Light transport as an optimal control problem

dc.contributor.author Zarza Pujol, Mariano
dc.date.accessioned 2021-02-04T07:22:49Z
dc.date.available 2021-02-04T07:22:49Z
dc.date.issued 2021
dc.description Treball fi de màster de: Master in Intelligent Interactive Systemsca
dc.description Tutors: Vicenç Gómez, Gergely Neu
dc.description.abstract Recently, reinforcement learning (RL) has attracted some attention in the research field of physically-based rendering. This thesis explores a deeper connection between both fields. In particular, we identify the light transport equations (LTE) used in physically-based rendering with the Bellman expectation equations used in optimal control. With this identification, we formulate an optimal control problem that can be used for scene rendering based on the framework of linearly-solvable Markov decision processes. This formulation provides a novel perspective on the use of RL techniques for rendering.ca
dc.format.mimetype application/pdf*
dc.identifier.uri http://hdl.handle.net/10230/46325
dc.language.iso engca
dc.rights Reconeixement-NoComercial-SenseObraDerivada 4.0 Internacional (CC BY-NC-ND 4.0)ca
dc.rights.accessRights info:eu-repo/semantics/openAccessca
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/ca
dc.subject.keyword Computer graphics
dc.subject.keyword Optimal control
dc.subject.keyword Light transport
dc.subject.keyword Bellman equation
dc.title Light transport as an optimal control problemca
dc.type info:eu-repo/semantics/masterThesisca

Col·leccions