MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding

• URL: http://arxiv.org/abs/2112.05221v1
• Date: Thu, 9 Dec 2021 21:32:10 GMT
• Title: MantissaCam: Learning Snapshot High-dynamic-range Imaging with Perceptually-based In-pixel Irradiance Encoding
• Authors: Haley M. So, Julien N.P. Martel, Piotr Dudek, and Gordon Wetzstein
• Abstract summary: High-dynamic-range ( HDR) images are crucial in many computer vision applications. Here, we design a neural network-based algorithm that outperforms previous irradiance unwrapping methods. We show preliminary results of a prototype MantissaCam implemented with a programmable sensor.
• Score: 39.78877654934457
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The ability to image high-dynamic-range (HDR) scenes is crucial in many computer vision applications. The dynamic range of conventional sensors, however, is fundamentally limited by their well capacity, resulting in saturation of bright scene parts. To overcome this limitation, emerging sensors offer in-pixel processing capabilities to encode the incident irradiance. Among the most promising encoding schemes is modulo wrapping, which results in a computational photography problem where the HDR scene is computed by an irradiance unwrapping algorithm from the wrapped low-dynamic-range (LDR) sensor image. Here, we design a neural network--based algorithm that outperforms previous irradiance unwrapping methods and, more importantly, we design a perceptually inspired "mantissa" encoding scheme that more efficiently wraps an HDR scene into an LDR sensor. Combined with our reconstruction framework, MantissaCam achieves state-of-the-art results among modulo-type snapshot HDR imaging approaches. We demonstrate the efficacy of our method in simulation and show preliminary results of a prototype MantissaCam implemented with a programmable sensor.

Related papers

• Retinex-RAWMamba: Bridging Demosaicing and Denoising for Low-Light RAW Image Enhancement [71.13353154514418]
  Low-light image enhancement, particularly in cross-domain tasks such as mapping from the raw domain to the sRGB domain, remains a significant challenge. We present a novel Mamba scanning mechanism, called RAWMamba, to effectively handle raw images with different CFAs. We also present a Retinex Decomposition Module (RDM) grounded in Retinex prior, which decouples illumination from reflectance to facilitate more effective denoising and automatic non-linear exposure correction.
  arXiv  Detail & Related papers  (2024-09-11T06:12:03Z)
• Towards High-quality HDR Deghosting with Conditional Diffusion Models [88.83729417524823]
  High Dynamic Range (LDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. DNNs still generate ghosting artifacts when LDR images have saturation and large motion. We formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition.
  arXiv  Detail & Related papers  (2023-11-02T01:53:55Z)
• Single Image LDR to HDR Conversion using Conditional Diffusion [18.466814193413487]
  Digital imaging aims to replicate realistic scenes, but Low Dynamic Range (LDR) cameras cannot represent the wide dynamic range of real scenes. This paper presents a deep learning-based approach for recovering intricate details from shadows and highlights. We incorporate a deep-based autoencoder in our proposed framework to enhance the quality of the latent representation of LDR image used for conditioning.
  arXiv  Detail & Related papers  (2023-07-06T07:19:47Z)
• Spatiotemporally Consistent HDR Indoor Lighting Estimation [66.26786775252592]
  We propose a physically-motivated deep learning framework to solve the indoor lighting estimation problem. Given a single LDR image with a depth map, our method predicts spatially consistent lighting at any given image position. Our framework achieves photorealistic lighting prediction with higher quality compared to state-of-the-art single-image or video-based methods.
  arXiv  Detail & Related papers  (2023-05-07T20:36:29Z)
• Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks [35.532434169432776]
  We propose a lightweight two-stage image enhancement algorithm sequentially balancing illumination and noise removal. We also propose a Fourier spectrum-based adversarial framework (AFNet) for consistent image enhancement under varying illumination conditions. Based on quantitative and qualitative evaluations, we also examine the practicality and effects of image enhancement techniques on the performance of common perception tasks.
  arXiv  Detail & Related papers  (2022-04-04T18:48:51Z)
• Video Reconstruction from a Single Motion Blurred Image using Learned Dynamic Phase Coding [34.76550131783525]
  We propose a hybrid optical-digital method for video reconstruction using a single motion-blurred image. We use a learned dynamic phase-coding in the lens aperture during the image acquisition to encode the motion trajectories. The proposed computational camera generates a sharp frame burst of the scene at various frame rates from a single coded motion-blurred image.
  arXiv  Detail & Related papers  (2021-12-28T02:06:44Z)
• RBSRICNN: Raw Burst Super-Resolution through Iterative Convolutional Neural Network [23.451063587138393]
  We propose a Raw Burst Super-Resolution Iterative Convolutional Neural Network (RBSRICNN) The proposed network produces the final output by an iterative refinement of the intermediate SR estimates. We demonstrate the effectiveness of our proposed approach in quantitative and qualitative experiments.
  arXiv  Detail & Related papers  (2021-10-25T19:01:28Z)
• Thermal Image Processing via Physics-Inspired Deep Networks [21.094006629684376]
  DeepIR combines physically accurate sensor modeling with deep network-based image representation. DeepIR requires neither training data nor periodic ground-truth calibration with a known black body target. Simulated and real data experiments demonstrate that DeepIR can perform high-quality non-uniformity correction with as few as three images.
  arXiv  Detail & Related papers  (2021-08-18T04:57:48Z)
• Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline [100.5353614588565]
  We propose to incorporate the domain knowledge of the LDR image formation pipeline into our model. We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization. We demonstrate that the proposed method performs favorably against state-of-the-art single-image HDR reconstruction algorithms.
  arXiv  Detail & Related papers  (2020-04-02T17:59:04Z)
• Deep Blind Video Super-resolution [85.79696784460887]
  We propose a deep convolutional neural network (CNN) model to solve video SR by a blur kernel modeling approach. The proposed CNN model consists of motion blur estimation, motion estimation, and latent image restoration modules. We show that the proposed algorithm is able to generate clearer images with finer structural details.
  arXiv  Detail & Related papers  (2020-03-10T13:43:24Z)

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.