Seker, Ahmet Cagatay Junseok, Kang Ahn, Sang Chul 2025-02-28T09:00:17Z 2025-02-28T09:00:17Z 2025-02-27 2025-02 https://pubs.kist.re.kr/handle/201004/151805 Head avatar reconstruction is a crucial research topic with wide-ranging applications. For this purpose, utilizing the promising technique of 3D Gaussian splatting significantly improves rendering quality. However, this method encounters challenges, such as imprecise geometry and noisy surfaces. To address these issues, we propose HeteroAvatar, a novel method for generating a Gaussian head avatar with correct geometry from a monocular video of a dynamic head. To achieve this, we introduce the hetero rendering method, which concurrently employs both 3D Gaussian rendering and mesh rendering techniques during training. This approach enables HeteroAvatar to accurately capture the head geometry with smooth surfaces while maintaining photorealistic rendering quality. Additionally, our approach is capable of generating a mesh-based head avatar, which ensures compatibility with a wide range of traditional graphics applications. Experimental results demonstrate that HeteroAvatar outperforms state-of-the-art methods in terms of reconstructed geometry quality and photorealistic rendering with fewer 3D Gaussians. Project page: https://felizang.github.io/HeteroAvatar. English Institute of Electrical and Electronics Engineers Inc. HeteroAvatar: Generation of Gaussian Head Avatars With Correct Geometry Using Hetero Rendering Article 10.1109/ACCESS.2025.3543163 1 IEEE Access, v.13, pp.33768 - 33782 IEEE Access 13 33768 33782 N scie scopus 001432827800004 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article 3D Gaussian splatting 3D head reconstruction 3D head reconstruction head avatar generation head avatar generation mesh rendering mesh rendering mesh rendering