[{"data":1,"prerenderedAt":308},["ShallowReactive",2],{"project-24671259":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":35,"aspects":36,"strip":41,"post_text":44,"what":45,"said":86,"maker_in_thread":170,"shape":180,"grid":184,"attempts":263,"same_week":271,"maker_shows":171,"maker_hidden":300,"reader_version":301,"card":302},"24671259","vision_blender","A computer vision addon for Blender","title","Show HN: I made a computer vision addon for Blender","https:\u002F\u002Fgithub.com\u002FCartucho\u002Fvision_blender","github.com","morroida",1601724290,2020,268,35,167,3028,6,"legend","dev_tools","synthetic data generation addon","library",[24,25,26,27,28],"blender","synthetic data","computer vision","ground truth","stereo depth maps","loved",0.419,{"positive":32,"neutral":33,"mixed":34,"critical":34},8,7,0,15,{"docs":37,"idea":38,"design":40},{"positive":34,"critical":34},{"positive":39,"critical":34},4,{"positive":34,"critical":34},[34,42,34,43,34,34,42,34,42,34,34,34,42,34,34,43,42,42,34,43,42,34,34,34,34,42,34,43,34,43,43,34,34,34,43],5,3,null,{"problem":46,"audience":54,"pricing":44,"motivation":64,"time_to_build":44,"stack":71,"openness":83,"stage":84,"team_size":85},{"value":47,"source":48,"evidence":49},"Generating synthetic ground truth data such as depth maps, masks, normals and optical flow for computer vision","commenter",[50],{"id":51,"by":52,"text":53},"24671535","dr_zoidberg","Ok, this turned out to be far more interesting than the title here reads like. The little abstract at the top is far more informative: > A Blender user-interface to generate…",{"value":55,"source":48,"evidence":56},"Computer vision researchers and practitioners using synthetic data",[57,61],{"id":58,"by":59,"text":60},"24672928","btparker","Excellent! For a while my job entailed this very thing: creating synthetic data for computer vision, and I used Blender as well! You've done a great job.",{"id":62,"by":11,"text":63},"24673352","I agree, these tools should have an official computer vision module since so many people are using synthetic data these days.",{"value":65,"source":66,"evidence":67},"Presented as academic work at MICCAI 2020","maker",[68],{"id":69,"by":11,"text":70},"24672348","So many likes, was not expecting that! I will be presenting this work tomorrow at MICCAI and then I will post my presentation link in the README of the repository!",[72,76],{"value":73,"source":48,"evidence":74},"Blender",[75],{"id":51,"by":52,"text":53},{"value":77,"source":48,"evidence":78},"Python",[79],{"id":80,"by":81,"text":82},"24674799","bluejellybean","Very, very cool work, I fully expect to use this exact project in the future! To those of you who always thought this stuff looked neat but never tried it out, and to those who…","open_source","launched","unknown",{"praise":87,"objections":105,"requests":117,"questions":135,"alternatives":150},[88,97],{"value":89,"source":48,"evidence":90},"Very cool, useful for synthetic computer vision data",[91,92,96],{"id":80,"by":81,"text":82},{"id":93,"by":94,"text":95},"24672223","daenz","Very cool! I've done something similar for improving an OCR system on crinkled paper[0]. Blender is a powerful and totally underutilized tool for this kind of work 0.…",{"id":58,"by":59,"text":60},{"value":98,"source":48,"evidence":99},"Good presentation and clear project",[100,101],{"id":51,"by":52,"text":53},{"id":102,"by":103,"text":104},"24672551","technicolorwhat","What the heck. This is beyond awesome I totally want to try it out",[106],{"value":107,"source":48,"evidence":108},"Term synthetic ground truth seems contradictory",[109,113],{"id":110,"by":111,"text":112},"24675876","tantalor","\"synthetic ground truth\"... isn't that an oxymoron?",{"id":114,"by":115,"text":116},"24676467","notsuoh","Ground truth in this case means images with labels of some sort on parts of the image or objects in the image, not that they're real images themselves. So a cat in a photo with a…",[118,125],{"value":119,"source":48,"evidence":120},"Add a link to the presentation video in the README",[121],{"id":122,"by":123,"text":124},"24685783","punnerud","Love it! Should maybe add a link in addition to the video \"image\". Was not intuitive if it is a an image from a video or a link to a video (I am not used to video \"preview\" on…",{"value":126,"source":48,"evidence":127},"Run as a library instead of inside Blender for speed",[128,132],{"id":129,"by":130,"text":131},"24675336","amelius","One question: why does it need to run inside