Deep Kinematic Pose Regression [article]

Xingyi Zhou, Xiao Sun, Wei Zhang, Shuang Liang, Yichen Wei
<span title="2016-09-17">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints and does not guarantee the geometric validity of their pose estimation, therefore requiring a post-processing to recover the correct geometry if desired, which is cumbersome and sub-optimal. In this work, we propose to directly embed a kinematic object model into the deep neutral network learning for general
more &raquo; ... d object pose estimation. The kinematic function is defined on the appropriately parameterized object motion variables. It is differentiable and can be used in the gradient descent based optimization in network training. The prior knowledge on the object geometric model is fully exploited and the structure is guaranteed to be valid. We show convincing experiment results on a toy example and the 3D human pose estimation problem. For the latter we achieve state-of-the-art result on Human3.6M dataset.
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.05317v1">arXiv:1609.05317v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h2s6f2afsfa6lagtpcfmjn3svy">fatcat:h2s6f2afsfa6lagtpcfmjn3svy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191024064215/https://arxiv.org/pdf/1609.05317v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ad/1f/ad1f223e83338b0b08779b3736d5a3b7ccfec592.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.05317v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>