{"schemaVersion":1,"requestedSlug":"2-5d-parallax","canonicalSlug":"2-5d-parallax","article":"/effect/2-5d-parallax","resource":"/api/public/atlas/effects/2-5d-parallax","effect":{"slide":151,"kind":"historical","decade":"2020s","funFact":"A sideways-moving virtual camera needs image parts that were hidden behind the foreground in the original photo.","body":[{"label":"Identify","text":"A photograph appears to move spatially, even though the depth is limited."},{"label":"Principle","text":"Image planes or depth values are shifted; hidden areas must be filled in."},{"label":"Example","text":"Shih and Team: 3D Photography, CVPR 2020."},{"label":"Try it out","text":"Animate three depth levels at different speeds."}],"caption":"3D Photo Inpainting: two frames from Moon Swing, 2020.","sourceUrl":"https://shihmengli.github.io/3D-Photo-Inpainting/","name":"2.5D parallax / 3D photo","dating":"2020: 3D Photo Inpainting as a research milestone; layer animation older","short":"2.5D parallax","image":"/images/fx/s151.webp","slug":"2-5d-parallax","context":["The term 2.5D describes spatial movement based on limited image and depth information. Manual layer animation is older; the CVPR work by Shih et al. in 2020 serves as a documented milestone. It transforms an RGB-D image into a layered depth representation and adds previously hidden color and depth areas. When the camera is moved laterally, near and far parts shift differently. Where this reveals new background behind a foreground object, information is missing in the original photo. The method estimates these areas. Therefore, pay particular attention to contours in the exercise. Small movements usually work more convincingly because less hidden space needs to be invented."],"distinction":"A depth photograph is not a fully captured three-dimensional object with freely accessible back sides.","aftermath":"Parallax is the relative difference in motion, not a simple zoom. The depth of field must remain plausible so that the subject doesn't appear flat.","question":"Why do gaps appear behind a person when there is too much movement?","answer":"The new view reveals areas that were hidden in the original image and therefore need to be added.","sources":[{"label":"Shih et al.: 3D Photography using Context-aware Layered Depth Inpainting, 2020","url":"https://shihmengli.github.io/3D-Photo-Inpainting/"},{"label":"3D Photo Inpainting: official repository with Moon Swing demo","url":"https://github.com/vt-vl-lab/3d-photo-inpainting"}],"credit":"Meng-Li Shih, Shih-Yang Su, Johannes Kopf and Jia-Bin Huang.","title":"2.5D Parallax","font":"Exo 2","highlights":["appears to move spatially","Image planes or depth values","hidden areas must be filled in"],"margin":[{"term":"Image planes","note":"Flat image layers placed at different simulated distances. Moving them at different rates can suggest depth."},{"term":"depth levels","note":"Groups of image content treated as being at different distances, such as foreground, middle ground, and background."}],"fontWeight":"400","fontCategory":"Sans Serif"},"gallery":[{"src":"/images/gallery/2-5d-parallax-ai2.webp","page":"/images/gallery/2-5d-parallax-ai2.webp","title":"AI illustration: A sequence showing a portrait separated from its background","artist":"Illustration generated for the Atlas (AI)","license":"Atlas illustration","note":"A sequence showing a portrait separated from its background. It illustrates the estimation of occluded areas necessary for spatial movement in 3D photography."},{"src":"/images/gallery/2-5d-parallax-ai3.webp","page":"/images/gallery/2-5d-parallax-ai3.webp","title":"AI illustration: A city skyline divided into three distinct depth planes","artist":"Illustration generated for the Atlas (AI)","license":"Atlas illustration","note":"A city skyline divided into three distinct depth planes. Arrows indicate the varying speeds of movement for each layer to create a spatial effect."},{"src":"/images/gallery/2-5d-parallax-ai6.webp","page":"/images/gallery/2-5d-parallax-ai6.webp","title":"AI illustration: Technical visualization of an RGB-D image and its mesh representation","artist":"Illustration generated for the Atlas (AI)","license":"Atlas illustration","note":"Technical visualization of an RGB-D image and its mesh representation. It shows the depth information used to project and animate a 2.5D scene."},{"src":"/images/gallery/2-5d-parallax-bi4.webp","page":"/images/gallery/2-5d-parallax-bi4.webp","title":"AI illustration: A birthday photo is decomposed into three distinct depth layers along a Z","artist":"Illustration generated for the Atlas (AI)","license":"Atlas illustration","note":"A birthday photo is decomposed into three distinct depth layers along a Z-axis. It clearly demonstrates the technical process of transforming a flat RGB image into a layered depth representation."},{"src":"/images/gallery/2-5d-parallax-ci1.webp","page":"/images/gallery/2-5d-parallax-ci1.webp","title":"AI illustration: A software interface separating a photograph into discrete depth layers","artist":"Illustration generated for the Atlas (AI)","license":"Atlas illustration","note":"The image shows a software interface separating a photograph into discrete depth layers. This visualization demonstrates how 2.5D parallax is achieved by assigning different planes to foreground, midground, and background elements."},{"src":"/images/gallery/2-5d-parallax-di1.webp","page":"/images/gallery/2-5d-parallax-di1.webp","title":"AI illustration: A portrait is split into three physical layers representing foreground, m","artist":"Illustration generated for the Atlas (AI)","license":"Atlas illustration","note":"A portrait is split into three physical layers representing foreground, midground, and background. This depicts the decomposition of a static image into planes for differential shifting."}],"prompt":"Apply a 2.5D Parallax effect as a single layered-depth still, separating foreground, subject, and background into subtly offset planes. Suggest shallow spatial movement through tiny edge reveals, gently differentiated focus, and seamlessly filled background gaps, without obvious collage seams. Keep the original subject and composition."}