FocusDiffuser: Perceiving Local Disparities for Camouflaged Object Detection
On the map: Diffusion models → Image generation, text-to-image and editing
Abstract (arXiv)
Detecting objects seamlessly blended into their surroundings represents a complex task for both human cognitive capabilities and advanced artificial intelligence algorithms. Currently, the majority of methodologies for detecting camouflaged objects mainly focus on utilizing discriminative models with various unique designs. However, it has been observed that generative models, such as Stable Diffusion, possess stronger capabilities for understanding various objects in complex environments; Yet their potential for the cognition and detection of camouflaged objects has not been extensively explored. In this study, we present a novel denoising diffusion model, namely FocusDiffuser, to investigate how generative models can enhance the detection and interpretation of camouflaged objects. We believe that the secret to spotting camouflaged objects lies in catching the subtle nuances in details. Consequently, our FocusDiffuser innovatively integrates specialized enhancements, notably the Boundary-Driven LookUp (BDLU) module and Cyclic Positioning (CP) module, to elevate standard diffusion models, significantly boosting the detail-oriented analytical capabilities. Our experiments demonstrate that FocusDiffuser, from a generative perspective, effectively addresses the challenge of camouflaged object detection, surpassing leading models on benchmarks like CAMO, COD10K and NC4K.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 39 of its 62 references that are in the map. First posted on arXiv 18 Jul 2024.
Builds on
39 of 62 references.
Closest ancestors · 2
Same direction, newest first
- 2023CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models29 May
- 2023LayoutDiffuse: Adapting Foundational Diffusion Models for Layout-to-Image Generation16 Feb
Other references · 37
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2020Denoising Diffusion Probabilistic Modelscited by 20,851
- 2020Denoising Diffusion Implicit Modelscited by 9,655
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2022Diffusion Models in Vision: A Surveycited by 1,008
- 2021Segmenter: Transformer for Semantic Segmentationcited by 855
- 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
- 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
25 more
- 2020PraNet: Parallel Reverse Attention Network for Polyp Segmentationcited by 460
- 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
- 2021Concealed Object Detectioncited by 212
- 2021Simultaneously Localize, Segment and Rank the Camouflaged Objectscited by 198
- 2021Diffusion Models for Implicit Image Segmentation Ensemblescited by 198
- 2021Visual Saliency Transformercited by 175
- 2021Camouflaged Object Segmentation with Distraction Miningcited by 151
- 2022Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detectioncited by 145
- 2021Salient Object Detection via Integrity Learningcited by 133
- 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
- 2021Mutual Graph Learning for Camouflaged Object Detectioncited by 103
- 2023Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformerscited by 87
- 2022High-resolution Iterative Feedback Network for Camouflaged Object Detectioncited by 78
- 2022Boundary-Guided Camouflaged Object Detectioncited by 68
- 2023Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objectscited by 56
- 2022Source-free Depth for Object Pop-outcited by 52
- 2023Stochastic Segmentation with Conditional Categorical Diffusion Modelscited by 38
- 2023Frequency Perception Network for Camouflaged Object Detectioncited by 37
- 2022Learning Optical Flow with Adaptive Graph Reasoningcited by 33
- 2023HSR-Diff:Hyperspectral Image Super-Resolution via Conditional Diffusion Modelscited by 31
- 2022OSFormer: One-Stage Camouflaged Instance Segmentation with Transformerscited by 30
- 2022Boosting Camouflaged Object Detection with Dual-Task Interactive Transformercited by 24
- 2023GAFlow: Incorporating Gaussian Attention into Optical Flowcited by 18
- 2023Object Segmentation by Mining Cross-Modal Semanticscited by 12
- 2023Learning 3D Photography Videos via Self-supervised Diffusion on Single Imagescited by 8
Built on by
Citing papers per year: 2025: 8; 2026: 6.
14 papers.
