CVApr 17, 2018

Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction

arXiv:1804.06032v2126 citations
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of selecting optimal shape representations for 3D object prediction, which is incremental as it compares existing paradigms rather than introducing a new one.

This paper compared surface-based and volumetric 3D shape representations, as well as viewer-centered and object-centered reference frames, for single-view 3D object shape prediction, finding that surface-based methods outperform voxels for novel classes and produce higher resolution outputs.

The goal of this paper is to compare surface-based and volumetric 3D object shape representations, as well as viewer-centered and object-centered reference frames for single-view 3D shape prediction. We propose a new algorithm for predicting depth maps from multiple viewpoints, with a single depth or RGB image as input. By modifying the network and the way models are evaluated, we can directly compare the merits of voxels vs. surfaces and viewer-centered vs. object-centered for familiar vs. unfamiliar objects, as predicted from RGB or depth images. Among our findings, we show that surface-based methods outperform voxel representations for objects from novel classes and produce higher resolution outputs. We also find that using viewer-centered coordinates is advantageous for novel objects, while object-centered representations are better for more familiar objects. Interestingly, the coordinate frame significantly affects the shape representation learned, with object-centered placing more importance on implicitly recognizing the object category and viewer-centered producing shape representations with less dependence on category recognition.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes