000168093 001__ 168093
000168093 005__ 20260126155509.0
000168093 0247_ $$2doi$$a10.1007/978-3-031-43999-5_48
000168093 0248_ $$2sideral$$a147676
000168093 037__ $$aART-2023-147676
000168093 041__ $$aeng
000168093 100__ $$0(orcid)0000-0002-6837-934X$$aBatlle, Víctor M.$$uUniversidad de Zaragoza
000168093 245__ $$aLightNeuS: Neural Surface Reconstruction in Endoscopy Using Illumination Decline
000168093 260__ $$c2023
000168093 5203_ $$aWe propose a new approach to 3D reconstruction from sequences of images acquired by monocular endoscopes. It is based on two key insights. First, endoluminal cavities are watertight, a property naturally enforced by modeling them in terms of a signed distance function. Second, the scene illumination is variable. It comes from the endoscope’s light sources and decays with the inverse of the squared distance to the surface. To exploit these insights, we build on NeuS [25], a neural implicit surface reconstruction technique with an outstanding capability to learn appearance and a SDF surface model from multiple views, but currently limited to scenes with static illumination. To remove this limitation and exploit the relation between pixel brightness and depth, we modify the NeuS architecture to explicitly account for it and introduce a calibrated photometric model of the endoscope’s camera and light source.
Our method is the first one to produce watertight reconstructions of whole colon sections. We demonstrate excellent accuracy on phantom imagery. Remarkably, the watertight prior combined with illumination decline, allows to complete the reconstruction of unseen portions of the surface with acceptable accuracy, paving the way to automatic quality assessment of cancer screening explorations, measuring the global percentage of observed mucosa.
000168093 540__ $$9info:eu-repo/semantics/closedAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000168093 592__ $$a0.606$$b2023
000168093 593__ $$aTheoretical Computer Science$$c2023$$dQ2
000168093 593__ $$aComputer Science (miscellaneous)$$c2023$$dQ2
000168093 594__ $$a2.6$$b2023
000168093 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000168093 700__ $$0(orcid)0000-0002-3627-7306$$aMontiel, José M. M.$$uUniversidad de Zaragoza
000168093 700__ $$aFua, Pascal
000168093 700__ $$0(orcid)0000-0002-4518-5876$$aTardós, Juan D.$$uUniversidad de Zaragoza
000168093 7102_ $$15007$$2520$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Ingen.Sistemas y Automát.
000168093 773__ $$g(2023), 502-512$$pLect. notes comput. sci.$$tLecture Notes in Computer Science$$x0302-9743
000168093 8564_ $$s661143$$uhttps://zaguan.unizar.es/record/168093/files/texto_completo.pdf$$yVersión publicada
000168093 8564_ $$s1517359$$uhttps://zaguan.unizar.es/record/168093/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000168093 909CO $$ooai:zaguan.unizar.es:168093$$particulos$$pdriver
000168093 951__ $$a2026-01-26-14:50:21
000168093 980__ $$aARTICLE