GBC-Splat: Generalizable Gaussian-Based Clothed Human Digitalization under Sparse RGB Cameras

• Published in: Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) pp. 26377 - 26387
• Main Authors: Tu, Hanzhang, Liao, Zhanfeng, Zhou, Boyao, Zheng, Shunyuan, Zhou, Xilong, Zhang, Liuxin, Wang, QianYing, Liu, Yebin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 10.06.2025
• Subjects: Computer vision; Estimation; free-view synthesis; Geometry; human performance capture; human reconstruction; Optimization; Parametric statistics; Pattern recognition; Real-time systems; Shape; Surface reconstruction; Surface texture
• ISSN: 1063-6919
• DOI: 10.1109/CVPR52734.2025.02456

We present an efficient approach for generalizable clothed human digitalization, termed GBC-Splat. Unlike previous methods that necessitate per-subject optimizations or discount watertight geometry, the proposed method is dedicated to reconstructing complete human shapes and Gaussian Splatting via sparse view RGB inputs in a feed-forward manner. We first extract a fine-grained mesh using a combination of implicit occupancy field regression and explicit disparity estimation between views. The reconstructed high-quality geometry allows us to easily anchor Gaussian primitives to mesh surface according to surface normal and texture, which allows 6-DoF photorealistic novel view synthesis. In addition, we introduce a simple yet effective algorithm to subdivide Gaussian primitives in high-frequency areas to further enhance the visual quality. Without the assistance of human parametric models, our method can tackle loose garments, such as dresses and costumes. Our method outperforms state-of-the-art methods in terms of novel view synthesis while keeping high efficiency, enabling the potential of deployment in real-time applications.