Blender instead of just using its graphical primitives as a library?",{"id":133,"by":11,"text":134},"24677080","That's a good idea, it would make it faster for sure.",[136,143],{"value":137,"source":48,"evidence":138},"Does synthetic training data introduce problems for real data matching",[139],{"id":140,"by":141,"text":142},"24675848","chrisseaton","Does using synthetic training data introduce any problems? How do you ensure your synthetic data matches real data?",{"value":144,"source":48,"evidence":145},"Is this face motion tracking",[146],{"id":147,"by":148,"text":149},"24675840","DonCopal","Is this face motion tracking using a camera to apply to 3D models?",[151,158,162,166],{"value":152,"source":48,"evidence":153},"BlenderProc",[154],{"id":155,"by":156,"text":157},"24675971","m_ke","A few related projects: - https:\u002F\u002Fgithub.com\u002FDLR-RM\u002FBlenderProc - https:\u002F\u002Fgithub.com\u002Fcheind\u002Fpytorch-blender - https:\u002F\u002Fgithub.com\u002FDIYer22\u002Fbpycv -…",{"value":159,"source":48,"evidence":160},"pytorch-blender",[161],{"id":155,"by":156,"text":157},{"value":163,"source":48,"evidence":164},"bpycv",[165],{"id":155,"by":156,"text":157},{"value":167,"source":48,"evidence":168},"blender-cli-rendering",[169],{"id":155,"by":156,"text":157},{"comments":33,"answered":171,"key":172},1,[173,174,177],{"id":69,"text":70},{"id":175,"text":176},"24680344","done! added to the GitHub README [presentation video](https:\u002F\u002Fimperialcollegelondon.box.com\u002Fs\u002Fcg54pddsf2pkx4ngf4pg96c7o1wm23rx)",{"id":178,"text":179},"24687170","Thank you! Yeah, I found that \"hack\" of the \"image-video\" in StackOverflow. Will add the link too as suggested",{"commenters":181,"max_depth":42,"maker_replies":33,"first_comment_mins":182,"lifespan_hours":183},21,62,51,[185,187,190,192,194,195,197,199,203,205,208,210,213,215,218,220,222,223,226,228,229,231,234,236,239,240,241,244,247,249,251,253,254,256,258],[69,34,34,186,11,171],"maker\u002Fneutral\u002Fnone",[188,34,42,189,123,34],"24674295","maker\u002Fpositive\u002Fnone",[175,34,34,191,11,171],"maker\u002Fneutral\u002Fdocs",[122,34,43,193,123,34],"project\u002Fneutral\u002Fdocs",[178,34,34,191,11,171],[196,34,34,189,11,171],"24680813",[80,171,42,198,81,34],"project\u002Fpositive\u002Fidea",[200,171,34,201,202,34],"24676054","other\u002Fneutral\u002Fnone","canada_dry",[93,204,42,198,94,34],2,[206,204,34,207,11,171],"24672364","commenter\u002Fneutral\u002Fnone",[209,204,34,207,94,34],"24672422",[211,204,34,207,212,34],"24672693","emcq",[102,204,42,214,103,34],"project\u002Fpositive\u002Fnone",[216,204,34,207,217,34],"24672865","modeless",[219,204,34,207,94,34],"24673077",[140,204,43,221,141,34],"project\u002Fneutral\u002Fidea",[51,43,42,198,52,34],[224,39,42,214,225,34],"24672570","doctoboggan",[227,39,34,201,81,34],"24674970",[155,42,43,221,156,34],[230,42,42,198,202,34],"24676012",[232,42,34,207,233,34],"24680312","A-Train",[235,42,34,207,202,34],"24682363",[237,18,34,201,238,34],"24673073","santaclaus",[62,18,34,201,11,171],[58,33,42,189,59,34],[242,32,34,201,243,34],"24671904","blensor",[129,245,43,246,130,34],9,"project\u002Fneutral\u002Fdesign",[133,245,34,248,11,171],"commenter\u002Fneutral\u002Fperformance",[147,250,43,221,148,34],10,[110,252,43,193,111,34],11,[114,252,34,207,115,34],[255,252,34,207,111,34],"24687302",[257,252,34,207,115,34],"24688070",[259,260,43,261,262,34],"24671569",12,"project\u002Fneutral\u002Fnone","tim44",[264,267,270],{"id":265,"t":266,"points":42,"comments":43},"24625105",1601365382,{"id":268,"t":269,"points":171,"comments":34},"24655805",1601583923,{"id":4,"t":12,"points":14,"comments":15},[272,277,282,287,292,296],{"id":273,"name":274,"points":275,"category":276},"24696658","TypeLit",1589,"productivity",{"id":278,"name":279,"points":280,"category":281},"24707407","Buy For Life",1392,"web_saas",{"id":283,"name":284,"points":285,"category":286},"24671525","Igel",405,"ai",{"id":288,"name":289,"points":290,"category":291},"24696145","Plausible",351,"data",{"id":293,"name":294,"points":295,"category":276},"24709393","nb",240,{"id":297,"name":298,"points":299,"category":276},"24690310","Screenbreak",204,false,"v2",{"id":303,"name":5,"line":6,"ai":300,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":304,"top":18,"kw":305,"maker":11,"domain":10,"tier":19,"attempts":43,"strip":306,"url":9,"mix":307,"praise":89,"objection":107,"sub":21},24671259,0.42,[24,25,26,27,28],"05030050500050035503500005030330003",[32,33,34,34],1793991017013]