Robust model fitting via motion-aware pyramid transformer-guided preference filtering and consensus smoothing

Author Identifier (ORCID)

David Suter’s ORCID record ORCID Logo

Abstract

Robust model fitting aims to estimate model parameters from data contaminated by noise and outliers in computer vision. Traditional RANSAC-based methods suffer from model hypothesis ambiguity and inefficiency due to the problems of neglecting data preference distributions and employing iterative hypothesis sampling. Learning-based methods enhance traditional methods through deep features. However, their reliance on static coordinate representations inherently lacks motion cues, hindering the analysis of complex dynamic scenes. Furthermore, the local receptive fields of CNNs inadequately capture global context. To address these issues, we propose MPCFormer, a motion-aware Transformer method via multi-channel preference filtering and multi-scale consensus smoothing for robust model fitting. It reformulates robust model fitting as a joint optimization of point classification and model estimation by integrating correspondence learning and embedding spatiotemporal motion cues, eliminating iterative hypothesis sampling. Specifically, we design a motion preference filter to explore multi-channel motion information by residual-connected Transformer layers. It explicitly encodes data preference distributions for models via multi-head preference attention, generating confidence scores to adaptively suppress outlier interference and enhance model robustness. Additionally, we present a pyramid consensus smoother with multi-scale Transformer encoding. It hierarchically captures local-to-global motion consistency through a sparse feature pyramid, effectively resolving motion ambiguity from spatial discontinuities. This module enables precise inlier identification and reliable model estimation through multi-head consensus attention. Extensive experiments demonstrate that MPCFormer outperforms state-of-the-art baselines by 4.68% mAP@5°, 1.89% AUC@3 pixel, and 1.52% F-score, even at extreme outlier ratios (up to 95%).

Keywords

correspondence learning, motion-aware transformers, multi-channel preference filter, multi-scale consensus smoother, outlier suppression, robust model fitting

Document Type

Journal Article

Date of Publication

1-1-2026

ISSN

01628828

Publication Title

IEEE Transactions on Pattern Analysis and Machine Intelligence

Publisher

IEEE

School

School of Science

Copyright

subscription content

Content Type

Metadata only

Recommended Citation

Yin, W., Wang, H., Lin, S., Yan, Y., Lu, Y., & Suter, D. (2026). Robust model fitting via motion-aware pyramid transformer-guided preference filtering and consensus smoothing. IEEE Transactions on Pattern Analysis and Machine Intelligence. Advance online publication. https://doi.org/10.1109/TPAMI.2026.3705535

Share

 
COinS
 

Link to publisher version (DOI)

10.1109/TPAMI.2026.3705535