3D-QueryIS: A Query-based Framework for 3D Instance Segmentation
This work addresses robustness and generalization issues in 3D instance segmentation for computer vision applications, representing an incremental improvement over existing methods.
The paper tackles the problem of 3D instance segmentation by proposing 3D-QueryIS, a query-based method that eliminates inter-task dependencies to improve robustness and generalization, achieving competitive results on multiple benchmark datasets.
Previous top-performing methods for 3D instance segmentation often maintain inter-task dependencies and the tendency towards a lack of robustness. Besides, inevitable variations of different datasets make these methods become particularly sensitive to hyper-parameter values and manifest poor generalization capability. In this paper, we address the aforementioned challenges by proposing a novel query-based method, termed as 3D-QueryIS, which is detector-free, semantic segmentation-free, and cluster-free. Specifically, we propose to generate representative points in an implicit manner, and use them together with the initial queries to generate the informative instance queries. Then, the class and binary instance mask predictions can be produced by simply applying MLP layers on top of the instance queries and the extracted point cloud embeddings. Thus, our 3D-QueryIS is free from the accumulated errors caused by the inter-task dependencies. Extensive experiments on multiple benchmark datasets demonstrate the effectiveness and efficiency of our proposed 3D-QueryIS method.