@inproceedings{48a9c9f97cfa4882817aa79a9e7f6ec1,
title = "Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild",
abstract = "We present a novel 3D pose refinement approach based ondifferentiable rendering for objects of arbitrary categories in the wild. Incontrast to previous methods, we make two main contributions: First,instead of comparing real-world images and synthetic renderings in theRGB or mask space, we compare them in a feature space optimized for3D pose refinement. Second, we introduce a novel differentiable rendererthat learns to approximate the rasterization backward pass from data in-stead of relying on a hand-crafted algorithm. For this purpose, we predictdeep cross-domain correspondences between RGB images and 3D modelrenderings in the form of what we call geometric correspondence fields.These correspondence fields serve as pixel-level gradients which are ana-lytically propagated backward through the rendering pipeline to performa gradient-based optimization directly on the 3D pose. In this way, weprecisely align 3D models to objects in RGB images which results in sig-nificantly improved 3D pose estimates. We evaluate our approach on thechallenging Pix3D dataset and achieve up to 55% relative improvementcompared to state-of-the-art refinement methods in multiple metrics.",
author = "Alexander Grabner and Yaming Wang and Peizhao Zhang and Peihong Guo and Tong Xiao and Peter Vajda and Roth, {Peter M.} and Vincent Lepetit",
year = "2020",
doi = "10.1007/978-3-030-58517-4_7",
language = "English",
isbn = "978-3-030-58516-7",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "102--119",
booktitle = "Computer Vision – ECCV 2020",
note = "16th European Conference on Computer Vision : ECCV 2020, ECCV 2020 ; Conference date: 23-08-2020 Through 28-08-2020",
}