PREMA: Part-based REcurrent Multi-view Aggregation Network for 3D Shape Retrieval
This work improves 3D shape retrieval for computer vision applications, but it is incremental as it builds on existing part-based and multi-view aggregation approaches.
The authors tackled the problem of 3D shape retrieval by addressing practical view defects like insufficient views, occlusions, and background clutter, resulting in a method that reliably locates and utilizes multi-view coherent parts to build robust shape representations.
We propose the Part-based Recurrent Multi-view Aggregation network(PREMA) to eliminate the detrimental effects of the practical view defects, such as insufficient view numbers, occlusions or background clutters, and also enhance the discriminative ability of shape representations. Inspired by the fact that human recognize an object mainly by its discriminant parts, we define the multi-view coherent part(MCP), a discriminant part reoccurring in different views. Our PREMA can reliably locate and effectively utilize MCPs to build robust shape representations. Comprehensively, we design a novel Regional Attention Unit(RAU) in PREMA to compute the confidence map for each view, and extract MCPs by applying those maps to view features. PREMA accentuates MCPs via correlating features of different views, and aggregates the part-aware features for shape representation.