VSCHH 2023: A Benchmark for the View Synthesis Challenge of Human Heads

Authors
Youngkyoon JangJiali ZhengJifei SongHelisa DhamoEduardo Perez-PelliteroThomas TanayMatteo MaggioniRichard ShawSibi Catley-ChandarYiren ZhouJiankang DengRuijie ZhuJiahao ChangZiyang SongJiahuan YuTianzhu ZhangKhanh-Binh NguyenJoon-Sung YangAndreea DogaruBernhard EggerHeng YuAarush GuptaJoel JulinLaszlo A. JeniHyeseong KimJungbin ChoDosik HwangLee, Deuk heeDoyeon KimDongseong SeoSeungJin JeonYoungDon Choi강준석Seker, Ahmet CagatayAhn, Sang ChulAles LeonardisStefanos Zafeiriou
Issue Date
2023-10-02
Publisher
Computer Vision Foundation(CVF), IEEE
Citation
ICCV2023 workshop, A View Synthesis Challenge for Human Heads(VSCHH)
Abstract
This manuscript presents the results of the “A View Synthesis Challenge for Humans Heads (VSCHH)”, which was part of the ICCV 2023 workshops. This paper describes the competition setup and provides details on replicating our initial baseline, TensoRF. Additionally, we provide a summary of the participants’ methods and their results in our benchmark table. The challenge aimed to synthesize novel camera views of human heads using a given set of sparse training view images. The proposed solutions of the participants were evaluated and ranked based on objective fidelity metrics, such as PSNR and SSIM, computed against unseen validation and test sets. In the supplementary material, we detailed the methods used by all participants in the VSCHH challenge, which opened on May 15th, 2023, and concluded on July 24th, 2023.
URI

Go to Link
Appears in Collections:
KIST Conference Paper > 2023
Files in This Item:
Jang_VSCHH_2023_A_Benchmark_for_the_View_Synthesis_Challenge_of_ICCVW_2023_paper.pdf(1.25 MB)Download
Jang_VSCHH_2023_A_ICCVW_2023_supplemental.pdf(7.98 MB)Download
Export
RIS (EndNote)
XLS (Excel)
XML

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE