GenCAMO: Scene-Graph Contextual Decoupling for Environment-aware and Mask-free Camouflage Image-Dense Annotation Generation

TL;DR

This paper introduces GenCAMO, a novel framework for generating high-quality, environment-aware camouflage images with dense annotations to enhance dense prediction tasks in complex camouflage scenes.

Contribution

The paper presents GenCAMO, a new generative model and a large-scale dataset for camouflage image synthesis, improving dense prediction performance in camouflage scene understanding.

Findings

GenCAMO significantly boosts dense prediction accuracy.

The dataset includes multi-modal annotations like depth, scene graphs, and text.

Synthetic data improves model training for complex camouflage scenes.

Abstract

Conceal dense prediction (CDP), especially RGB-D camouflage object detection and open-vocabulary camouflage object segmentation, plays a crucial role in advancing the understanding and reasoning of complex camouflage scenes. However, high-quality and large-scale camouflage datasets with dense annotation remain scarce due to expensive data collection and labeling costs. To address this challenge, we explore leveraging generative models to synthesize realistic camouflage image-dense data for training CDP models with fine-grained representations, prior knowledge, and auxiliary reasoning. Concretely, our contributions are threefold: (i) we introduce GenCAMO-DB, a large-scale camouflage dataset with multi-modal annotations, including depth maps, scene graphs, attribute descriptions, and text prompts; (ii) we present GenCAMO, an environment-aware and mask-free generative framework that produces high-fidelity camouflage image-dense annotations; (iii) extensive experiments across multiple modalities demonstrate that GenCAMO significantly improves dense prediction performance on complex camouflage scenes by providing high-quality synthetic data. The code and datasets will be released after paper acceptance.