YUV20K: A Complexity-Driven Benchmark and Trajectory-Aware Alignment Model for Video Camouflaged Object Detection

TL;DR

This paper introduces YUV20K, a comprehensive benchmark dataset for video camouflaged object detection, and proposes a novel alignment framework with modules for motion stabilization and trajectory-aware alignment, improving robustness in complex scenarios.

Contribution

It provides a large, challenging annotated dataset and a new alignment framework with modules for motion stabilization and trajectory-aware alignment, advancing VCOD performance.

Findings

The proposed method outperforms existing models on multiple datasets.

YUV20K enables better evaluation of VCOD methods in complex scenarios.

The framework shows strong cross-domain generalization and robustness.

Abstract

Video Camouflaged Object Detection (VCOD) is currently constrained by the scarcity of challenging benchmarks and the limited robustness of models against erratic motion dynamics. Existing methods often struggle with Motion-Induced Appearance Instability and Temporal Feature Misalignment caused by complex motion scenarios. To address the data bottleneck, we present YUV20K, a pixel-level annoated complexity-driven VCOD benchmark. Comprising 24,295 annotated frames across 91 scenes and 47 kinds of species, it specifically targets challenging scenarios like large-displacement motion, camera motion and other 4 types scenarios. On the methodological front, we propose a novel framework featuring two key modules: Motion Feature Stabilization (MFS) and Trajectory-Aware Alignment (TAA). The MFS module utilizes frame-agnostic Semantic Basis Primitives to stablize features, while the TAA module leverages trajectory-guided deformable sampling to ensure precise temporal alignment. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art competitors on existing datasets and establishes a new baseline on the challenging YUV20K. Notably, our framework exhibits superior cross-domain generalization and robustness when confronting complex spatiotemporal scenarios. Our code and dataset will be available at https://github.com/K1NSA/YUV20K