DaDiff: Domain-aware Diffusion Model for Nighttime UAV Tracking

TL;DR

DaDiff introduces a progressive domain-aware diffusion model to improve nighttime UAV tracking by aligning low-resolution night images with daytime features, addressing noise and detail loss.

Contribution

It proposes a novel progressive alignment paradigm with specialized modules for nighttime UAV tracking, including a new benchmark dataset for low-resolution objects.

Findings

Demonstrates robustness in feature alignment and tracking accuracy

Outperforms existing methods on the NUT-LR benchmark

Provides a new dataset for low-resolution nighttime UAV tracking

Abstract

Domain adaptation is an inspiring solution to the misalignment issue of day/night image features for nighttime UAV tracking. However, the one-step adaptation paradigm is inadequate in addressing the prevalent difficulties posed by low-resolution (LR) objects when viewed from the UAVs at night, owing to the blurry edge contour and limited detail information. Moreover, these approaches struggle to perceive LR objects disturbed by nighttime noise. To address these challenges, this work proposes a novel progressive alignment paradigm, named domain-aware diffusion model (DaDiff), aligning nighttime LR object features to the daytime by virtue of progressive and stable generations. The proposed DaDiff includes an alignment encoder to enhance the detail information of nighttime LR objects, a tracking-oriented layer designed to achieve close collaboration with tracking tasks, and a successive distribution discriminator presented to distinguish different feature distributions at each diffusion timestep successively. Furthermore, an elaborate nighttime UAV tracking benchmark is constructed for LR objects, namely NUT-LR, consisting of 100 annotated sequences. Exhaustive experiments have demonstrated the robustness and feature alignment ability of the proposed DaDiff. The source code and video demo are available at https://github.com/vision4robotics/DaDiff.