Semi-Supervised Co-Analysis of 3D Shape Styles from Projected Lines

TL;DR

This paper introduces a semi-supervised method for analyzing and localizing style patches on 3D shapes using projected feature lines, combining multi-view feature fusion and style clustering with weak supervision.

Contribution

It proposes a novel semi-supervised co-analysis framework that effectively localizes style patches on 3D shapes from projected lines with minimal supervision.

Findings

Achieves accurate style patch localization on 3D shapes.

Outperforms state-of-the-art methods in style analysis.

Supports both unsupervised and semi-supervised learning modes.

Abstract

We present a semi-supervised co-analysis method for learning 3D shape styles from projected feature lines, achieving style patch localization with only weak supervision. Given a collection of 3D shapes spanning multiple object categories and styles, we perform style co-analysis over projected feature lines of each 3D shape and then backproject the learned style features onto the 3D shapes. Our core analysis pipeline starts with mid-level patch sampling and pre-selection of candidate style patches. Projective features are then encoded via patch convolution. Multi-view feature integration and style clustering are carried out under the framework of partially shared latent factor (PSLF) learning, a multi-view feature learning scheme. PSLF achieves effective multi-view feature fusion by distilling and exploiting consistent and complementary feature information from multiple views, while also selecting style patches from the candidates. Our style analysis approach supports both unsupervised and semi-supervised analysis. For the latter, our method accepts both user-specified shape labels and style-ranked triplets as clustering constraints.We demonstrate results from 3D shape style analysis and patch localization as well as improvements over state-of-the-art methods. We also present several applications enabled by our style analysis.