ICPR 2026 Competition on Privacy-Preserving Person Re-Identification from Top-View RGB-Depth Camera (TVRID)

TL;DR

This paper introduces the ICPR 2026 TVRID competition, providing a new dataset and benchmark for privacy-aware top-view person re-identification using RGB and Depth data, with results highlighting modality challenges.

Contribution

It presents a novel dataset, evaluation protocol, and baseline results for privacy-preserving top-view person re-identification across multiple modalities.

Findings

RGB modality outperforms Depth in re-identification accuracy.

Cross-modal retrieval remains more challenging than single-modality tasks.

Strong modality-invariant learning methods can improve cross-modal re-identification.

Abstract

This companion paper reports the ICPR 2026 TVRID competition on privacy-aware top-view person re-identification. We present the competition setting, the released RGB-Depth dataset, and a summary of final results with descriptions of the top entries. TVRID contains 86 identities captured by four synchronized overhead Intel RealSense D455 cameras, with paired RGB/Depth streams and structured geometric variation across flat, ascent, descent, and oblique viewpoints. The evaluation protocol includes three tracks: RGB Re-ID, Depth Re-ID, and RGB$\leftrightarrow$Depth cross-modal retrieval. Submissions are ranked using mAP and CMC-1 under a unified server-side evaluation. The final results show a clear difficulty ordering (RGB $>$ Depth $>$ Cross-Modal), highlighting both the challenge of modality-constrained retrieval and the feasibility of strong performance with modality-invariant learning. By releasing the dataset at https://zenodo.org/records/17909410, the evaluation scripts at https://github.com/RaphaelDel/ICPR-TVRID, and the accompanying documentation, TVRID establishes a reproducible benchmark for top-view, depth-based, and cross-modal person re-id.