{"id":2075,"date":"2022-04-25T15:50:22","date_gmt":"2022-04-25T15:50:22","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2022\/04\/25\/let-me-shoyu-how-its-done-creating-the-nvidia-omniverse-ramen-shop\/"},"modified":"2022-04-25T15:50:22","modified_gmt":"2022-04-25T15:50:22","slug":"let-me-shoyu-how-its-done-creating-the-nvidia-omniverse-ramen-shop","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2022\/04\/25\/let-me-shoyu-how-its-done-creating-the-nvidia-omniverse-ramen-shop\/","title":{"rendered":"Let Me Shoyu How It\u2019s Done: Creating the NVIDIA Omniverse Ramen Shop"},"content":{"rendered":"<div data-url=\"https:\/\/blogs.nvidia.com\/blog\/2022\/04\/25\/making-of-omniverse-ramen-shop\/\" data-title=\"Let Me Shoyu How It\u2019s Done: Creating the NVIDIA Omniverse Ramen Shop\" data-hashtags=\"\">\n<p>When brainstorming a scene to best showcase the groundbreaking capabilities of the <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/\" target=\"_blank\" rel=\"noopener\">Omniverse<\/a> platform, some NVIDIA artists turned to a cherished memory: enjoying ramen together in a mom-and-pop shop down a side street in Tokyo.<\/p>\n<p>Simmering pots of noodles, steaming dumplings, buzzing kitchen appliances, warm ambient lighting and glistening black ledger stools. These were all simulated in a true-to-reality virtual world by nearly two dozen NVIDIA artists and freelancers across the globe using NVIDIA Omniverse, a <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/solutions\/3d-design-collaboration\/\" target=\"_blank\" rel=\"noopener\">3D design collaboration<\/a> and world simulation platform.<\/p>\n<p>The final scene \u2014 consisting of over 22 million triangles, 350 unique textured models and 3,000 4K-resolution texture maps \u2014 welcomes viewers into a virtual ramen shop featured in last month\u2019s <a href=\"https:\/\/www.nvidia.com\/gtc\/keynote\/\" target=\"_blank\" rel=\"noopener\">GTC keynote address<\/a> by NVIDIA founder and CEO Jensen Huang.<\/p>\n<\/p>\n<p>The mouth-watering demo was created to highlight the NVIDIA RTX-powered real-time rendering and physics simulation capabilities of Omniverse, which scales performance and speed when running on multiple GPUs.<\/p>\n<p>It\u2019s a feast for the eyes, as all of the demo\u2019s parts are physically accurate and photorealistic, from the kitchen appliances and order slips; to the shoyu ramen and chashu pork; to the stains on the pots and pans.<\/p>\n<p>\u201cOur team members were hungry just looking at the renders,\u201d said Andrew Averkin, senior art manager and lead environment artist at NVIDIA, in a GTC session offering a behind-the-scenes look at the making of the Omniverse ramen shop.<\/p>\n<p>The session \u2014 presented by Averkin and Gabriele Leone, senior art director at NVIDIA \u2014 is now available <a href=\"https:\/\/www.nvidia.com\/en-us\/on-demand\/session\/gtcspring22-s42109\/\" target=\"_blank\" rel=\"noopener\">on demand<\/a>.<\/p>\n<h2><b>Gathering the Ingredients for Reference<\/b><\/h2>\n<p>The team\u2019s first step was to gather the artistic ingredients: visual references on which to base the 3D models and props for the scene.<\/p>\n<p>An NVIDIA artist traveled to a real ramen restaurant in Tokyo and collected over 2,000 high-resolution reference images and videos, each capturing aspects from the kitchen\u2019s distinct areas for cooking, cleaning, food preparation and storage.<\/p>\n<p>Then, props artists modeled and textured 3D assets for all of the shop\u2019s items, from the stoves and fridges to gas pipes and power plugs. Even the nutrition labels on bottled drinks and the buttons for the ticket machine from which visitors order meals were precisely replicated.