We address domain-agnostic slice-to-volume (S2V) registration, the alignment of 2D sliced/tomographic images into 3D volumes without prior knowledge of structure, shape, or orientation. While S2V registration is well-studied in medical imaging, which often relies on auxiliary information (e.g. landmarks, segmentation masks, pre-defined orientations, canonical/atlas volumes), applications such as micro-structure characterization in materials science lack such domain-specific aids. This makes the task inherently ill-posed due to noise, unstructured regions, repetitive patterns, rotational and translational symmetries. To address this challenge, we present "Needles & Haystacks," a novel multi-domain algorithm development dataset with 158,436 unique registration problems and ground-truth solutions, based on diverse and openly licensed real-world volumetric data. Additionally, we provide an online platform with 8,461 test problems for reproducible evaluation of competing methods. We also propose strong baseline solutions with public implementations and highlight opportunities for further algorithmic advancements.
@article{nhrs2v_2025,
author = {Frolov, Anton and Kleiner, Florian and R\"o{\ss}ler, Christiane and Rodehorst, Volker},
title = {Needles \& Haystacks: Dataset and Benchmark for Domain-Agnostic Image-Based Rigid Slice-to-Volume Registration},
booktitle = {Proceedings of the Winter Conference on Applications of Computer Vision (WACV)},
month = {February},
year = {2025},
pages = {7081-7091}
}