cs.CVNov 1, 2026

Spade-SLAM: Sparse Correspondence Anchors for Dense Self-Supervised Visual SLAM

Authors: Julian Philipp Schmitt, Weirong Chen, Ganlin Zhang, Felix Wimbauer, Daniel Cremers

Organizations: All authors are with Technical University of Munich, Munich, Germany. · All authors are with Munich Center for Machine Learning (MCML), Munich, Germany.

Abstract

We introduce Spade-SLAM, a self-supervised dense visual SLAM framework that substantially narrows the long-standing performance gap to supervised methods in a zero-shot setting. By demonstrating that high-fidelity tracking can be achieved without explicit ground-truth pose and depth labels, our approach offers a highly effective and label-efficient alternative to fully supervised pretraining. Our core contribution is a complementary sparse-to-dense training regime: While a warping-based photometric loss provides a dense training signal, we stabilize the optimization and suppress drift in ambiguous regions using a sparse correspondence loss derived from image feature matches. Extensive experiments demonstrate that Spade-SLAM significantly improves robustness and accuracy compared to existing self-supervised baselines, closely rivaling SLAM systems trained with explicit pose and depth supervision. The code will be made publicly available at https://github.com/JulianPSchmitt/Spade-SLAM.

Figures & tables

Explore similar work

CardsList
  1. VGGT-SLAM++

    Apr 8, 2026Avilasha Mandal, Rajesh Kumar, Sudarshan Sunil Harithas +1Visual SLAMVisual Odometry

  2. DASH-SLAM: Calibration-Free Metric Monocular SLAM via Depth Scale Propagation

    Nov 6, 2026Otavio Ribas, Jacopo Panerati, Pierre-Yves LajoieVisual SLAM

  3. Why does Deep Learning Improve Visual SLAM?

    Jul 7, 2026Giovanni Cioffi, Davide ScaramuzzaVisual SLAM