<?xml version="1.0" encoding="utf-8"?>
<!-- generator="FeedCreator 1.8" -->
<?xml-stylesheet href="https://cvg.cit.tum.de/lib/exe/css.php?s=feed" type="text/css"?>
<feed xmlns="http://www.w3.org/2005/Atom">
    <title>Computer Vision Group research:geometry</title>
    <subtitle></subtitle>
    <link rel="alternate" type="text/html" href="https://cvg.cit.tum.de/"/>
    <id>https://cvg.cit.tum.de/</id>
    <updated>2026-04-21T17:08:39+00:00</updated>
    <generator>FeedCreator 1.8 (info@mypapit.net)</generator>
    <link rel="self" type="application/atom+xml" href="https://cvg.cit.tum.de/feed.php" />
    <entry>
        <title>FIRe🔥: Fast Inverse Rendering using Directional and Signed Distance Functions</title>
        <link rel="alternate" type="text/html" href="https://cvg.cit.tum.de/research/geometry/fire?rev=1713432401&amp;do=diff"/>
        <published>2024-04-18T09:26:41+00:00</published>
        <updated>2024-04-18T09:26:41+00:00</updated>
        <id>https://cvg.cit.tum.de/research/geometry/fire?rev=1713432401&amp;do=diff</id>
        <author>
            <name>Anonymous</name>
            <email>anonymous@undisclosed.example.com</email>
        </author>
        <category  term="research:geometry" />
        <content>FIRe🔥: Fast Inverse Rendering using Directional and Signed Distance Functions

Tarun Yenamandra  Ayush Tewari  Nan Yang  Florian Bernard  Christian Theobalt  Daniel Cremers

Abstract

Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating the network multiple times per camera ray so that the high computational time…</content>
        <summary>FIRe🔥: Fast Inverse Rendering using Directional and Signed Distance Functions

Tarun Yenamandra  Ayush Tewari  Nan Yang  Florian Bernard  Christian Theobalt  Daniel Cremers

Abstract

Neural 3D implicit representations learn priors that are useful for diverse applications, such as single- or multiple-view 3D reconstruction. A major downside of existing approaches while rendering an image is that they require evaluating the network multiple times per camera ray so that the high computational time…</summary>
    </entry>
    <entry>
        <title>research:geometry:intrinsic-neural-fields</title>
        <link rel="alternate" type="text/html" href="https://cvg.cit.tum.de/research/geometry/intrinsic-neural-fields?rev=1657618345&amp;do=diff"/>
        <published>2022-07-12T09:32:25+00:00</published>
        <updated>2022-07-12T09:32:25+00:00</updated>
        <id>https://cvg.cit.tum.de/research/geometry/intrinsic-neural-fields?rev=1657618345&amp;do=diff</id>
        <author>
            <name>Anonymous</name>
            <email>anonymous@undisclosed.example.com</email>
        </author>
        <category  term="research:geometry" />
        <content>intrinsic-neural-fields</content>
        <summary>intrinsic-neural-fields</summary>
    </entry>
</feed>
