Source‐enhanced prototypical alignment for single image 3D model retrieval. (15th June 2022)

• Record Type: Journal Article
• Authors: Song, Dan; Wang, Teng; Zhang, Chumeng; Li, Xuanya; Tong, Ruofeng
• Is Part Of: Computer animation and virtual worlds. Volume 33:Number 3/4(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-06-15
• Subjects: 3D model retrieval -- domain adaptation -- transfer learning; Computer animation -- Periodicals; Visualization -- Periodicals; 006.6
• DOI: 10.1002/cav.2065
• Languages: English
• ISSNs: 1546-4261

Abstract

Abstract: Single image 3D model retrieval has attracted a lot of attentions with the convenience of organizing large‐scale unlabeled 3D models. Existing methods transfer the knowledge from well‐annotated 2D images (i.e., source domain) to unlabeled 3D models (i.e., target domain) to improve the discriminability of 3D models and align the feature distributions of 2D images and 3D models. However, during the alignment, the feature learning target of improving the discriminability of 3D models sometimes confuses the boundaries between 2D image categories, where prior methods ignore keeping the discriminability of 2D images. Motivated by this observation, we propose a source‐enhanced prototypical alignment framework to first remain the discriminability of 2D images and then guide the category‐level cross‐domain alignment with better image representations. Specifically, a novel separation and compactness loss is proposed for images to separate the samples from different categories and compact the samples within the same category. Then we perform prototypical alignment to make 2D image features assist in the discriminative feature learning for 3D models. We evaluate the proposed method on the commonly used cross‐domain 3D model retrieval benchmarks, namely MI3DOR and MI3DOR‐2, and the results demonstrate the effectiveness of the proposed method. Abstract : In this article, we propose a source‐enhanced prototypical alignment framework to firstly remain the discriminability of 2D images and then guide the category‐level cross‐domain alignment with better image representations. Specifically, a novel separation and compactness loss is proposed for images to separate the samples from different categories and compact the samples within the same category. Then we perform prototypical alignment to make 2D image features assist in the discriminative feature learning for 3D models.