Lite2Relight: 3D-aware Single Image Portrait Relighting
Name
3641519.3657470.pdf
Size
56.88 MB
Format
Adobe PDF
Checksum (MD5)
797ef1d0c215142b461ae7a634a87ca2
Author(s)
Rao, Pramod
Fox, Gereon
Meka, Abhimitra
B R, Mallikarjun
Zhan, Fangneng
Weyrich, Tim
Bickel, Bernd
Pfister, Hanspeter
Matusik, Wojciech
Elgharib, Mohamed
Date Issued
July 13, 2024
Publisher
ACM|Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers '24
Citation
Rao, Pramod, Fox, Gereon, Meka, Abhimitra, B R, Mallikarjun, Zhan, Fangneng et al. 2024. "Lite2Relight: 3D-aware Single Image Portrait Relighting."
Version
Final published version
Abstract
Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency, coupled with inaccuracies in physically realistic lighting and identity preservation. Furthermore, personalization from a single view is difficult to achieve and often requires multiview images during the testing phase or involves slow optimization processes. This paper introduces Lite2Relight , a novel technique that can predict 3D consistent head poses of portraits while performing physically plausible light editing at interactive speed. Our method uniquely extends the generative capabilities and efficient volumetric representation of EG3D, leveraging a lightstage dataset to implicitly disentangle face reflectance and perform relighting under target HDRI environment maps. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space, enhancing them with a strong face geometry and reflectance prior. Through extensive quantitative and qualitative evaluations, we show that our method outperforms the state-of-the-art methods in terms of efficacy, photorealism, and practical application. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions. Lite2Relight paves the way for large-scale adoption of photorealistic portrait editing in various domains, offering a robust, interactive solution to a previously constrained problem.
Description
SIGGRAPH Conference Papers ’24, July 27–August 01, 2024, Denver, CO, USA
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3641519.3657470
