RAFT-DVC: Resolution-Aware Machine Learning-Based Digital Volume Correlation
Abstract
Digital volume correlation (DVC) provides three-dimensional full-field displacement measurements from volumetric images, but how the internal resolution of a machine-learning-based DVC model affects accuracy and operating range remains poorly understood. Here, we present RAFT-DVC, a resolution-aware family of recurrent all-pairs field transforms (RAFT)-based DVC solvers with encoder downsampling factors s = 2, 4, and 8. Using a matched design, we find that the three solvers localize displacement to approximately 0.017 feature-grid voxel, giving an empirical raw-volume error scaling of approximately 0.017s voxel. The solvers exhibit complementary operating regimes governed jointly by displacement reach and volumetric-texture compatibility. Synthetic benchmarks show that RAFT-DVC achieves errors of the same order as tuned classical DVC under fine-texture, small-to-moderate-displacement conditions and becomes competitive or advantageous under coarse-texture, large-displacement conditions. Frequency-swept tests quantify deformation spatial resolution, while tiled inference enables dense estimation on large volumes. Evaluation on confocal volumetric images acquired during indentation illustrates the importance of matching solver operating regime to deformation magnitude and image texture. Tests on micro-CT images of elastomeric foam, despite training only on particle-labeled synthetic data, provide evidence of cross-texture transfer. We also identify coordinate-order inconsistencies in three-dimensional RAFT correlation sampling and introduce a non-cubic impulse test to verify sampler geometry independently of network training. Correcting the sampler improves native-input accuracy and generalization to unseen volume dimensions. Together, these results establish RAFT-DVC as a fast, resolution-aware framework for dense DVC with characterized accuracy and operating regimes.
Related
- Identification of damage mechanisms in a metal-matrix composite material via digital volume correlation and finite element model updating
- Machine Learning Unveils Finite-volume Energy Shifts in Three-body System
- Machine Learning-Based Inter-Crystal Scatter Recovery for Ultra-High Resolution PET Imaging
- Digital Twins of Networked Dynamical Systems: Machine Learning Prediction of Synchronization Transitions in Coupled Chaotic Oscillators
- Quantum Machine Learning for Few-Shot Impersonation Detection in Digital Account Opening
BibTeX
@misc{tong2026raftdvc,
title = {{RAFT-DVC: Resolution-Aware Machine Learning-Based Digital Volume Correlation}},
author = {Zixiang Tong and Lehu Bu and Jin Yang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.01876},
eprint = {2609.01876},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.01876},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - RAFT-DVC: Resolution-Aware Machine Learning-Based Digital Volume Correlation
AU - Zixiang Tong
AU - Lehu Bu
AU - Jin Yang
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.01876
UR - https://arxiv.org/abs/2609.01876
AB - Digital volume correlation (DVC) provides three-dimensional full-field displacement measurements from volumetric images, but how the internal resolution of a machine-learning-based DVC model affects accuracy and operating range remains poorly understood. Here, we present RAFT-DVC, a resolution-aware family of recurrent all-pairs field transforms (RAFT)-based DVC solvers with encoder downsampling factors s = 2, 4, and 8. Using a matched design, we find that the three solvers localize displacement to approximately 0.017 feature-grid voxel, giving an empirical raw-volume error scaling of approximately 0.017s voxel. The solvers exhibit complementary operating regimes governed jointly by displacement reach and volumetric-texture compatibility. Synthetic benchmarks show that RAFT-DVC achieves errors of the same order as tuned classical DVC under fine-texture, small-to-moderate-displacement conditions and becomes competitive or advantageous under coarse-texture, large-displacement conditions. Frequency-swept tests quantify deformation spatial resolution, while tiled inference enables dense estimation on large volumes. Evaluation on confocal volumetric images acquired during indentation illustrates the importance of matching solver operating regime to deformation magnitude and image texture. Tests on micro-CT images of elastomeric foam, despite training only on particle-labeled synthetic data, provide evidence of cross-texture transfer. We also identify coordinate-order inconsistencies in three-dimensional RAFT correlation sampling and introduce a non-cubic impulse test to verify sampler geometry independently of network training. Correcting the sampler improves native-input accuracy and generalization to unseen volume dimensions. Together, these results establish RAFT-DVC as a fast, resolution-aware framework for dense DVC with characterized accuracy and operating regimes.
ER -