposed network can be trained with cheap, or even off-the-shelf bounding box-level annotations and subcloud-level tags.
  arXiv  Detail & Related papers  (2022-01-09T09:07:48Z)
• One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation [78.36781565047656]
  We propose "One Thing One Click," meaning that the annotator only needs to label one point per object. We iteratively conduct the training and label propagation, facilitated by a graph propagation module. Our results are also comparable to those of the fully supervised counterparts.
  arXiv  Detail & Related papers  (2021-04-06T02:27:25Z)
• Weakly-Supervised Salient Object Detection via Scribble Annotations [54.40518383782725]
  We propose a weakly-supervised salient object detection model to learn saliency from scribble labels. We present a new metric, termed saliency structure measure, to measure the structure alignment of the predicted saliency maps. Our method not only outperforms existing weakly-supervised/unsupervised methods, but also is on par with several fully-supervised state-of-the-art models.
  arXiv  Detail & Related papers  (2020-03-17T12:59:50Z)

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.