Related papers: ParamISP: Learned Forward and Inverse ISPs using C…
Autonomous driving algorithms usually employ sRGB images as model input due to their compatibility with the human visual system. However, visually pleasing sRGB images are possibly sub-optimal for downstream tasks when compared to RAW…
Object detection models are typically applied to standard RGB images processed through Image Signal Processing (ISP) pipelines, which are designed to enhance sensor-captured RAW images for human vision. However, these ISP functions can lead…
As the revolutionary improvement being made on the performance of smartphones over the last decade, mobile photography becomes one of the most common practices among the majority of smartphone users. However, due to the limited size of…
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…
This paper presents a modular neural image signal processing (ISP) framework that processes raw inputs and renders high-quality display-referred images. Unlike prior neural ISP designs, our method introduces a high degree of modularity,…
Traditional image signal processing (ISP) pipeline consists of a set of individual image processing components onboard a camera to reconstruct a high-quality sRGB image from the sensor raw data. Due to the hand-crafted nature of the ISP…
Image signal processors (ISPs) are historically grown legacy software systems for reconstructing color images from noisy raw sensor measurements. They are usually composited of many heuristic blocks for denoising, demosaicking, and color…
Image Signal Processors (ISPs) convert raw sensor signals into digital images, which significantly influence the image quality and the performance of downstream computer vision tasks. Designing ISP pipeline and tuning ISP parameters are two…
With the advent of deep learning methods replacing the ISP in transforming sensor RAW readings into RGB images, numerous methodologies solidified into real-life applications. Equally potent is the task of inverting this process which will…
The deep learning (DL)-based methods of low-level tasks have many advantages over the traditional camera in terms of hardware prospects, error accumulation and imaging effects. Recently, the application of deep learning to replace the image…
Deep learning-based ISP algorithms have demonstrated significant potential in raw2rgb reconstruction. However, existing networks have not fully considered the specific characteristics of raw data, such as black level and CFA, which can…
Event-guided imaging has received significant attention due to its potential to revolutionize instant imaging systems. However, the prior methods primarily focus on enhancing RGB images in a post-processing manner, neglecting the challenges…
RGB-to-RAW reconstruction, or the reverse modeling of a camera Image Signal Processing (ISP) pipeline, aims to recover high-fidelity RAW data from RGB images. Despite notable progress, existing learning-based methods typically treat this…
In the computer vision community, the preference for pre-training visual models has largely shifted toward sRGB images due to their ease of acquisition and compact storage. However, camera RAW images preserve abundant physical details…
The success of deep denoisers on real-world color photographs usually relies on the modeling of sensor noise and in-camera signal processing (ISP) pipeline. Performance drop will inevitably happen when the sensor and ISP pipeline of test…
As the popularity of mobile photography is growing constantly, lots of efforts are being invested now into building complex hand-crafted camera ISP solutions. In this work, we demonstrate that even the most sophisticated ISP pipelines can…
The image acquisition parameters (IAPs) used to create MRI scans are central to defining the appearance of the images. Deep learning models trained on data acquired using certain parameters might not generalize well to images acquired with…
Image pyramids are commonly used in modern computer vision tasks to obtain multi-scale features for precise understanding of images. However, image pyramids process multiple resolutions of images using the same large-scale model, which…
Low-light Object detection is crucial for many real-world applications but remains challenging due to degraded image quality. While recent studies have shown that RAW images offer superior potential over RGB images, existing approaches…
Numerous low-level vision tasks operate in the RAW domain due to its linear properties, bit depth, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public sRGB…