Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds

• URL: http://arxiv.org/abs/2010.15157v2
• Date: Fri, 12 Feb 2021 17:46:31 GMT
• Title: Panoster: End-to-end Panoptic Segmentation of LiDAR Point Clouds
• Authors: Stefano Gasperini, Mohammad-Ali Nikouei Mahani, Alvaro Marcos-Ramiro, Nassir Navab, Federico Tombari
• Abstract summary: We present Panoster, a novel proposal-free panoptic segmentation method for LiDAR point clouds. Unlike previous approaches, Panoster proposes a simplified framework incorporating a learning-based clustering solution to identify instances. At inference time, this acts as a class-agnostic segmentation, allowing Panoster to be fast, while outperforming prior methods in terms of accuracy.
• Score: 81.12016263972298
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Panoptic segmentation has recently unified semantic and instance segmentation, previously addressed separately, thus taking a step further towards creating more comprehensive and efficient perception systems. In this paper, we present Panoster, a novel proposal-free panoptic segmentation method for LiDAR point clouds. Unlike previous approaches relying on several steps to group pixels or points into objects, Panoster proposes a simplified framework incorporating a learning-based clustering solution to identify instances. At inference time, this acts as a class-agnostic segmentation, allowing Panoster to be fast, while outperforming prior methods in terms of accuracy. Without any post-processing, Panoster reached state-of-the-art results among published approaches on the challenging SemanticKITTI benchmark, and further increased its lead by exploiting heuristic techniques. Additionally, we showcase how our method can be flexibly and effectively applied on diverse existing semantic architectures to deliver panoptic predictions.

Related papers

• Rethinking Range View Representation for LiDAR Segmentation [66.73116059734788]
  "Many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer, a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks.
  arXiv  Detail & Related papers  (2023-03-09T16:13:27Z)
• PUPS: Point Cloud Unified Panoptic Segmentation [13.668363631123649]
  We propose a simple but effective point cloud unified panoptic segmentation (PUPS) framework. PUPS uses a set of point-level classifiers to directly predict semantic and instance groupings in an end-to-end manner. PUPS achieves 1st place on the leader board of Semantic KITTI panoptic segmentation task and state-of-the-art results on nuScenes.
  arXiv  Detail & Related papers  (2023-02-13T08:42:41Z)
• Pointly-Supervised Panoptic Segmentation [106.68888377104886]
  We propose a new approach to applying point-level annotations for weakly-supervised panoptic segmentation. Instead of the dense pixel-level labels used by fully supervised methods, point-level labels only provide a single point for each target as supervision. We formulate the problem in an end-to-end framework by simultaneously generating panoptic pseudo-masks from point-level labels and learning from them.
  arXiv  Detail & Related papers  (2022-10-25T12:03:51Z)
• A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction [115.9169213834476]
  This paper offers a comprehensive review on label-efficient segmentation methods. We first develop a taxonomy to organize these methods according to the supervision provided by different types of weak labels. Next, we summarize the existing label-efficient segmentation methods from a unified perspective.
  arXiv  Detail & Related papers  (2022-07-04T06:21:01Z)
• Beyond the Prototype: Divide-and-conquer Proxies for Few-shot Segmentation [63.910211095033596]
  Few-shot segmentation aims to segment unseen-class objects given only a handful of densely labeled samples. We propose a simple yet versatile framework in the spirit of divide-and-conquer. Our proposed approach, named divide-and-conquer proxies (DCP), allows for the development of appropriate and reliable information.
  arXiv  Detail & Related papers  (2022-04-21T06:21:14Z)
• Proposal-free Lidar Panoptic Segmentation with Pillar-level Affinity [10.378476897786571]
  We jointly optimize semantic segmentation and class-agnostic instance classification in a single network. Our experiments on nuScenes dataset show that our approach outperforms previous proposal-free methods.
  arXiv  Detail & Related papers  (2022-04-19T08:39:37Z)
• Weighted Sparse Subspace Representation: A Unified Framework for Subspace Clustering, Constrained Clustering, and Active Learning [0.3553493344868413]
  We first propose a novel spectral-based subspace clustering algorithm that seeks to represent each point as a sparse convex combination of a few nearby points. We then extend the algorithm to constrained clustering and active learning settings. Our motivation for developing such a framework stems from the fact that typically either a small amount of labelled data is available in advance; or it is possible to label some points at a cost.
  arXiv  Detail & Related papers  (2021-06-08T13:39:43Z)
• Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation [21.296942497092402]
  We present a fast and robust LiDAR point cloud panoptic segmentation framework, referred to as Panoptic-PolarNet. We learn both semantic segmentation and class-agnostic instance clustering in a single inference network using a polar Bird's Eye View representation. Our experiments show that Panoptic-PolarNet outperforms the baseline methods on Semantic KITTI and nuScenes datasets with an almost real-time inference speed.
  arXiv  Detail & Related papers  (2021-03-27T18:31:40Z)
• Point-Level Temporal Action Localization: Bridging Fully-supervised Proposals to Weakly-supervised Losses [84.2964408497058]
  Point-level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse single-frame labels. This paper attempts to explore the proposal-based prediction paradigm for point-level annotations.
  arXiv  Detail & Related papers  (2020-12-15T12:11:48Z)

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.