Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling 文章

ArXiv CS.CV2026-06-01NEWSen作者: Timo Bolkart, Daoye Wang, Prashanth Chandran

摘要

arXiv:2605.31283v1 Announce Type: new Abstract: We present SHELLS (Semantic Head Estimation via Layered Local Sampling), an efficient feed-forward framework for 3D head reconstruction in dense semantic correspondence from multi-view images. Existing methods typically refine vertices independently via localized feature volumes. This approach couples memory-intensive feature sampling to mesh resolution, which limits scalability for dense topologies (> 10k vertices) and introduces surface noise. In contrast, SHELLS decouples feature extraction from mesh resolution via a hierarchical sampling strategy. We extract multi-view features using a DINOv2 backbone with LoRA adaptation, projectively sample a sparse global feature cloud, and predict an intermediate coarse mesh. This coarse prior guides the construction of layered, surface-aware sampling shells that serve as a discrete search space for the final reconstruction.

相关公司

暂无数据

相关人物

暂无数据