FNeVR: Neural Volume Rendering for Face Animation
Nov 28, 2022
Speakers
Bohan Zeng
Speaker · 0 followers
Xu-Hui Liu
Speaker · 0 followers
Jianzhuang Liu
Speaker · 0 followers
Dapeng Chen
Speaker · 0 followers
Baochang Zhang
Speaker · 0 followers
About
Face animation, one of the hottest topics in computer vision, has achieved a promising performance with the help of generative models. However, it remains a critical challenge to generate identity preserving and photo-realistic images due to the sophisticated motion deformation and complex facial detail modeling. To address these problems, we propose a Face Neural Volume Rendering (FNeVR) network to fully explore the potential of 2D motion warping and 3D volume rendering in a unified framework. In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering. Specifically, we first extract 3D information with a well designed architecture, and then introduce an orthogonal adaptive ray-sampling module for efficient rendering. We also design a lightweight pose editor, enabling FNeVR to edit the facial pose in a simple yet effective way. Extensive experiments show that our FNeVR obtains the best overall quality and performance on widely used talking-head benchmarks.Face animation, one of the hottest topics in computer vision, has achieved a promising performance with the help of generative models. However, it remains a critical challenge to generate identity preserving and photo-realistic images due to the sophisticated motion deformation and complex facial detail modeling. To address these problems, we propose a Face Neural Volume Rendering (FNeVR) network to fully explore the potential of 2D motion warping and 3D volume rendering in a unified framework.…
Organizer
NeurIPS 2022
Account · 961 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Learning in Congestion Games with Bandit Feedback
Watch later
Zhihan Xiong, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
Watch later
Yanpeng Sun, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Featured Papers Panels 5A
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Detection and Localization of Changes in Conditional Distributions
Watch later
Lizhen Nie, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Variational Reparametrized Policy Learning with Differentiable Physics
Watch later
Zhiao Huang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Fair and Efficient Allocations Without Obvious Manipulations
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%