{"id":2,"date":"2022-01-07T14:09:41","date_gmt":"2022-01-07T14:09:41","guid":{"rendered":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/?page_id=2"},"modified":"2022-12-16T03:39:42","modified_gmt":"2022-12-16T03:39:42","slug":"our-project","status":"publish","type":"page","link":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/","title":{"rendered":"Capstone Project"},"content":{"rendered":"\n<h1 class=\"wp-block-heading\">Overview<\/h1>\n\n\n\n<p>Given a collection of bokeh images of a <em>static<\/em> scene (shown left), how would we render a new image with a different bokeh setting from the <em>same viewpoint<\/em> (shown right)? <\/p>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\" style=\"flex-basis:100%\">\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-9d6595d7 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"698\" height=\"516\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png\" alt=\"\" class=\"wp-image-144\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png 698w, https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35-300x222.png 300w\" sizes=\"auto, (max-width: 698px) 100vw, 698px\" \/><figcaption>Images captured under different camera settings<\/figcaption><\/figure>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<figure class=\"wp-block-image size-full is-resized\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-36.png\" alt=\"\" class=\"wp-image-146\" width=\"321\" height=\"229\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-36.png 674w, https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-36-300x214.png 300w\" sizes=\"auto, (max-width: 321px) 100vw, 321px\" \/><figcaption>Images generated using new camera settings <\/figcaption><\/figure>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n\n\n\n<p>We answer this common problem in the domain of post-capture image processing through our capstone project. Through this work, we enable <em>re-photography<\/em> using a neural rendering approach.<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">Motivation<\/h1>\n\n\n\n<p>People often capture interesting snapshots of their lives using their smartphones and digital cameras. In the spur of the moment, we might take multiple images focusing on some parts of the scene but later wished that we captured an image focusing on some other part of the scene.<\/p>\n\n\n\n<p>Our project aims to bridge this gap by modeling a subset of camera settings such that we can render images with novel camera settings (focus and aperture).<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">Problem Statement<\/h1>\n\n\n\n<p>Given a bunch of images captured using varying camera settings (focus and aperture), we want to generate images with new values of those settings that still appear photorealistic.<\/p>\n\n\n\n<h1 class=\"wp-block-heading\">Approach<\/h1>\n\n\n\n<p>We first break this problem into two parts &#8211; inverse rendering and forward rendering.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"317\" src=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-1-1024x317.png\" alt=\"\" class=\"wp-image-62\" srcset=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-1-1024x317.png 1024w, https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-1-300x93.png 300w, https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-1-768x238.png 768w, https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-1.png 1430w\" sizes=\"auto, (max-width: 767px) 89vw, (max-width: 1000px) 54vw, (max-width: 1071px) 543px, 580px\" \/><figcaption>High-level pipeline for our approach<\/figcaption><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">Inverse rendering<\/h3>\n\n\n\n<p>From a collection of images given as input,  a neural representation of the scene is built using state-of-the-art approaches in neural rendering. We chose to experiment with two scene representations &#8211; Multi-Plane Images (MPI), a 2.5D representation of the world, and Neural Radiance Fields (NeRF), a continuous 3D representation of the world. Both approaches have their advantages and drawbacks which are explained in the <a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/method\/\">Approach<\/a> section.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Forward rendering<\/h3>\n\n\n\n<p>New images of a scene for a new set of camera settings can be generated from the neural scene representation. In the MPI representation, this can be achieved through multi-ray sampling. In the NeRF setting, volume rendering can be used to generate a new scene image. It is to be noted that in both representations, a thin-lens-based formulation is integrated into the rendering pipelines such that photorealistic defocus effects can be generated.<\/p>\n\n\n\n<p><\/p>\n\n\n\n<p><em>Our code is available at <a href=\"https:\/\/github.com\/nitchith\/Neural-Rephotography\" target=\"_blank\" rel=\"noreferrer noopener\">https:\/\/github.com\/nitchith\/Neural-Rephotography<\/a><\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Overview Given a collection of bokeh images of a static scene (shown left), how would we render a new image with a different bokeh setting from the same viewpoint (shown right)? We answer this common problem in the domain of post-capture image processing through our capstone project. Through this work, we enable re-photography using a &hellip; <\/p>\n<p class=\"link-more\"><a href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Capstone Project&#8221;<\/span><\/a><\/p>\n","protected":false},"author":68,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"open","template":"","meta":{"footnotes":""},"class_list":["post-2","page","type-page","status-publish","hentry"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v27.4 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Capstone Project - Neural Re-Photography<\/title>\n<meta name=\"description\" content=\"Capstone project on modeling a neural camera using computer vision and computational photography.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Capstone Project - Neural Re-Photography\" \/>\n<meta property=\"og:description\" content=\"Capstone project on modeling a neural camera using computer vision and computational photography.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\" \/>\n<meta property=\"og:site_name\" content=\"Neural Re-Photography\" \/>\n<meta property=\"article:modified_time\" content=\"2022-12-16T03:39:42+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"3 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\",\"name\":\"Capstone Project - Neural Re-Photography\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/wp-content\\\/uploads\\\/sites\\\/57\\\/2022\\\/05\\\/image-35.png\",\"datePublished\":\"2022-01-07T14:09:41+00:00\",\"dateModified\":\"2022-12-16T03:39:42+00:00\",\"description\":\"Capstone project on modeling a neural camera using computer vision and computational photography.\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2#primaryimage\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/wp-content\\\/uploads\\\/sites\\\/57\\\/2022\\\/05\\\/image-35.png\",\"contentUrl\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/wp-content\\\/uploads\\\/sites\\\/57\\\/2022\\\/05\\\/image-35.png\",\"width\":698,\"height\":516},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Capstone Project\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/#website\",\"url\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/\",\"name\":\"Neural Re-Photography\",\"description\":\"\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/mscvprojects.ri.cmu.edu\\\/2022team2\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Capstone Project - Neural Re-Photography","description":"Capstone project on modeling a neural camera using computer vision and computational photography.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2","og_locale":"en_US","og_type":"article","og_title":"Capstone Project - Neural Re-Photography","og_description":"Capstone project on modeling a neural camera using computer vision and computational photography.","og_url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2","og_site_name":"Neural Re-Photography","article_modified_time":"2022-12-16T03:39:42+00:00","og_image":[{"url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png","type":"","width":"","height":""}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"3 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2","name":"Capstone Project - Neural Re-Photography","isPartOf":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/#website"},"primaryImageOfPage":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2#primaryimage"},"image":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2#primaryimage"},"thumbnailUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png","datePublished":"2022-01-07T14:09:41+00:00","dateModified":"2022-12-16T03:39:42+00:00","description":"Capstone project on modeling a neural camera using computer vision and computational photography.","breadcrumb":{"@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/mscvprojects.ri.cmu.edu\/2022team2"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2#primaryimage","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png","contentUrl":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-content\/uploads\/sites\/57\/2022\/05\/image-35.png","width":698,"height":516},{"@type":"BreadcrumbList","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/"},{"@type":"ListItem","position":2,"name":"Capstone Project"}]},{"@type":"WebSite","@id":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/#website","url":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/","name":"Neural Re-Photography","description":"","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/pages\/2","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/users\/68"}],"replies":[{"embeddable":true,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/comments?post=2"}],"version-history":[{"count":43,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/pages\/2\/revisions"}],"predecessor-version":[{"id":391,"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/pages\/2\/revisions\/391"}],"wp:attachment":[{"href":"https:\/\/mscvprojects.ri.cmu.edu\/2022team2\/wp-json\/wp\/v2\/media?parent=2"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}