Globally Optimal Pose from Orthographic Silhouettes
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present a method to find the exact position and orientation (pose) of 3D shapes by looking only at their clear, unblocked outlines (silhouettes) from images. They use a mathematical property showing how the silhouette's area changes smoothly as the shape rotates. By pre-calculating how silhouette areas vary with rotation, they quickly narrow down possible poses without needing point matches. They also speed up the search using the shape of the silhouette's ellipse outline. Their method works for any shape and achieves better accuracy than similar existing techniques.
Pose estimationSilhouetteRotation spaceResponse surfaceGlobal optimization2D ellipse fittingShape signaturesConvexityGenusCandidate search
Authors
Agniva Sengupta, Dilara Kuş, Jianning Li, Stefan Zachow
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/