000131652 001__ 131652
000131652 005__ 20241125101141.0
000131652 0247_ $$2doi$$a10.1145/3618367
000131652 0248_ $$2sideral$$a137230
000131652 037__ $$aART-2023-137230
000131652 041__ $$aeng
000131652 100__ $$aWang, Chao
000131652 245__ $$aAn Implicit Neural Representation for the Image Stack: Depth, All in Focus, and High Dynamic Range
000131652 260__ $$c2023
000131652 5060_ $$aAccess copy available to the general public$$fUnrestricted
000131652 5203_ $$aIn everyday photography, physical limitations of camera sensors and lenses frequently lead to a variety of degradations in captured images such as saturation or defocus blur. A common approach to overcome these limitations is to resort to image stack fusion, which involves capturing multiple images with different focal distances or exposures. For instance, to obtain an all-in-focus image, a set of multi-focus images is captured. Similarly, capturing multiple exposures allows for the reconstruction of high dynamic range. In this paper, we present a novel approach that combines neural fields with an expressive camera model to achieve a unified reconstruction of an all-in-focus high-dynamic-range image from an image stack. Our approach is composed of a set of specialized implicit neural representations tailored to address specific sub-problems along our pipeline: We use neural implicits to predict flow to overcome misalignments arising from lens breathing, depth, and all-in-focus images to account for depth of field, as well as tonemapping to deal with sensor responses and saturation - all trained using a physically inspired supervision structure with a differentiable thin lens model at its core. An important benefit of our approach is its ability to handle these tasks simultaneously or independently, providing flexible post-editing capabilities such as refocusing and exposure adjustment. By sampling the three primary factors in photography within our framework (focal distance, aperture, and exposure time), we conduct a thorough exploration to gain valuable insights into their significance and impact on overall reconstruction quality. Through extensive validation, we demonstrate that our method outperforms existing approaches in both depth-from-defocus and all-in-focus image reconstruction tasks. Moreover, our approach exhibits promising results in each of these three dimensions, showcasing its potential to enhance captured image quality and provide greater control in post-processing.
000131652 536__ $$9info:eu-repo/grantAgreement/ES/AEI/PID2022-141539NB-I00
000131652 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttp://creativecommons.org/licenses/by/3.0/es/
000131652 590__ $$a7.8$$b2023
000131652 592__ $$a7.766$$b2023
000131652 591__ $$aCOMPUTER SCIENCE, SOFTWARE ENGINEERING$$b5 / 132 = 0.038$$c2023$$dQ1$$eT1
000131652 593__ $$aComputer Graphics and Computer-Aided Design$$c2023$$dQ1
000131652 594__ $$a14.3$$b2023
000131652 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000131652 700__ $$0(orcid)0000-0002-7796-3177$$aSerrano, Ana$$uUniversidad de Zaragoza
000131652 700__ $$aPan, Xingang
000131652 700__ $$aWolski, Krzysztof
000131652 700__ $$aChen, Bin
000131652 700__ $$aMyszkowski, Karol
000131652 700__ $$aSeidel, Hans-Peter
000131652 700__ $$aTheobalt, Christian
000131652 700__ $$aLeimkühler, Thomas
000131652 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000131652 773__ $$g42, 6 (2023), 1-11$$pACM trans. graph.$$tACM TRANSACTIONS ON GRAPHICS$$x0730-0301
000131652 8564_ $$s1329249$$uhttps://zaguan.unizar.es/record/131652/files/texto_completo.pdf$$yVersión publicada
000131652 8564_ $$s2644303$$uhttps://zaguan.unizar.es/record/131652/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000131652 909CO $$ooai:zaguan.unizar.es:131652$$particulos$$pdriver
000131652 951__ $$a2024-11-22-12:02:37
000131652 980__ $$aARTICLE