UltrAvatar: A Realistic Animatable 3D Avatar Diffusion Model with Authenticity Guided Textures
Authors:
- 16 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1238-1248
Abstract
Recent advances in 3D avatar generation have gained significant attention. These breakthroughs aim to produce more realistic animatable avatars, narrowing the gap between virtual and real-world experiences. Most of existing works employ Score Distillation Sampling (SDS) loss, combined with a differentiable renderer and text condition, to guide a diffusion model in generating 3D avatars. How-ever, SDS often generates over-smoothed results with few facial details, thereby lacking the diversity compared with ancestral sampling. On the other hand, other works gen-erate 3D avatar from a single image, where the challenges of unwanted lighting effects, perspective views, and inferior image quality make them difficult to reliably reconstruct the 3D face meshes with the aligned complete textures. In this paper, we propose a novel 3D avatar generation approach termed UltrAvatar with enhanced fidelity of geometry, and superior quality of physically based rendering (PBR)textures without unwanted lighting. To this end, the proposed approach presents a diffuse color extraction model and an authenticity guided texture diffusion model. The former removes the unwanted lighting effects to reveal true diffuse colors, so that the generated avatars can be rendered under various lighting conditions. The latter follows two gradient-based guidances for generating PBR textures to render diverse face-identity features and details better aligning with 3D mesh geometry. We demonstrate the effectiveness and robustness of the proposed method, outperforming the state-of-the-art methods by a large margin in the experiments.Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- TECA: Text-Guided Generation and Editing of Compositional 3D Avatars2024
- Towards Metrical Reconstruction of Human Faces2022
- Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks2020
- AvatarMe: Realistically Renderable 3D Facial Reconstruction “In-the-Wild”2020
- GANFIT: Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction2019
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Learning to Regress 3D Face Shape and Expression From an Image Without 3D Supervision2019
- BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation2018
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018
- Structure-from-Motion Revisited2016