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:20250110T023309Z
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:Technical Papers\n\nEach Paper gives a 10 minute presentation.
 \n\nGS^3: Efficient Relighting with Triple Gaussian Splatting\n\nWe presen
 t a spatial and angular Gaussian based representation and a triple splatti
 ng process, for real-time, high-quality novel lighting-and-view synthesis 
 from multi-view point-lit input images. To describe complex appearance, we
  employ a Lambertian plus a mixture of angular Gaussians as an effect...\n
 \n\nZoubin Bi, Yixin Zeng, Chong Zeng, Fan Pei, Xiang Feng, Kun Zhou, and 
 Hongzhi Wu (State Key Laboratory of CAD&CG, Zhejiang University)\n--------
 -------------\nDifFRelight: Diffusion-Based Facial Performance Relighting\
 n\nWe present a novel framework for free-viewpoint facial performance reli
 ghting using diffusion-based image-to-image translation. Leveraging a subj
 ect-specific dataset containing diverse facial expressions captured under 
 various lighting conditions, including flat-lit and one-light-at-a-time (O
 LAT) sc...\n\n\nMingming He (Netflix Eyeline Studios); Pascal Clausen (Net
 flix Eyeline Studios, Osylum); and Ahmet Levent Taşel, Li Ma, Oliver Pilar
 ski, Wenqi Xian, Laszlo Rikker, Xueming Yu, Ryan Burgert, Ning Yu, and Pau
 l Debevec (Netflix Eyeline Studios)\n---------------------\nNeRF-Casting: 
 Improved View-Dependent Appearance with Consistent Reflections\n\nNeural R
 adiance Fields (NeRFs) typically struggle to reconstruct and render highly
  specular objects, whose appearance varies quickly with changes in viewpoi
 nt. Recent works have improved NeRF's ability to render detailed specular 
 appearance of distant environment illumination, but are unable to synt...\
 n\n\nDor Verbin, Pratul P. Srinivasan, Peter Hedman, and Ben Mildenhall (G
 oogle Research); Benjamin Attal (Carnegie Mellon University); and Richard 
 Szeliski and Jonathan T. Barron (Google Research)\n---------------------\n
 OLAT Gaussians for Generic Relightable Appearance Acquisition\n\nOne-light
 -at-a-time (OLAT) images sample a broader range of object appearance chang
 es than images captured under constant lighting and are superior as input 
 to object relighting. Although existing methods have produced reasonable r
 elighting quality using OLAT images, they utilize surface-like repres...\n
 \n\nZhiyi Kuang (State Key Laboratory of CAD&CG, Zhejiang University); Yan
 chao Yang and Siyan Dong (University of Hong Kong); Jiayue Ma (State Key L
 aboratory of CAD&CG, Zhejiang University); Hongbo Fu (Hong Kong University
  of Science and Technology); and Youyi Zheng (State Key Laboratory of CAD&
 CG, Zhejiang University)\n---------------------\nLocal Gaussian Density Mi
 xtures for Unstructured Lumigraph Rendering\n\nTo improve novel-view synth
 esis of curved surface reflections and refractions, we revisit local geome
 try-guided ray interpolation techniques with modern differentiable renderi
 ng and optimization.\nIn contrast to depth or mesh geometries, our approac
 h uses a local or per-view density represented as Ga...\n\n\nXiuchao Wu (S
 tate Key Laboratory of CAD&CG, Zhejiang University); Jiamin Xu (Hangzhou D
 ianzi Univeristy); Chi Wang (State Key Laboratory of CAD&CG, Zhejiang Univ
 ersity); Yifan Peng (University of Hong Kong); Qixing Huang (University of
  Texas at Austin); James Tompkin (Brown University); and Weiwei Xu (State 
 Key Laboratory of CAD&CG, Zhejiang University)\n---------------------\nRef
 lection-Aware Neural Radiance Fields\n\nNeural Radiance Fields (NeRF) have
  demonstrated exceptional capabilities in reconstructing complex scenes wi
 th high fidelity. However, NeRF's view dependency can only handle low-freq
 uency reflections. It falls short when handling complex planar reflections
 , often interpreting them as erroneous scene...\n\n\nChen Gao, Yipeng Wang
 , and Changil Kim (Meta); Jia-Bin Huang (University of Maryland, College P
 ark); and Johannes Kopf (Meta)\n\nRegistration Category: Full Access, Full
  Access Supporter\n\nLanguage Format: English Language\n\nSession Chair: H
 ongzhi Wu (Zhejiang University; State Key Laboratory of CAD&CG, Zhejiang U
 niversity)
END:VEVENT
END:VCALENDAR