Urs Waldmann<p>Our latest work "Neural Texture Puppeteer" is published at <a href="https://openaccess.thecvf.com/content/WACV2024W/CV4Smalls/html/Waldmann_Neural_Texture_Puppeteer_A_Framework_for_Neural_Geometry_and_Texture_WACVW_2024_paper.html" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">openaccess.thecvf.com/content/</span><span class="invisible">WACV2024W/CV4Smalls/html/Waldmann_Neural_Texture_Puppeteer_A_Framework_for_Neural_Geometry_and_Texture_WACVW_2024_paper.html</span></a></p><p>As a base we make use of "Neural Puppeteer", an efficient and flexible neural rendering pipeline <a href="https://openaccess.thecvf.com/content/ACCV2022/html/Giebenhain_Neural_Puppeteer_Keypoint-Based_Neural_Rendering_of_Dynamic_Shapes_ACCV_2022_paper.html" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">openaccess.thecvf.com/content/</span><span class="invisible">ACCV2022/html/Giebenhain_Neural_Puppeteer_Keypoint-Based_Neural_Rendering_of_Dynamic_Shapes_ACCV_2022_paper.html</span></a></p><p>Our key idea is to disentangle texture and geometry. </p><p>We show with twelve distinct synthetic cow textures that the new pipeline can be used in a downstream task to identify individuals.</p><p><a href="https://sigmoid.social/tags/NeTePu" class="mention hashtag" rel="tag">#<span>NeTePu</span></a> <a href="https://sigmoid.social/tags/NePu" class="mention hashtag" rel="tag">#<span>NePu</span></a> <a href="https://sigmoid.social/tags/WACV" class="mention hashtag" rel="tag">#<span>WACV</span></a> <a href="https://sigmoid.social/tags/WACV24" class="mention hashtag" rel="tag">#<span>WACV24</span></a> <a href="https://sigmoid.social/tags/computervision" class="mention hashtag" rel="tag">#<span>computervision</span></a> <span class="h-card" translate="no"><a href="https://xn--baw-joa.social/@unikonstanz" class="u-url mention">@<span>unikonstanz</span></a></span> <a href="https://sigmoid.social/tags/CBehav" class="mention hashtag" rel="tag">#<span>CBehav</span></a> <a href="https://sigmoid.social/tags/NeuralRendering" class="mention hashtag" rel="tag">#<span>NeuralRendering</span></a> <a href="https://sigmoid.social/tags/ReIdentification" class="mention hashtag" rel="tag">#<span>ReIdentification</span></a></p>
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!
Administered by:
Server stats:
586active users
sigmoid.social: About · Profiles directory · Privacy policy
Mastodon: About · Get the app · Keyboard shortcuts · View source code · v4.4.3
#NePu
0 posts · 0 participants · 0 posts today
Urs Waldmann<p>Our paper "Neural Texture Puppeteer" was accepted for oral presentation <a href="https://cv4smalls.sites.northeastern.edu/schedule-deadlines/" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">cv4smalls.sites.northeastern.e</span><span class="invisible">du/schedule-deadlines/</span></a> at the <a href="https://sigmoid.social/tags/WACV2024" class="mention hashtag" rel="tag">#<span>WACV2024</span></a> workshop "CV4Smalls" <a href="https://cv4smalls.sites.northeastern.edu/" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">cv4smalls.sites.northeastern.e</span><span class="invisible">du/</span></a></p><p>Stay tuned for more infos.</p><p><a href="https://sigmoid.social/tags/NeTePu" class="mention hashtag" rel="tag">#<span>NeTePu</span></a> <a href="https://sigmoid.social/tags/NePu" class="mention hashtag" rel="tag">#<span>NePu</span></a> <a href="https://sigmoid.social/tags/WACV" class="mention hashtag" rel="tag">#<span>WACV</span></a> <a href="https://sigmoid.social/tags/WACV24" class="mention hashtag" rel="tag">#<span>WACV24</span></a> <a href="https://sigmoid.social/tags/computervision" class="mention hashtag" rel="tag">#<span>computervision</span></a> <span class="h-card" translate="no"><a href="https://xn--baw-joa.social/@unikonstanz" class="u-url mention">@<span>unikonstanz</span></a></span> <a href="https://sigmoid.social/tags/CBehav" class="mention hashtag" rel="tag">#<span>CBehav</span></a> <a href="https://sigmoid.social/tags/NeuralRendering" class="mention hashtag" rel="tag">#<span>NeuralRendering</span></a> <a href="https://sigmoid.social/tags/ReIdentification" class="mention hashtag" rel="tag">#<span>ReIdentification</span></a></p>
