Observability-Aware Rotation-Target Filtering for Self-Supervised Depth-Only Odometry
Plane-based pseudo-labels can provide complete pose targets even when scene geometry supports only some motion components. We introduce an observabilityaware training approach that gates rotation targets using matched-plane normal separation and projects translation residuals onto separately supported directions. The student is a depth-only model at inference and receives no geometric support indicators. We compare it with unfiltered supervision using the same 620,169- parameter student, five paired random seeds, equal training budgets, and a common data protocol. The evaluation covers nine sequences from TUM RGB-D, VCURVI and ETH3D, including four ETH3D zero-shot transfer sequences. Across all nine sequences, the filtered model has lower mean rotation root-mean-square error (RMSE) but higher mean translation RMSE than the unfiltered model. Thus the benefit is component-specific rather than a uniform pose improvement. Finite contiguoustrajectory tests likewise show no uniform trajectory benefit and reveal unfavorable translation accumulation. TUM and ETH3D provide verified-camera physical evidence; VCU results remain conditional because the supplied reference-frame semantics are not independently verified. The method is therefore best understood as targeted supervision for rotation under geometric degeneracy, not as a guarantee of globally improved odometry.
Authors
- Ouarda Lounis (ORCID: https://orcid.org/0000-0002-8081-5618)
- Farah Ibelaiden (ORCID: https://orcid.org/0009-0006-2820-5974)
- Seif Eddine Bouziane (ORCID: https://orcid.org/0000-0001-5244-1324)
Institutions
- National School of Artificial Intelligence (DZ)
Publication Details
- Journal
- Babylonian Journal of Artificial Intelligence
- Published
- 2026-11-17
- DOI
- https://doi.org/10.58496/bjai/2026/014
- Primary Topic
- Robotics and Sensor-Based Localization
- Type
- article
- Field-Weighted Citation Impact
- 0.00