<\/p>\n<figure id=\"attachment_56705\" aria-describedby=\"caption-attachment-56705\" class=\"wp-caption aligncenter\">\n<p><img decoding=\"async\" loading=\"lazy\" src=\"https:\/\/blogs.nvidia.com\/wp-content\/uploads\/2022\/04\/drinks-in-fridge-672x378.png\" alt=\"\" width=\"672\" height=\"378\"><figcaption id=\"caption-attachment-56705\" class=\"wp-caption-text\">Drinks in a fridge at the virtual ramen shop, made using Omniverse Create, Adobe Substance 3D Painter, Autodesk 3ds Max, Blender, Maxon Cinema 4D, and RizomUV.<\/figcaption><\/figure>\n<p>In just two months, NVIDIA artists across the world modeled 350 unique props for the scene, using a range of design software including Autodesk Maya, Autodesk 3ds Max, Blender, Maxon Cinema 4D and Pixologic Zbrush. Omniverse Connectors and Pixar\u2019s <a href=\"https:\/\/developer.nvidia.com\/usd\" target=\"_blank\" rel=\"noopener\">Universal Scene Description<\/a> format enabled the models to be seamlessly brought into the <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/apps\/create\/\" target=\"_blank\" rel=\"noopener\">Omniverse Create<\/a> app.<\/p>\n<p>\u201cThe best way to think about Omniverse Create is to consider it a world-building tool,\u201d Leone said. \u201cIt works with <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/#apps-connectors\" target=\"_blank\" rel=\"noopener\">Omniverse Connectors<\/a>, which allow artists to use whichever third-party apps they\u2019re familiar with and connect their work seamlessly in Omniverse \u2014 taking creativity and experimentation to new levels.\u201d<\/p>\n<h2><b>Adding Lighting and Texture Garnishes\u00a0<\/b><\/h2>\n<p>Artists then used Adobe Substance Painter to texture the materials. To make the props look used on a daily basis, the team whipped up details like dents on wooden counters, stickers peeling off appliances and sauce stains on pots.<\/p>\n<p>\u201cSome of our artists went as far as cooking some of the recipes themselves and taking references of their own pots to get a good idea of how sauce or burn stains might accumulate,\u201d Averkin said.<\/p>\n<p>Omniverse\u2019s simulation capabilities enable light to reflect off of glass and other materials with true-to-reality physical accuracy. Plus, real-time photorealistic lighting rendered in 4K resolution created an orange warmth inside the cozy virtual shop, contrasting the rainy atmosphere that can be seen through the windows.<\/p>\n<p>Artists used <a href=\"https:\/\/docs.omniverse.nvidia.com\/prod_extensions\/prod_extensions\/ext_fluid-dynamics.html\" target=\"_blank\" rel=\"noopener\">Omniverse Flow<\/a>, a fluid simulation <a href=\"https:\/\/docs.omniverse.nvidia.com\/prod_extensions\/prod_extensions\/overview.html\" target=\"_blank\" rel=\"noopener\">Omniverse Extension<\/a> for smoke and fire, to bring the restaurant\u2019s burning stoves and steaming plates to life. SideFX Houdini software helped to animate the boiling water, which was eventually brought into the virtual kitchen using an Omniverse Connector.<\/p>\n<figure id=\"attachment_56709\" aria-describedby=\"caption-attachment-56709\" class=\"wp-caption aligncenter\">\n<p><img decoding=\"async\" loading=\"lazy\" src=\"https:\/\/blogs.nvidia.com\/wp-content\/uploads\/2022\/04\/boiling-water-672x378.png\" alt=\"\" width=\"672\" height=\"378\"><figcaption id=\"caption-attachment-56709\" class=\"wp-caption-text\">Broth boils in the virtual kitchen using visual effects offered by Houdini software.