# Resolution as a Direction: Vector-Panning Feature Alignment for Cross-Resolution Re-Identification

arXiv: https://arxiv.org/abs/2510.00936 · HTML: https://mlsanity.com/paper/2510.00936/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 61 references that are in the map.
- First posted on arXiv 1 Oct 2025.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Deep Learning for Person Re-identification: A Survey and Outlook](https://mlsanity.com/paper/2001.04193/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Harmonious Attention Network for Person Re-Identification](https://mlsanity.com/paper/1802.08122/) (2018)
- [Cross-Modal Implicit Relation Reasoning and Aligning for Text-to-Image Person Retrieval](https://mlsanity.com/paper/2303.12501/) (2023)
- [DSSL: Deep Surroundings-person Separation Learning for Text-based Person Retrieval](https://mlsanity.com/paper/2109.05534/) (2021)
- [FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification](https://mlsanity.com/paper/1810.02936/) (2018)
- [ICE: Inter-instance Contrastive Encoding for Unsupervised Person Re-identification](https://mlsanity.com/paper/2103.16364/) (2021)
- [Deeply-Learned Part-Aligned Representations for Person Re-Identification](https://mlsanity.com/paper/1707.07256/) (2017)
- [Camera Style Adaptation for Person Re-identification](https://mlsanity.com/paper/1711.10295/) (2017)
- [NFormer: Robust Person Re-identification with Neighbor Transformer](https://mlsanity.com/paper/2204.09331/) (2022)
- [Unsupervised Tracklet Person Re-Identification](https://mlsanity.com/paper/1903.00535/) (2019)
- [Person Re-identification with Deep Similarity-Guided Graph Neural Network](https://mlsanity.com/paper/1807.09975/) (2018)
- [Person Re-Identification by Camera Correlation Aware Feature Augmentation](https://mlsanity.com/paper/1703.08837/) (2017)
- [Implicit Discriminative Knowledge Learning for Visible-Infrared Person Re-Identification](https://mlsanity.com/paper/2403.11708/) (2024)
- [Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification](https://mlsanity.com/paper/1908.06052/) (2019)
- [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025)
- [Camera-Driven Representation Learning for Unsupervised Domain Adaptive Person Re-identification](https://mlsanity.com/paper/2308.11901/) (2023)
- [Deep High-Resolution Representation Learning for Cross-Resolution Person Re-identification](https://mlsanity.com/paper/2105.11722/) (2021)
- [Intra-Camera Supervised Person Re-Identification: A New Benchmark](https://mlsanity.com/paper/1908.10344/) (2019)
- [Learning Resolution-Invariant Deep Representations for Person Re-Identification](https://mlsanity.com/paper/1907.10843/) (2019)
- [Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification](https://mlsanity.com/paper/2207.13035/) (2022)
- [Few-Shot Deep Adversarial Learning for Video-based Person Re-identification](https://mlsanity.com/paper/1903.12395/) (2019)
- [Dynamic Feature Pruning and Consolidation for Occluded Person Re-Identification](https://mlsanity.com/paper/2211.14742/) (2022)
- [Learning Resolution-Adaptive Representations for Cross-Resolution Person Re-Identification](https://mlsanity.com/paper/2207.13037/) (2022)

## Built on by (most cited first, 3 of 3)

- [MOS: Mitigating Optical-SAR Modality Gap for Cross-Modal Ship Re-Identification](https://mlsanity.com/paper/2512.03404/) (2025)
- [Towards Robust Text-to-Image Person Retrieval: Multi-View Reformulation for Semantic Compensation](https://mlsanity.com/paper/2604.18376/) (2026)
- [OmniPerson: Unified Identity-Preserving Pedestrian Generation](https://mlsanity.com/paper/2512.02554/) (2025)

## Abstract (arXiv)

Cross-resolution person re-identification (CR-ReID) remains challenging in practical surveillance, where camera quality and capture distance lead to substantial resolution gaps between low-resolution (LR) queries and high-resolution (HR) gallery images. Prior approaches commonly rely on super-resolution (SR) or resolution-invariant representation learning, which often increases system complexity and may not directly address the feature mismatch induced by resolution degradation. In this work, we report a new empirical finding from a dedicated analysis in which identity-specific variation is averaged out: the HR--LR feature discrepancy produced by standard ReID backbones exhibits a consistent, resolution-related semantic direction in the embedding space. We further support this observation with statistical analyses based on Canonical Correlation Analysis (CCA) and Pearson correlation analysis. Motivated by this finding, we propose Vector Panning Feature Alignment (VPFA), a lightweight post-hoc module that learns to pan LR features along the learned resolution direction to obtain pseudo-HR representations. VPFA operates after feature extraction and can be integrated into existing ReID systems with negligible overhead. Extensive experiments on multiple CR-ReID benchmarks show that VPFA achieves state-of-the-art performance while improving efficiency compared to SR-based or jointly trained alternatives.