Urs Waldmann<p>Our paper Neural Puppeteer <a href="https://urs-waldmann.github.io/NePu/" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="">urs-waldmann.github.io/NePu/</span><span class="invisible"></span></a> was accepted in the Nactar Track at <a href="https://sigmoid.social/tags/GCPR23" class="mention hashtag" rel="tag">#<span>GCPR23</span></a> <a href="https://www.dagm-gcpr.de/year/2023" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://www.</span><span class="">dagm-gcpr.de/year/2023</span><span class="invisible"></span></a>.</p><p>See you all in <a href="https://sigmoid.social/tags/Heidelberg" class="mention hashtag" rel="tag">#<span>Heidelberg</span></a>.</p><p><a href="https://sigmoid.social/tags/NePu" class="mention hashtag" rel="tag">#<span>NePu</span></a> <a href="https://sigmoid.social/tags/GCPR" class="mention hashtag" rel="tag">#<span>GCPR</span></a> <a href="https://sigmoid.social/tags/GCPR2023" class="mention hashtag" rel="tag">#<span>GCPR2023</span></a> <a href="https://sigmoid.social/tags/computervision" class="mention hashtag" rel="tag">#<span>computervision</span></a> <a href="https://sigmoid.social/tags/UniKonstanz" class="mention hashtag" rel="tag">#<span>UniKonstanz</span></a> <a href="https://sigmoid.social/tags/CBehav" class="mention hashtag" rel="tag">#<span>CBehav</span></a> <a href="https://sigmoid.social/tags/NeuralRendering" class="mention hashtag" rel="tag">#<span>NeuralRendering</span></a> <a href="https://sigmoid.social/tags/PoseEstimation" class="mention hashtag" rel="tag">#<span>PoseEstimation</span></a> <a href="https://sigmoid.social/tags/3dpose" class="mention hashtag" rel="tag">#<span>3dpose</span></a></p>
Urs Waldmann<p>Our latest work "Neural Puppeteer" is published at <a href="https://link.springer.com/chapter/10.1007/978-3-031-26316-3_15" target="_blank" rel="nofollow noopener" translate="no"><span class="invisible">https://</span><span class="ellipsis">link.springer.com/chapter/10.1</span><span class="invisible">007/978-3-031-26316-3_15</span></a>.</p><p>We estimate 3D keypoints from multi-view silhouettes only, using our inverse neural rendering pipeline. In this way our 3D keypoint estimation is robust against transformations that leave silhouettes unchanged like texture and lighting.</p><p><a href="https://sigmoid.social/tags/NePu" class="mention hashtag" rel="tag">#<span>NePu</span></a> <a href="https://sigmoid.social/tags/NeuralRendering" class="mention hashtag" rel="tag">#<span>NeuralRendering</span></a> <a href="https://sigmoid.social/tags/PoseEstimation" class="mention hashtag" rel="tag">#<span>PoseEstimation</span></a> <a href="https://sigmoid.social/tags/3dpose" class="mention hashtag" rel="tag">#<span>3dpose</span></a> <a href="https://sigmoid.social/tags/computervision" class="mention hashtag" rel="tag">#<span>computervision</span></a> <a href="https://sigmoid.social/tags/CBehav" class="mention hashtag" rel="tag">#<span>CBehav</span></a> <a href="https://sigmoid.social/tags/UniKonstanz" class="mention hashtag" rel="tag">#<span>UniKonstanz</span></a></p>
TrendingLive feeds
Mastodon is the best way to keep up with what's happening.
Follow anyone across the fediverse and see it all in chronological order. No algorithms, ads, or clickbait in sight.
Create accountLoginDrag & drop to upload