{"ID":5937284,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T07:20:22.971468815Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04745","arxiv_id":"2607.04745","title":"Trajectory-Anchor Optimization for Overconfident Thermal Visual Place Recognition: Zero-Leakage OOD Auditing and Kidnapped-Robot Recovery","abstract":"Modern thermal visual place recognition (TIR-VPR) frontends based on foundation models achieve remarkable closed-set retrieval but suffer from an overconfident forced-matching failure mode. Under out-of-distribution (OOD) or unmapped conditions, they generate highly plausible yet false loop candidates without a drop in similarity scores. While classical multi-hypothesis tracking (MHT) backends can mitigate these ambiguities by maintaining divergent trajectory beliefs, their exponential computational overhead violates real-time robotic constraints. To bridge this gap, we present Trajectory-Anchor Optimization (TAO). To counter the combinatorial challenge of evaluating parallel hypotheses (e.g., K=100), TAO compresses multi-view temporal verification into a batched SE(2) Procrustes alignment problem. By leveraging tensor-level vectorization and single-invocation batched SVD, this formulation bypasses the dynamic tree expansion of MHT, guaranteeing a strictly bounded per-frame execution loop of O(KN). Under a strict zero-leakage evaluation protocol, we show that while a passive geometric backend cannot mathematically separate metric localization errors from coherent hallucinations at a micro-scale (\u003c5m) due to local visual ambiguities, TAO serves as an efficient fail-safe filter at a macro-scale. Within a 5m radius, hallucinations often possess a locally consistent geometry that deceives rigid alignment. However, beyond this threshold, the K=100 disparate hypotheses disperse spatially across the global map. This dispersion breaks the rigid temporal co-visibility constraint within the sliding window (N=20), causing the joint optimization residual to escalate sharply. Consequently, TAO establishes a distinct macroscopic convergence basin (10m) where multi-view geometric consistency reliably isolates catastrophic topological breaks and suppresses critical false acceptances.","short_abstract":"Modern thermal visual place recognition (TIR-VPR) frontends based on foundation models achieve remarkable closed-set retrieval but suffer from an overconfident forced-matching failure mode. Under out-of-distribution (OOD) or unmapped conditions, they generate highly plausible yet false loop candidates without a drop in...","url_abs":"https://arxiv.org/abs/2607.04745","url_pdf":"https://arxiv.org/pdf/2607.04745v1","authors":"[\"Zhiyuan Lu\",\"Kanji Tanaka\"]","published":"2026-07-06T07:31:37Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.CV\"]","methods":"[]","has_code":false}