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

arXiv: https://arxiv.org/abs/2605.31283 · HTML: https://mlsanity.com/paper/2605.31283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 14 references that are in the map.
- First posted on arXiv 29 May 2026.

## Builds on (most cited first, 3 of 3)

- [3D Morphable Face Models -- Past, Present and Future](https://mlsanity.com/paper/1909.01815/) (2019)
- [Embodied Hands: Modeling and Capturing Hands and Bodies Together](https://mlsanity.com/paper/2201.02610/) (2022)
- [Learning to Stabilize Faces](https://mlsanity.com/paper/2411.15074/) (2024)

## Abstract (arXiv)

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. SHELLS maintains surface consistency while using 88% less inference GPU memory (2.4GB vs. 20GB) than volumetric baselines. It reduces median registration error by 21% to 29% with a 3.5x inference speedup (0.08s vs. 0.29s) for 18k-vertex meshes. Notably, our model is trained exclusively on synthetic data yet generalizes effectively to real-world captures, eliminating the need for the costly, pre-registered multi-view datasets common in prior work.