Presentation / Installation


SketchFaceNeRF: Sketch-based Facial Generation and Editing in Neural Radiance Fields
SessionNeRFs for Avatars
DescriptionWe present a novel sketch-based 3D facial NeRF generation and editing method to produce free-view photo-realistic facial images. We lift 2D input sketches into tri-plane features to improve the robustness and faithfulness and employ 3D fusion and an optimization strategy to maintain consistency in unedited regions during editing.
Authors
Lin Gao
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Feng-Lin Liu
Institute of Computing Technology, Chinese Academy of Sciences
University of Chinese Academy of Sciences
Shu-Yu Chen
Institute of Computing Technology, Chinese Academy of Sciences
Kaiwen Jiang
Institute of Computing Technology, Chinese Academy of Sciences
Beijing Jiaotong University
Chun-Peng Li
Institute of Computing Technology, Chinese Academy of Sciences
Yu-Kun Lai
Cardiff University
Hongbo Fu
City University of Hong Kong
Event Type
Technical Paper
TimeThursday, 10 August 20233:56pm - 4:07pm PDT
LocationPetree Hall C
ACM Digital Library Technical Papers pdfs
Session Time & Location
Sunday, 6 August 20236pm - 8:30pm PDTWest Hall B
Thursday, 10 August 20233:45pm - 5:15pm PDTPetree Hall C
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Rendering
Video
Registration Categories
FC
FCS
V
VS
EFC
Next PresentationNext Presentation
HumanRF: High-fidelity Neural Radiance Fields for Humans in Motion