Lighting-aware Unified Model for Instance Segmentation

• URL: http://arxiv.org/abs/2605.20436v1
• Date: Tue, 19 May 2026 19:35:51 GMT
• Title: Lighting-aware Unified Model for Instance Segmentation
• Abstract summary: We develop an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone.<n>lca employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes.<n>We present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions.
• Score: 12.511503644139369
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing \textit{Lighting Convolutional-Attention (\lca{})}, an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. \lca{} employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize \lca{} through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.

Related papers

• Generalized Synthetic Image Detection with Enhanced RGB-Noise Representation Learning [33.97020349697987]
  We propose RNSIDNet, a novel forensic framework that achieves robust detection through enhanced RGB-Noise representation learning.<n>Specifically, our method employs a dual-branch architecture where global RGB semantics, extracted by an attention-refined CLIP backbone, dynamically modulate high-frequency noise artifacts captured by Bayar convolutions via a Feature-wise Linear Modulation (FiLM) module.<n>To further enhance the learned representations, we design a Hard Sample-aware Contrastive Learning (HSCL) strategy.
  arXiv  Detail & Related papers  (2026-07-07T14:52:22Z)
• UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization [18.768161260032553]
  Ambient Lighting Normalization aims to restore images degraded by complex, spatially varying illumination conditions.<n>Existing methods, such as IFBlend, leverage frequency-domain priors to model illumination variations.<n>We propose UniBlendNet, a unified framework for ambient lighting normalization that jointly models global illumination, multi-scale structures, and region-adaptive refinement.
  arXiv  Detail & Related papers  (2026-04-15T01:13:18Z)
• Dual-Path Learning based on Frequency Structural Decoupling and Regional-Aware Fusion for Low-Light Image Super-Resolution [15.557346345104307]
  Low-light image super-resolution (LLISR) is essential for restoring fine visual details and perceptual quality under insufficient illumination conditions.<n>We propose Decoupling then Perceive (DTP), a novel frequency-aware framework that separates luminance and texture into semantically independent components.<n>Experiments on the most widely used LLISR benchmarks demonstrate the superiority of our DTP framework.
  arXiv  Detail & Related papers  (2026-03-28T15:15:08Z)
• Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation [18.67176370944511]
  Real-world dark images commonly exhibit not only low visibility and contrast but also complex noise and blur, posing significant restoration challenges.<n>We propose a generative framework based on visual autoregressive ( VAR) modeling, guided by perceptual priors from the vision-language model (VLM)<n>Our framework is fully unsupervised and achieves state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2025-11-23T19:08:45Z)
• After the Party: Navigating the Mapping From Color to Ambient Lighting [48.01497878412971]
  We introduce CL3AN, the first large-scale, high-resolution dataset of its kind.<n>We find that leading approaches often produce artifacts, such as illumination inconsistencies, texture leakage, and color distortion.<n>We achieve such a desired decomposition through a novel learning framework.
  arXiv  Detail & Related papers  (2025-08-04T08:07:03Z)
• Towards Generalized Range-View LiDAR Segmentation in Adverse Weather [65.22588361803942]
  We identify and analyze the unique challenges that affect the generalization of range-view LiDAR segmentation in severe weather.<n>We propose a modular and lightweight framework that enhances robustness without altering the core architecture of existing models.<n>Our approach significantly improves generalization to adverse weather with minimal inference overhead.
  arXiv  Detail & Related papers  (2025-06-10T16:48:27Z)
• 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)
• Enhancing Low-light Light Field Images with A Deep Compensation Unfolding Network [52.77569396659629]
  This paper presents the deep compensation network unfolding (DCUNet) for restoring light field (LF) images captured under low-light conditions. The framework uses the intermediate enhanced result to estimate the illumination map, which is then employed in the unfolding process to produce a new enhanced result. To properly leverage the unique characteristics of LF images, this paper proposes a pseudo-explicit feature interaction module.
  arXiv  Detail & Related papers  (2023-08-10T07:53:06Z)
• Toward Fast, Flexible, and Robust Low-Light Image Enhancement [87.27326390675155]
  We develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage. We make comprehensive explorations to SCI's inherent properties including operation-insensitive adaptability and model-irrelevant generality.
  arXiv  Detail & Related papers  (2022-04-21T14:40:32Z)
• Learning Deep Context-Sensitive Decomposition for Low-Light Image Enhancement [58.72667941107544]
  A typical framework is to simultaneously estimate the illumination and reflectance, but they disregard the scene-level contextual information encapsulated in feature spaces. We develop a new context-sensitive decomposition network architecture to exploit the scene-level contextual dependencies on spatial scales. We develop a lightweight CSDNet (named LiteCSDNet) by reducing the number of channels.
  arXiv  Detail & Related papers  (2021-12-09T06:25:30Z)

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.