RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects

• URL: http://arxiv.org/abs/2605.15450v1
• Date: Thu, 14 May 2026 22:19:52 GMT
• Title: RIDE: Retinex-Informed Decoupling for Exposing Concealed Objects
• Abstract summary: Concealed Object (COS) encompasses a family of dense-prediction tasks, including camouflaged object detection, polyp segmentation, transparent object detection, and industrial defect inspection.<n>Existing methods either operate directly on RGB images or employ emphheterogeneous decompositions that redistribute spatial evidence across scale/frequency coefficients.<n>We introduce a fundamentally different perspective: textbfhomogeneous image decomposition via Retinex theory, which factorizes an image into illumination and reflectance components within the emphsame spatial domain.
• Score: 13.362481648112444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Concealed Object Segmentation (COS) encompasses a family of dense-prediction tasks, including camouflaged object detection, polyp segmentation, transparent object detection, and industrial defect inspection, where targets are visually entangled with their surroundings through different physical mechanisms. Existing methods either operate directly on RGB images or employ \emph{heterogeneous} decompositions (\eg, Fourier, wavelet) that redistribute spatial evidence across scale/frequency coefficients, making pixel-aligned cues less direct. We introduce a fundamentally different perspective: \textbf{homogeneous image decomposition} via Retinex theory, which factorizes an image into illumination and reflectance components within the \emph{same} spatial domain. Our key insight is that visual entanglement enforces appearance matching in the composite space, but this does \emph{not} necessitate simultaneous matching in both component spaces, a phenomenon we formalize as the \textbf{Discriminability Gap Theorem}. Crucially, we show that across diverse COS sub-tasks, the underlying physical processes systematically anti-correlate illumination and reflectance differences, yielding theoretical guarantees that Retinex decomposition preserves or strictly improves total foreground--background discriminability across the full physical regime, with anti-correlation maximizing the gain. Building on this, we propose \textbf{RIDE} comprising: (i) a Task-Driven Retinex Decomposition module that learns segmentation-optimal factorizations end-to-end; (ii) a Discriminability Gap Attention mechanism that adaptively exploits where decomposition helps; and (iii) a Camouflage-Breaking Contrastive loss operating in reflectance feature space.

