BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
X-LIC-LOCATION:Asia/Tokyo
BEGIN:STANDARD
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
DTSTART:18871231T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260817T171541Z
LOCATION:Hall B5 (2)\, B Block\, Level 5
DTSTART;TZID=Asia/Tokyo:20241203T144500
DTEND;TZID=Asia/Tokyo:20241203T155500
UID:siggraphasia_SIGGRAPH Asia 2024_sess107@linklings.com
SUMMARY:Neural Relighting and Reflection
DESCRIPTION:Each Paper gives a 10 minute presentation.\n\nDifFRelight: Dif
 fusion-Based Facial Performance Relighting\n\nWe present a novel framework
  for free-viewpoint facial performance relighting using diffusion-based im
 age-to-image translation. Leveraging a subject-specific dataset containing
  diverse facial expressions captured under various lighting conditions, in
 cluding flat-lit and one-light-at-a-time (OLAT) sc...\n\n\nMingming He (Ne
 tflix Eyeline Studios); Pascal Clausen (Netflix Eyeline Studios, Osylum); 
 and Ahmet Levent Taşel, Li Ma, Oliver Pilarski, Wenqi Xian, Laszlo Rikker,
  Xueming Yu, Ryan Burgert, Ning Yu, and Paul Debevec (Netflix Eyeline Stud
 ios)\n---------------------\nGS^3: Efficient Relighting with Triple Gaussi
 an Splatting\n\nWe present a spatial and angular Gaussian based representa
 tion and a triple splatting process, for real-time, high-quality novel lig
 hting-and-view synthesis from multi-view point-lit input images. To descri
 be complex appearance, we employ a Lambertian plus a mixture of angular Ga
 ussians as an effect...\n\n\nZoubin Bi, Yixin Zeng, Chong Zeng, Fan Pei, X
 iang Feng, Kun Zhou, and Hongzhi Wu (State Key Laboratory of CAD&CG, Zheji
 ang University)\n---------------------\nOLAT Gaussians for Generic Relight
 able Appearance Acquisition\n\nOne-light-at-a-time (OLAT) images sample a 
 broader range of object appearance changes than images captured under cons
 tant lighting and are superior as input to object relighting. Although exi
 sting methods have produced reasonable relighting quality using OLAT image
 s, they utilize surface-like repres...\n\n\nZhiyi Kuang (State Key Laborat
 ory of CAD&CG, Zhejiang University); Yanchao Yang and Siyan Dong (Universi
 ty of Hong Kong); Jiayue Ma (State Key Laboratory of CAD&CG, Zhejiang Univ
 ersity); Hongbo Fu (Hong Kong University of Science and Technology); and Y
 ouyi Zheng (State Key Laboratory of CAD&CG, Zhejiang University)\n--------
 -------------\nReflection-Aware Neural Radiance Fields\n\nNeural Radiance 
 Fields (NeRF) have demonstrated exceptional capabilities in reconstructing
  complex scenes with high fidelity. However, NeRF's view dependency can on
 ly handle low-frequency reflections. It falls short when handling complex 
 planar reflections, often interpreting them as erroneous scene...\n\n\nChe
 n Gao, Yipeng Wang, and Changil Kim (Meta); Jia-Bin Huang (University of M
 aryland, College Park); and Johannes Kopf (Meta)\n---------------------\nN
 eRF-Casting: Improved View-Dependent Appearance with Consistent Reflection
 s\n\nNeural Radiance Fields (NeRFs) typically struggle to reconstruct and 
 render highly specular objects, whose appearance varies quickly with chang
 es in viewpoint. Recent works have improved NeRF's ability to render detai
 led specular appearance of distant environment illumination, but are unabl
 e to synt...\n\n\nDor Verbin, Pratul P. Srinivasan, Peter Hedman, and Ben 
 Mildenhall (Google Research); Benjamin Attal (Carnegie Mellon University);
  and Richard Szeliski and Jonathan T. Barron (Google Research)\n----------
 -----------\nLocal Gaussian Density Mixtures for Unstructured Lumigraph Re
 ndering\n\nTo improve novel-view synthesis of curved surface reflections a
 nd refractions, we revisit local geometry-guided ray interpolation techniq
 ues with modern differentiable rendering and optimization.\nIn contrast to
  depth or mesh geometries, our approach uses a local or per-view density r
 epresented as Ga...\n\n\nXiuchao Wu (State Key Laboratory of CAD&CG, Zheji
 ang University); Jiamin Xu (Hangzhou Dianzi Univeristy); Chi Wang (State K
 ey Laboratory of CAD&CG, Zhejiang University); Yifan Peng (University of H
 ong Kong); Qixing Huang (University of Texas at Austin); James Tompkin (Br
 own University); and Weiwei Xu (State Key Laboratory of CAD&CG, Zhejiang U
 niversity)\n\nRegistration Category: Full Access, Full Access Supporter\n\
 nLanguage Format: English Language\n\nSession Chair: Hongzhi Wu (Zhejiang 
 University; State Key Laboratory of CAD&CG, Zhejiang University)
END:VEVENT
END:VCALENDAR