TY - GEN
T1 - Focal Length and Object Pose Estimation via Render and Compare
AU - Ponimatkin, Georgy
AU - Labbe, Yann
AU - Russell, Bryan
AU - Aubry, Mathieu
AU - Sivic, Josef
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/1/1
Y1 - 2022/1/1
N2 - 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.
AB - 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.
KW - 3D from single images
KW - Robot vision
UR - https://www.scopus.com/pages/publications/85141777383
U2 - 10.1109/CVPR52688.2022.00380
DO - 10.1109/CVPR52688.2022.00380
M3 - Conference contribution
AN - SCOPUS:85141777383
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 3815
EP - 3824
BT - Proceedings - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
PB - IEEE Computer Society
T2 - 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022
Y2 - 19 June 2022 through 24 June 2022
ER -