Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images
This work addresses limitations in flexibility, generalizability, robustness, and representation capability for researchers and practitioners in computer vision and 3D modeling, though it is incremental as it builds on prior explicit and implicit methods.
The paper tackles single-view 3D human reconstruction by proposing an explicit point-based framework (HaP) that uses point clouds as intermediate representations, achieving 20% to 40% quantitative performance improvements over state-of-the-art methods and better qualitative results.
The latest trends in the research field of single-view human reconstruction devote to learning deep implicit functions constrained by explicit body shape priors. Despite the remarkable performance improvements compared with traditional processing pipelines, existing learning approaches still show different aspects of limitations in terms of flexibility, generalizability, robustness, and/or representation capability. To comprehensively address the above issues, in this paper, we investigate an explicit point-based human reconstruction framework called HaP, which adopts point clouds as the intermediate representation of the target geometric structure. Technically, our approach is featured by fully-explicit point cloud estimation, manipulation, generation, and refinement in the 3D geometric space, instead of an implicit learning process that can be ambiguous and less controllable. The overall workflow is carefully organized with dedicated designs of the corresponding specialized learning components as well as processing procedures. Extensive experiments demonstrate that our framework achieves quantitative performance improvements of 20% to 40% over current state-of-the-art methods, and better qualitative results. Our promising results may indicate a paradigm rollback to the fully-explicit and geometry-centric algorithm design, which enables to exploit various powerful point cloud modeling architectures and processing techniques. We will make our code and data publicly available at https://github.com/yztang4/HaP.