---
res:
  bibo_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.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Pramod
      foaf_name: Rao, Pramod
      foaf_surname: Rao
  - foaf_Person:
      foaf_givenName: Gereon
      foaf_name: Fox, Gereon
      foaf_surname: Fox
  - foaf_Person:
      foaf_givenName: Abhimitra
      foaf_name: Meka, Abhimitra
      foaf_surname: Meka
  - foaf_Person:
      foaf_givenName: B. R.
      foaf_name: Mallikarjun, B. R.
      foaf_surname: Mallikarjun
  - foaf_Person:
      foaf_givenName: Fangneng
      foaf_name: Zhan, Fangneng
      foaf_surname: Zhan
  - foaf_Person:
      foaf_givenName: Tim
      foaf_name: Weyrich, Tim
      foaf_surname: Weyrich
  - foaf_Person:
      foaf_givenName: Bernd
      foaf_name: Bickel, Bernd
      foaf_surname: Bickel
      foaf_workInfoHomepage: http://www.librecat.org/personId=49876194-F248-11E8-B48F-1D18A9856A87
    orcid: 0000-0001-6511-9385
  - foaf_Person:
      foaf_givenName: Hanspeter
      foaf_name: Pfister, Hanspeter
      foaf_surname: Pfister
  - foaf_Person:
      foaf_givenName: Wojciech
      foaf_name: Matusik, Wojciech
      foaf_surname: Matusik
  - foaf_Person:
      foaf_givenName: Mohamed
      foaf_name: Elgharib, Mohamed
      foaf_surname: Elgharib
  - foaf_Person:
      foaf_givenName: Christian
      foaf_name: Theobalt, Christian
      foaf_surname: Theobalt
  bibo_doi: 10.1145/3641519.3657470
  dct_date: 2024^xs_gYear
  dct_identifier:
  - UT:001282218200076
  dct_isPartOf:
  - http://id.crossref.org/issn/9798400705250
  dct_language: eng
  dct_publisher: Association for Computing Machinery@
  dct_title: 'Lite2Relight: 3D-aware single image portrait relighting@'
...