Related papers

• SGPDFuse: Semantically-Guided Physics-Disentanglement General Multi-Modal Image Fusion [12.582762404188257]
  Multimodal image fusion aims to integrate complementary sensor data into a single representation that preserves intrinsic scene reality.<n>We propose SGPDFuse, which bridges the gap by mapping inputs into a physics-disentangled structural representation.<n>We show that SGPDFuse achieves state-of-the-art performance across infrared-visible, multi-focus, and multi-exposure benchmarks.
  arXiv  Detail & Related papers  (2026-08-29T12:08:27Z)
• Hyperspectral Intrinsic Decomposition: Joint Recovery of Reflectance and Photometric Components for Non-Lambertian Scenes [29.51510553736925]
  Hyperspectral intrinsic decomposition (HID) aims to disentangle material-related spectral properties and photometric effects in hyperspectral images.<n>Most existing HID studies have been developed under Lambertian or near-Lambertian assumptions.<n>We develop a unified inversion paradigm that reformulates the recovery of four coupled reflectance and photometric components as the estimation of two spectral--spatial target variables.
  arXiv  Detail & Related papers  (2026-07-28T07:26:07Z)
• PRISM: Latent Composition Consistency for Single-Image Reflection Removal [8.368543987898734]
  Single-image reflection removal (SIRR) seeks to recover the transmission layer from a mixture corrupted by reflections.<n>Existing methods operate in pixel space, where the nonlinear sRGB formation model entangles the two layers.<n>We propose textbfPRISM (Pretrained-latent Reflection Image Separation Model), which reinterprets SIRR as a latent linear separation problem.
  arXiv  Detail & Related papers  (2026-06-30T11:28:02Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Oversmoothing as Representation Degeneracy in Neural Sheaf Diffusion [0.0]
  Neural Sheaf Diffusion (NSD) generalizes diffusion-based Graph Neural Networks by replacing scalar graph Laplacians with sheaf Laplacians.<n>We develop a quiver-theoretic interpretation of NSD by identifying cellular sheaves on graphs with representations of the associated incidence.<n>We show that direct-sum decompositions of the underlying incidence-quiver representation induce decompositions of the harmonic space reached in the diffusion limit.
  arXiv  Detail & Related papers  (2026-05-11T19:41:56Z)
• Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers [0.33842793760651557]
  We introduce a hallucination-free inversion framework built on magnitude-phase decoupling and Local Adjoint Correctors.<n>Our method mathematically guarantees that the spatial gradient support of every reconstruction stems strictly from genuinely active channels.<n>Using this framework as a geometric probe, we uncover the first pixel-level evidence of strong superposition in vision encoders.
  arXiv  Detail & Related papers  (2026-04-30T07:32:07Z)
• Hyperbolic Enhanced Representation Learning for Incomplete Multi-view Clustering [57.38215918201251]
  We propose HERL, a Hyperbolic Enhanced Representation Learning framework for Incomplete Multi-View Clustering.<n> operating within the Poincaré ball, HERL constructs a structure-aware latent space to enhance representation learning.<n>We show that HERL consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-04-18T10:50:46Z)
• Beyond Cosine Similarity: Zero-Initialized Residual Complex Projection for Aspect-Based Sentiment Analysis [3.154269505086155]
  Aspect-Based Sentiment Analysis (ABSA) is fundamentally challenged by representation entanglement.<n>Standard contrastive learning suffers from false-negative collisions, severely degrading performance on high-frequency aspects.<n>We propose a novel framework featuring a Zero-Residual Complex Projection and an Anti-collision Masked Angle Loss.
  arXiv  Detail & Related papers  (2026-03-30T09:23:04Z)
• Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning [28.392130815615545]
  Spectral Disentanglement and Enhancement (SDE) is a novel framework that bridges the gap between the geometry of the embedded spaces and their spectral properties.<n>SDE consistently improves representation and robustness, outperforming state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-02-09T07:29:43Z)
• MirrorLA: Reflecting Feature Map for Vision Linear Attention [49.41670925034762]
  Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance.<n>We propose MirrorLA, a geometric framework that substitutes passive truncation with active reorientation.<n>MirrorLA achieves state-of-the-art performance across standard benchmarks, demonstrating that strictly linear efficiency can be achieved without compromising representational fidelity.
  arXiv  Detail & Related papers  (2026-02-04T09:14:09Z)
• Interpreting Structured Perturbations in Image Protection Methods for Diffusion Models [17.625614970517884]
  Glaze and Nightshade introduce imperceptible, adversarially designed perturbations intended to disrupt downstream text-to-image generative models.<n>This study provides a systematic, explainable AI analysis using a unified framework that integrates white-box feature-space inspection and black-box signal-level probing.<n>We show that protection mechanisms operate as structured, low-entropy perturbations tightly coupled to underlying image content across representational, spatial, and spectral domains.
  arXiv  Detail & Related papers  (2025-12-09T07:55:11Z)
• Manifold-aware Representation Learning for Degradation-agnostic Image Restoration [135.90908995927194]
  Image Restoration (IR) aims to recover high quality images from degraded inputs affected by various corruptions such as noise, blur, haze, rain, and low light conditions.<n>We present MIRAGE, a unified framework for all in one IR that explicitly decomposes the input feature space into three semantically aligned parallel branches.<n>This modular decomposition significantly improves generalization and efficiency across diverse degradations.
  arXiv  Detail & Related papers  (2025-05-24T12:52:10Z)
• Low-Light Video Enhancement via Spatial-Temporal Consistent Decomposition [52.89441679581216]
  Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise.<n>We present an innovative video decomposition strategy that incorporates view-independent and view-dependent components.<n>Our framework consistently outperforms existing methods, establishing a new SOTA performance.
  arXiv  Detail & Related papers  (2024-05-24T15:56:40Z)
• Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement [58.9768112704998]
  Disentangled representation learning strives to extract the intrinsic factors within observed data. We introduce a new perspective and framework, demonstrating that diffusion models with cross-attention can serve as a powerful inductive bias. This is the first work to reveal the potent disentanglement capability of diffusion models with cross-attention, requiring no complex designs.
  arXiv  Detail & Related papers  (2024-02-15T05:07:54Z)
• ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection [70.11264880907652]
  Recent object (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. We propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and camouflaged zooming in and out. Our framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks.
  arXiv  Detail & Related papers  (2023-10-31T06:11:23Z)
• PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant Semantic Segmentation [50.556961575275345]
  We propose a perception-aware fusion framework to promote segmentation robustness in adversarial scenes. We show that our scheme substantially enhances the robustness, with gains of 15.3% mIOU, compared with advanced competitors.
  arXiv  Detail & Related papers  (2023-08-08T01:55:44Z)
• Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation [56.44946660061753]
  This paper proposes a universal regularization technique called maximum spatial perturbation consistency (MSPC) MSPC enforces a spatial perturbation function (T ) and the translation operator (G) to be commutative (i.e., TG = GT ) Our method outperforms the state-of-the-art methods on most I2I benchmarks.
  arXiv  Detail & Related papers  (2022-03-23T19:59:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.