Focal Length and Object Pose Estimation via Render and Compare - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Focal Length and Object Pose Estimation via Render and Compare

Résumé

We introduce FocalPose, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are twofold. First, we derive a focal length update rule that extends an existing state-of-the-art render-and-compare 6D pose estimator to address the joint estimation task. Second, we investigate several different loss functions for jointly estimating the object pose and focal length. We find that a combination of direct focal length regression with a reprojection loss disentangling the contribution of translation, rotation, and focal length leads to improved results. We show results on three challenging benchmark datasets that depict known 3D models in uncontrolled settings. We demonstrate that our focal length and 6D pose estimates have lower error than the existing state-of-the-art methods.

Dates et versions

hal-03847201 , version 1 (10-11-2022)

Identifiants

Citer

Georgy Ponimatkin, Yann Labbé, Bryan Russell, Mathieu Aubry, Josef Sivic. Focal Length and Object Pose Estimation via Render and Compare. CVPR 2022 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2022, New Orleans, United States. ⟨hal-03847201⟩
45 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More