Boundary Cues for 3D Object Shape Recovery

TL;DR

This paper revisits boundary cues like self occlusions and folds for 3D shape reconstruction, showing their importance alongside shading cues and suggesting new research directions.

Contribution

It highlights the significance of boundary cues in shape recovery, providing empirical evaluation and proposing future research avenues in automatic detection and relaxed assumptions.

Findings

Boundary cues significantly improve shape reconstruction quality.

Boundary cues enhance shape recognition accuracy.

Future work should focus on automatic boundary detection.

Abstract

Early work in computer vision considered a host of geometric cues for both shape reconstruction and recognition. However, since then, the vision community has focused heavily on shading cues for reconstruction, and moved towards data-driven approaches for recognition. In this paper, we reconsider these perhaps overlooked "boundary" cues (such as self occlusions and folds in a surface), as well as many other established constraints for shape reconstruction. In a variety of user studies and quantitative tasks, we evaluate how well these cues inform shape reconstruction (relative to each other) in terms of both shape quality and shape recognition. Our findings suggest many new directions for future research in shape reconstruction, such as automatic boundary cue detection and relaxing assumptions in shape from shading (e.g. orthographic projection, Lambertian surfaces).