<\/figcaption><\/figure>\n<p>And Omniverse Create\u2019s camera animation feature allowed the artists to capture the final <a href=\"https:\/\/blogs.nvidia.com\/blog\/2022\/03\/23\/what-is-path-tracing\/\" target=\"_blank\" rel=\"noopener\">path-traced<\/a> scene in real time, exactly as observed through the viewport.<\/p>\n<figure id=\"attachment_56712\" aria-describedby=\"caption-attachment-56712\" class=\"wp-caption aligncenter\">\n<p><img decoding=\"async\" loading=\"lazy\" src=\"https:\/\/blogs.nvidia.com\/wp-content\/uploads\/2022\/04\/ramen-shop-672x378.jpg\" alt=\"\" width=\"672\" height=\"378\"><figcaption id=\"caption-attachment-56712\" class=\"wp-caption-text\">Photorealistic lighting illuminates the virtual ramen shop, enabled by NVIDIA RTX-based ray tracing and path tracing.<\/figcaption><\/figure>\n<p>Learn more about Omniverse by watching additional <a href=\"https:\/\/www.nvidia.com\/en-us\/on-demand\/playlist\/playList-1ac7f8b5-386b-414c-95ce-f09901382dbd\/\" target=\"_blank\" rel=\"noopener\">GTC sessions on demand<\/a> \u2014 featuring visionaries from the Omniverse team, Adobe, Autodesk, Epic Games, Pixar, Unity and Walt Disney Studios.<\/p>\n<h2><b>Join in on the Creation<\/b><\/h2>\n<p>Creators across the world can <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/creators\/\" target=\"_blank\" rel=\"noopener\">download NVIDIA Omniverse for free<\/a>, and <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/enterprise\/\" target=\"_blank\" rel=\"noopener\">enterprise teams<\/a> can use the platform for their 3D projects.<\/p>\n<p>Join the <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/machinima-contest\/\" target=\"_blank\" rel=\"noopener\">#MadeInMachinima contest<\/a>, running through June 27, for a chance to win the latest <a href=\"https:\/\/www.nvidia.com\/en-us\/studio\/\" target=\"_blank\" rel=\"noopener\">NVIDIA Studio<\/a> laptop.<\/p>\n<p>Connect your workflows to Omniverse with software from Adobe, Autodesk, Epic Games, Maxon, Reallusion <a href=\"https:\/\/www.nvidia.com\/en-us\/omniverse\/#apps-connectors\" target=\"_blank\" rel=\"noopener\">and more<\/a>.<\/p>\n<p><i>Follow<\/i><i> Omniverse on <\/i><a href=\"https:\/\/www.instagram.com\/nvidiaomniverse\/\" target=\"_blank\" rel=\"nofollow noopener\"><i>Instagram<\/i><\/a><i>, <\/i><a href=\"https:\/\/twitter.com\/nvidiaomniverse\" target=\"_blank\" rel=\"nofollow noopener\"><i>Twitter<\/i><\/a><i>, <\/i><a href=\"https:\/\/www.youtube.com\/channel\/UCSKUoczbGAcMld7HjpCR8OA\" target=\"_blank\" rel=\"nofollow noopener\"><i>YouTube<\/i><\/a><i> and <\/i><a href=\"https:\/\/medium.com\/@nvidiaomniverse\" target=\"_blank\" rel=\"nofollow noopener\"><i>Medium<\/i><\/a><i> for additional resources and inspiration. Check out the Omniverse <\/i><a href=\"https:\/\/forums.developer.nvidia.com\/c\/omniverse\/300\" target=\"_blank\" rel=\"nofollow noopener\"><i>forums<\/i><\/a><i> and join our <\/i><a href=\"https:\/\/discord.com\/invite\/XWQNJDNuaC\" target=\"_blank\" rel=\"nofollow noopener\"><i>Discord Server<\/i><\/a><i> to chat with the community.<\/i><\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"<p>https:\/\/blogs.nvidia.com\/blog\/2022\/04\/25\/making-of-omniverse-ramen-shop\/<\/p>\n","protected":false},"author":0,"featured_media":2076,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/2075"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=2075"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/2075\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/2076"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=2075"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=2075"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=2075"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}