Conditional Generative Denoiser for Nighttime UAV Tracking

TL;DR

This paper introduces CGDenoiser, a novel conditional generative denoising method that improves nighttime UAV tracking accuracy and speed, addressing real noise challenges in low-light conditions.

Contribution

It proposes a new conditional generative denoiser with nested residual Transformer and multi-kernel refiner, achieving faster inference and better denoising for UAV tracking in low-light environments.

Findings

Increases tracking precision by 18.18% on DarkTrack2021

Operates 5.8 times faster than previous denoisers

Proves effectiveness in real-world complex scenarios

Abstract

State-of-the-art (SOTA) visual object tracking methods have significantly enhanced the autonomy of unmanned aerial vehicles (UAVs). However, in low-light conditions, the presence of irregular real noise from the environments severely degrades the performance of these SOTA methods. Moreover, existing SOTA denoising techniques often fail to meet the real-time processing requirements when deployed as plug-and-play denoisers for UAV tracking. To address this challenge, this work proposes a novel conditional generative denoiser (CGDenoiser), which breaks free from the limitations of traditional deterministic paradigms and generates the noise conditioning on the input, subsequently removing it. To better align the input dimensions and accelerate inference, a novel nested residual Transformer conditionalizer is developed. Furthermore, an innovative multi-kernel conditional refiner is designed to pertinently refine the denoised output. Extensive experiments show that CGDenoiser promotes the tracking precision of the SOTA tracker by 18.18\% on DarkTrack2021 whereas working 5.8 times faster than the second well-performed denoiser. Real-world tests with complex challenges also prove the effectiveness and practicality of CGDenoiser. Code, video demo and supplementary proof for CGDenoier are now available at: \url{https://github.com/vision4robotics/CGDenoiser}.