TIFace: Improving Facial Reconstruction through Tensorial Radiance Fields and Implicit Surfaces
This work solves the problem of high-quality facial reconstruction from sparse images for computer vision applications, representing an incremental improvement over baseline methods.
The paper tackled the problem of synthesizing novel viewpoint images of human heads from sparse views, addressing artifacts in facial reconstruction caused by complex textures and lighting. The proposed TI-Face method improved performance by using tensorial radiance fields and implicit surfaces, securing first place in the ICCV 2023 VSCHH challenge.
This report describes the solution that secured the first place in the "View Synthesis Challenge for Human Heads (VSCHH)" at the ICCV 2023 workshop. Given the sparse view images of human heads, the objective of this challenge is to synthesize images from novel viewpoints. Due to the complexity of textures on the face and the impact of lighting, the baseline method TensoRF yields results with significant artifacts, seriously affecting facial reconstruction. To address this issue, we propose TI-Face, which improves facial reconstruction through tensorial radiance fields (T-Face) and implicit surfaces (I-Face), respectively. Specifically, we employ an SAM-based approach to obtain the foreground mask, thereby filtering out intense lighting in the background. Additionally, we design mask-based constraints and sparsity constraints to eliminate rendering artifacts effectively. The experimental results demonstrate the effectiveness of the proposed improvements and superior performance of our method on face reconstruction. The code will be available at https://github.com/RuijieZhu94/TI-Face.