UniISP: A Unified ISP Framework for Both Human and Machine Vision

• URL: http://arxiv.org/abs/2605.07359v1
• Date: Fri, 08 May 2026 07:13:14 GMT
• Title: UniISP: A Unified ISP Framework for Both Human and Machine Vision
• Abstract summary: Raw sensor data provides a richer representation of information, which is crucial for accurate recognition.<n>Traditional Image Signal Processing pipeline generates visually pleasing RGB images for human perception through a series of steps.<n>In computer vision tasks that directly utilize raw camera data, most existing methods integrate minimal ISP processing with downstream networks.<n>This paper proposes UniISP, a novel ISP framework designed to simultaneously meet the requirements of both human visual perception and computer vision applications.
• Score: 10.279867927108613
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Compared to RGB images, raw sensor data provides a richer representation of information, which is crucial for accurate recognition, particularly under challenging conditions such as low-light environments. The traditional Image Signal Processing (ISP) pipeline generates visually pleasing RGB images for human perception through a series of steps, but some of these operations may adversely impact the information integrity by introducing compression and loss. Furthermore, in computer vision tasks that directly utilize raw camera data, most existing methods integrate minimal ISP processing with downstream networks, yet the resulting images are often difficult to visualize or do not align with human aesthetic preferences. This paper proposes UniISP, a novel ISP framework designed to simultaneously meet the requirements of both human visual perception and computer vision applications. By incorporating a carefully designed Hybrid Attention Module (HAM) and employing supervised learning, the proposed method ensures that the generated images are visually appealing. Additionally, a Feature Adapter module is introduced to effectively propagate informative features from the ISP stage to subsequent downstream networks. Extensive experiments demonstrate that our approach achieves state-of-the-art performance across various scenarios and multiple datasets, proving its generalizability and effectiveness.

Related papers

• Task-Aware Image Signal Processor for Advanced Visual Perception [32.29324101518987]
  Task-Aware Image Signal Processing (TA-ISP) is a compact RAW-to-RGB framework that produces task-oriented representations for pretrained vision models.<n>TA-ISP consistently improves downstream accuracy while markedly reducing parameter count and inference time.<n>It is well suited for deployment on resource-constrained devices.
  arXiv  Detail & Related papers  (2025-09-17T07:16:51Z)
• Learned Lightweight Smartphone ISP with Unpaired Data [55.2480439325792]
  We propose a novel training method for a learnable Image Signal Processor (ISP)<n>Our unpaired approach employs a multi-term loss function guided by adversarial training.<n>Compared to paired training methods, our unpaired learning strategy shows strong potential and achieves high fidelity.
  arXiv  Detail & Related papers  (2025-05-15T15:37:51Z)
• Towards Realistic Low-Light Image Enhancement via ISP Driven Data Modeling [61.95831392879045]
  Deep neural networks (DNNs) have recently become the leading method for low-light image enhancement (LLIE)<n>Despite significant progress, their outputs may still exhibit issues such as amplified noise, incorrect white balance, or unnatural enhancements when deployed in real world applications.<n>A key challenge is the lack of diverse, large scale training data that captures the complexities of low-light conditions and imaging pipelines.<n>We propose a novel image signal processing (ISP) driven data synthesis pipeline that addresses these challenges by generating unlimited paired training data.
  arXiv  Detail & Related papers  (2025-04-16T15:53:53Z)
• Beyond RGB: Adaptive Parallel Processing for RAW Object Detection [5.36869872375791]
  Raw Adaptation Module (RAM) is a module designed to replace the traditional Image Signal Processing (ISP)<n>Our approach outperforms RGB-based methods and achieves state-of-the-art results across diverse RAW image datasets.
  arXiv  Detail & Related papers  (2025-03-17T13:36:49Z)
• AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection [15.63212587981912]
  Image Signal Processors (ISPs) convert raw sensor signals into digital images. ISPs are designed to maximize the image quality, which are sub-optimal in the performance of high-level computer vision tasks. We propose AdaptiveISP, a task-driven and scene-adaptive ISP.
  arXiv  Detail & Related papers  (2024-10-30T11:49:06Z)
• RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images [51.68432586065828]
  We introduce RAW-Adapter, a novel approach aimed at adapting sRGB pre-trained models to camera RAW data. Raw-Adapter comprises input-level adapters that employ learnable ISP stages to adjust RAW inputs, as well as model-level adapters to build connections between ISP stages and subsequent high-level networks.
  arXiv  Detail & Related papers  (2024-08-27T06:14:54Z)
• DemosaicFormer: Coarse-to-Fine Demosaicing Network for HybridEVS Camera [70.28702677370879]
  Hybrid Event-Based Vision Sensor (HybridEVS) is a novel sensor integrating traditional frame-based and event-based sensors. Despite its potential, the lack of Image signal processing (ISP) pipeline specifically designed for HybridEVS poses a significant challenge. We propose a coarse-to-fine framework named DemosaicFormer which comprises coarse demosaicing and pixel correction.
  arXiv  Detail & Related papers  (2024-06-12T07:20:46Z)
• Efficient Visual State Space Model for Image Deblurring [99.54894198086852]
  Convolutional neural networks (CNNs) and Vision Transformers (ViTs) have achieved excellent performance in image restoration.<n>We propose a simple yet effective visual state space model (EVSSM) for image deblurring.<n>The proposed EVSSM performs favorably against state-of-the-art methods on benchmark datasets and real-world images.
  arXiv  Detail & Related papers  (2024-05-23T09:13:36Z)
• Multi-scale Semantic Prior Features Guided Deep Neural Network for Urban Street-view Image [1.4473649585131072]
  This paper presents a novel Deep Neural Network (DNN) for inpainting street-view images. A semantic prior prompter is introduced to learn rich semantic priors from large pre-trained model. Experiments on Apolloscapes and Cityscapes datasets demonstrate better performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-17T03:02:18Z)
• Two-shot Spatially-varying BRDF and Shape Estimation [89.29020624201708]
  We propose a novel deep learning architecture with a stage-wise estimation of shape and SVBRDF. We create a large-scale synthetic training dataset with domain-randomized geometry and realistic materials. Experiments on both synthetic and real-world datasets show that our network trained on a synthetic dataset can generalize well to real-world images.
  arXiv  Detail & Related papers  (2020-04-01T12:56:13Z)

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.