Globally Optimal Pose from Orthographic Silhouettes

TL;DR

This paper presents a novel method for globally optimal pose estimation of known 3D shapes from silhouettes using silhouette-signatures and shape signatures, achieving high accuracy without correspondence guidance.

Contribution

It introduces the first efficient approach to estimate globally optimal pose from silhouettes for any shape, leveraging silhouette-area continuity and auxiliary shape signatures.

Findings

Achieves significantly improved accuracy over comparable methods.

Validates the approach on synthetic and real data.

Provides code and data at the specified URL.

Abstract

We solve the problem of determining the pose of known shapes in $\mathbb{R}^3$ from their unoccluded silhouettes. The pose is determined up to global optimality using a simple yet under-explored property of the area-of-silhouette: its continuity w.r.t trajectories in the rotation space. The proposed method utilises pre-computed silhouette-signatures, modelled as a response surface of the area-of-silhouettes. Querying this silhouette-signature response surface for pose estimation leads to a strong branching of the rotation search space, making resolution-guided candidate search feasible. Additionally, we utilise the aspect ratio of 2D ellipses fitted to projected silhouettes as an auxiliary global shape signature to accelerate the pose search. This combined strategy forms the first method to efficiently estimate globally optimal pose from just the silhouettes, without being guided by correspondences, for any shape, irrespective of its convexity and genus. We validate our method on synthetic and real examples, demonstrating significantly improved accuracy against comparable approaches. Code, data, and supplementary in: https://agnivsen.github.io/pose-from-silhouette/