# Task-Aware Image Signal Processor for Advanced Visual Perception

arXiv: https://arxiv.org/abs/2509.13762 · HTML: https://mlsanity.com/paper/2509.13762/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Replacing Mobile Camera ISP with a Single Deep Learning Model](https://mlsanity.com/paper/2002.05509/) (2020)
- [DeepISP: Towards Learning an End-to-End Image Processing Pipeline](https://mlsanity.com/paper/1801.06724/) (2018)
- [AIM 2020 Challenge on Learned Image Signal Processing Pipeline](https://mlsanity.com/paper/2011.04994/) (2020)
- [Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision](https://mlsanity.com/paper/2108.08119/) (2021)
- [Model-Based Image Signal Processors via Learnable Dictionaries](https://mlsanity.com/paper/2201.03210/) (2022)
- [Dirty Pixels: Towards End-to-End Image Processing and Perception](https://mlsanity.com/paper/1701.06487/) (2017)
- [CameraNet: A Two-Stage Framework for Effective Camera ISP Learning](https://mlsanity.com/paper/1908.01481/) (2019)
- [ParamISP: Learned Forward and Inverse ISPs using Camera Parameters](https://mlsanity.com/paper/2312.13313/) (2023)
- [Automatic ISP image quality tuning using non-linear optimization](https://mlsanity.com/paper/1902.09023/) (2019)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [VisionISP: Repurposing the Image Signal Processor for Computer Vision Applications](https://mlsanity.com/paper/1911.05931/) (2019)
- [Learning Degradation-Independent Representations for Camera ISP Pipelines](https://mlsanity.com/paper/2307.00761/) (2023)

## Built on by (most cited first, 2 of 2)

- [POS-ISP: Pipeline Optimization at the Sequence Level for Task-aware ISP](https://mlsanity.com/paper/2604.06938/) (2026)
- [RawVLA: Embodied Neural Image Signal Processor For Robotic Manipulation](https://mlsanity.com/paper/2609.37530/) (2026)

## Abstract (arXiv)

In recent years, there has been a growing trend in computer vision towards exploiting RAW sensor data, which preserves richer information compared to conventional low-bit RGB images. Early studies mainly focused on enhancing visual quality, while more recent efforts aim to leverage the abundant information in RAW data to improve the performance of visual perception tasks such as object detection and segmentation. However, existing approaches still face two key limitations: large-scale ISP networks impose heavy computational overhead, while methods based on tuning traditional ISP pipelines are restricted by limited representational capacity.To address these issues, we propose Task-Aware Image Signal Processing (TA-ISP), a compact RAW-to-RGB framework that produces task-oriented representations for pretrained vision models. Instead of heavy dense convolutional pipelines, TA-ISP predicts a small set of lightweight, multi-scale modulation operators that act at global, regional, and pixel scales to reshape image statistics across different spatial extents. This factorized control significantly expands the range of spatially varying transforms that can be represented while keeping memory usage, computation, and latency tightly constrained. Evaluated on several RAW-domain detection and segmentation benchmarks under both daytime and nighttime conditions, TA-ISP consistently improves downstream accuracy while markedly reducing parameter count and inference time, making it well suited for deployment on resource-constrained devices.