{"version": "1.0", "type": "rich", "title": "Casual 3D Photography\n Research from\nPeter Hedman\n\n and Facebook on method to create photography with depth using a standard...", "author_name": "kontextmaschine", "author_url": "https://kontextmaschine.com", "provider_name": "kontextmaschine", "provider_url": "https://kontextmaschine.com", "url": "https://kontextmaschine.com/post/165561196578/", "html": "<p><a href=\"http://prostheticknowledge.tumblr.com/post/165557900596/casual-3d-photography-research-from-peter-hedman\" class=\"tumblr_blog\" target=\"_blank\">prostheticknowledge</a>:</p><blockquote>\n<h2>\nCasual 3D Photography</h2>\n<p>Research from\n<a href=\"http://phogzone.com/\" title=\"Peter Hedman\" target=\"_blank\">Peter Hedman</a>\n\n and Facebook on method to create photography with depth using a standard single cameras:</p>\n<figure class=\"tmblr-embed tmblr-full\" data-provider=\"youtube\" data-orig-width=\"540\" data-orig-height=\"304\" data-url=\"https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3DwGBistgOsyQ\"><iframe id=\"youtube_iframe\" src=\"https://www.youtube.com/embed/wGBistgOsyQ?feature=oembed&amp;enablejsapi=1&amp;origin=https://safe.txmblr.com&amp;wmode=opaque\" allowfullscreen=\"\" width=\"540\" height=\"304\" frameborder=\"0\"></iframe></figure><blockquote>\n<p>We present an algorithm that enables casual 3D \nphotography. Given a set of input photos captured with a hand-held cell \nphone or DSLR camera, our algorithm reconstructs a 3D photo, a central \npanoramic, textured, normal mapped, multi-layered geometric mesh \nrepresentation. 3D photos can be stored compactly and are optimized for \nbeing rendered from viewpoints that are near the capture viewpoints. \nThey can be rendered using a standard rasterization pipeline to produce \nperspective views with motion parallax. When viewed in VR, 3D photos \nprovide geometrically consistent views for both eyes. Our geometric \nrepresentation also allows interacting with the scene using 3D \ngeometry-aware effects, such as adding new objects to the scene and \nartistic lighting effects.</p>\n<p>Our 3D photo reconstruction algorithm starts \nwith a standard structure from motion and multi-view stereo \nreconstruction of the scene. The dense stereo reconstruction is made \nrobust to the imperfect capture conditions using a novel near envelope \ncost volume prior that discards erroneous near depth hypotheses. We \npropose a novel parallax-tolerant stitching algorithm that warps the \ndepth maps into the central panorama and stitches two color-and-depth \npanoramas for the front and back scene surfaces. The two panoramas are \nfused into a single non-redundant, well-connected geometric mesh. We \nprovide videos demonstrating users interactively viewing and \nmanipulating our 3D photos.</p>\n</blockquote>\n<p><a href=\"http://visual.cs.ucl.ac.uk/pubs/casual3d/\" target=\"_blank\">More Here</a><br/></p>\n</blockquote>\n<img src=\"/media/tumblr_owli84FJZX1qav3uso1_540_72a840c6f851.gif\" />\n<img src=\"/media/tumblr_owli84FJZX1qav3uso3_r1_540_8397b7a5613a.gif\" />\n<img src=\"/media/tumblr_owli84FJZX1qav3uso2_r2_540_c03024e7239f.gif\" />\n<img src=\"/media/tumblr_owli84FJZX1qav3uso4_r1_540_357663040b1b.gif\" />\n<img src=\"/media/tumblr_owli84FJZX1qav3uso5_r1_540_7442e60121cb.gif\" />", "thumbnail_url": "https://kontextmaschine.com/media/tumblr_owli84FJZX1qav3uso1_540_72a840c6f851.gif", "thumbnail_width": 540, "thumbnail_height": 304}