State-of-the-art lidar panoptic segmentation (LPS) methods follow bottom-up
segmentation-centric fashion wherein they build upon semantic segmentation
networks by utilizing clustering to obtain object instances. In this paper, we
re-think this approach and propose a surprisingly simple yet effective
detection-centric network for both LPS and tracking. Our network is modular by
design and optimized for all aspects of both the panoptic segmentation and
tracking task. One of the core components of our network is the object instance
detection branch, which we train using point-level (modal) annotations, as
available in segmentation-centric datasets. In the absence of amodal (cuboid)
annotations, we regress modal centroids and object extent using
trajectory-level supervision that provides information about object size, which
cannot be inferred from single scans due to occlusions and the sparse nature of
the lidar data. We obtain fine-grained instance segments by learning to
associate lidar points with detected centroids. We evaluate our method on
several 3D/4D LPS benchmarks and observe that our model establishes a new
state-of-the-art among open-sourced models, outperforming recent query-based
models.

本文提出了一个简单而有效的基于检测的网络，用于激光雷达全景分割和追踪任务，通过使用点级别注释训练目标实例检测分支，以及使用轨迹级别监督回归模态中心和物体范围来获取细粒度实例段，该方法在多个 3D/4D LPS 基准测试中表现出色，超过最新的基于查询的模型，建立了新的开源模型的最新技术水平。

基于激光雷达的全景分割与追踪

Lidar Panoptic Segmentation and Tracking without Bells and Whistles

Instance segmentation methods often require costly per-pixel labels. We
propose a method that only requires point-level annotations. During training,
the model only has access to a single pixel label per object, yet the task is
to output full segmentation masks. To address this challenge, we construct a
network with two branches: (1) a localization network (L-Net) that predicts the
location of each object; and (2) an embedding network (E-Net) that learns an
embedding space where pixels of the same object are close. The segmentation
masks for the located objects are obtained by grouping pixels with similar
embeddings. At training time, while L-Net only requires point-level
annotations, E-Net uses pseudo-labels generated by a class-agnostic object
proposal method. We evaluate our approach on PASCAL VOC, COCO, KITTI and
CityScapes datasets. The experiments show that our method (1) obtains
competitive results compared to fully-supervised methods in certain scenarios;
(2) outperforms fully- and weakly- supervised methods with a fixed annotation
budget; and (3) is a first strong baseline for instance segmentation with
point-level supervision.

该研究提出了一种只需要点级别注释来训练模型实现物体实例分割的方法，其通过建立一个具有两个分支（定位网络和嵌入网络）的网络，使用伪标签和相似嵌入方法来提高分割效果，在特定情况下，可以获得有竞争力的结果，并且是一种实例分割点级别监督的强基准线。