arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.16319cs.CV
收藏

CutS3D:在3D中切割语义以实现2D无监督实例分割

CutS3D: Cutting Semantics in 3D for 2D Unsupervised Instance Segmentation

Ulm University(乌尔姆大学);KAUST(科罗Swiss阿尔特姆大学);TU Vienna(维也纳技术大学)

Leon Sick, Dominik Engel, Sebastian Hartwig, Pedro Hermosilla, Timo Ropinski

AI总结:

针对无监督2D实例分割中重叠实例难分离及伪掩码歧义问题,本文提出CutS3D,借助点云在3D中切割语义并引入空间重要性与三类空间置信度分量,在多个基准上取得领先性能。

摘要:

传统上,学习在2D图像中分割对象实例的算法严重依赖大量人工标注数据。直到最近,才出现了以无监督方式解决该问题的新方法。通常,这些方法首先生成伪掩码,然后训练一个类别无关的检测器。尽管此类方法代表了当前最先进水平,但由于只考虑语义,它们往往无法正确分离在2D图像空间中重叠的实例。为解决这一问题,我们转而提出利用场景的点云表示,在3D中切割语义掩码以获得最终的2D实例。此外,我们推导了一个空间重要性函数,用其沿实例的3D边界重新锐化语义。尽管如此,这些伪掩码仍存在掩码歧义。为解决该问题,我们进一步提出用三个空间置信度分量增强类别无关检测器的训练,旨在分离出干净的学习信号。凭借这些贡献,我们的方法在多个无监督实例分割和目标检测标准基准上优于竞争方法。

英文摘要:

Traditionally, algorithms that learn to segment object instances in 2D images have heavily relied on large amounts of human-annotated data. Only recently, novel approaches have emerged tackling this problem in an unsupervised fashion. Generally, these approaches first generate pseudo-masks and then train a class-agnostic detector. While such methods deliver the current state of the art, they often fail to correctly separate instances overlapping in 2D image space since only semantics are considered. To tackle this issue, we instead propose to cut the semantic masks in 3D to obtain the final 2D instances by utilizing a point cloud representation of the scene. Furthermore, we derive a Spatial Importance function, which we use to resharpen the semantics along the 3D borders of instances. Nevertheless, these pseudo-masks are still subject to mask ambiguity. To address this issue, we further propose to augment the training of a class-agnostic detector with three Spatial Confidence components aiming to isolate a clean learning signal. With these contributions, our approach outperforms competing methods across multiple standard benchmarks for unsupervised instance segmentation and object detection.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