Sort:
By area:
- 2025RUN: Reversible Unfolding Network for Concealed Object Segmentationcited by 28
- 2025CamSAM2: Segment Anything Accurately in Camouflaged Videoscited by 7
- 2025Nested Unfolding Network for Real-World Concealed Object Segmentationcited by 7
- 2025Deep Learning in Concealed Dense Predictioncited by 6
- 2025SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentationcited by 6
- 2025Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentationcited by 3
- 2025Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillationcited by 2
- 2026DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesiscited by 1
- 2026CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wildcited by 1
- 2026B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentationcited by 1
- 2026Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidancecited by 1
- 2025LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detectioncited by 0
- 2026VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection30 Jul 2026
- 2026Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance25 May 2026
- 2026B-GRTO: Bootstrapped Group Relative Tool Optimization for Referring Segmentation22 May 2026
- 2026Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection14 Apr 2026
- 2026CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild9 Apr 2026
- 2026DMAligner: Enhancing Image Alignment via Diffusion Model Based View Synthesis26 Feb 2026
- 2025Nested Unfolding Network for Real-World Concealed Object Segmentation22 Nov 2025
- 2025SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation22 Nov 2025
- 2025Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation7 Jun 2025
- 2025LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detection20 Apr 2025
- 2025Deep Learning in Concealed Dense Prediction15 Apr 2025
- 2025Marine Saliency Segmenter: Object-Focused Conditional Diffusion with Region-Level Semantic Knowledge Distillation3 Apr 2025
2 more
- 2025RUN: Reversible Unfolding Network for Concealed Object Segmentationcited by 28
- 2025CamSAM2: Segment Anything Accurately in Camouflaged Videoscited by 7
- 2025Nested Unfolding Network for Real-World Concealed Object Segmentationcited by 7
- 2025Deep Learning in Concealed Dense Predictioncited by 6
- 2025SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentationcited by 6
- 2025Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentationcited by 3
- 2026CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wildcited by 1
- 2026Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidancecited by 1
- 2025LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detectioncited by 0
- 2026Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detectioncited by 0
- 2026VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detectioncited by 0
- 2026VCP-DCN: Beyond Visual Concealed Property via Depth Collaborative Network for Camouflaged Object Detection30 Jul 2026
- 2026Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance25 May 2026
- 2026Modality-Agnostic Prompt Learning for Multi-Modal Camouflaged Object Detection14 Apr 2026
- 2026CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild9 Apr 2026
- 2025Nested Unfolding Network for Real-World Concealed Object Segmentation22 Nov 2025
- 2025SCALER: SAM-Enhanced Collaborative Learning for Label-Deficient Concealed Object Segmentation22 Nov 2025
- 2025Stepwise Decomposition and Dual-stream Focus: A Novel Approach for Training-free Camouflaged Object Segmentation7 Jun 2025
- 2025LSP-ST: Ladder Shape-Biased Side-Tuning for Robust Infrared Small Target Detection20 Apr 2025
- 2025Deep Learning in Concealed Dense Prediction15 Apr 2025
- 2025CamSAM2: Segment Anything Accurately in Camouflaged Videos25 Mar 2025
- 2025RUN: Reversible Unfolding Network for Concealed Object Segmentation30 Jan 2025
Similar, not cited
Close in wording, no citation either way
- 2023Diffusion Model for Camouflaged Object Detection
- 2023CamDiff: Camouflage Image Augmentation via Diffusion Model
- 2023Catch Me If You Can Describe Me: Open-Vocabulary Camouflaged Instance Segmentation with Diffusion
- 2022DiffusionDet: Diffusion Model for Object Detection
- 2025First RAG, Second SEG: A Training-Free Paradigm for Camouflaged Object Detection
- 2025Text-guided Controllable Diffusion for Realistic Camouflage Images Generation
- 2026LAD-COD: Language-Aligned Dense Perception for Camouflaged Object Detection
- 2026Domain shift-robust object detection with GenAI image editing