[{"data":1,"prerenderedAt":265},["ShallowReactive",2],{"project-6355818":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":34,"aspects":35,"strip":42,"post_text":45,"what":46,"said":99,"maker_in_thread":177,"shape":182,"grid":186,"attempts":226,"same_week":227,"maker_shows":40,"maker_hidden":257,"reader_version":258,"card":259},"6355818","RealityCap","3D sensing SDK for iOS – Produces point cloud and 6DOF device motion","title","Show HN: 3D sensing SDK for iOS – Produces point cloud and 6DOF device motion","http:\u002F\u002Fwww.realitycap.com","realitycap.com","benhirashima",1378757318,2013,42,20,597,1739,35,"shown","dev_tools","computer vision sdk","api",[24,25,26,27,28],"3d sensing","point cloud","slam","ios sdk","6dof motion","mixed",0.286,{"positive":32,"neutral":32,"mixed":33,"critical":33},7,2,18,{"idea":36,"pricing":39,"performance":41},{"positive":37,"critical":38},6,0,{"positive":38,"critical":40},1,{"positive":38,"critical":40},[43,43,40,44,44,44,43,44,44,44,38,43,44,38,44,44,40,43,43,43],5,3,null,{"problem":47,"audience":61,"pricing":72,"motivation":45,"time_to_build":45,"stack":84,"openness":96,"stage":97,"team_size":98},{"value":48,"source":49,"evidence":50},"Capturing 3D measurements and device motion from a phone camera and sensors","inferred",[51,53,57],{"id":52},"post",{"id":54,"by":55,"text":56},"6356459","feniv","Very cool! Can you give a brief overview of the underlying technology you use to extract the distance data back out from a 2D image?",{"id":58,"by":59,"text":60},"6356999","yetanotherphd","I'm fairly sure that the tech is based around \"structure from motion\". The API simultaneously estimates the position of the camera at each point in time, and the location of some…",{"value":62,"source":49,"evidence":63},"Developers building indoor navigation, measurement and AR apps",[64,68],{"id":65,"by":66,"text":67},"6356875","z-e-r-o","Really impressive! Nice name, video, website! However I would strongly recommend picking only one of your \"features\", the indoor navigation. If I were you, I'd definitely try to…",{"id":69,"by":70,"text":71},"6359577","junto","I know of several large companies that would be seriously interested in the measurement feature. Manually measuring the rooms in a house is seriously time consuming.",{"value":73,"source":74,"evidence":75},"Evaluation tier (online only, low API call limit) and enterprise tier by contact; tiers still being defined","commenter",[76,80],{"id":77,"by":78,"text":79},"6357155","eaglej","You make a great point, and we certainly don't want to exclude the in-between cases. We're still figuring out what those pricing tiers might look like, so if you've got an…",{"id":81,"by":82,"text":83},"6356223","chrisdevereux","Looks very cool, but it feels like there's a big gap between Evaluation (online only, low API call limit) and Enterprise (\"contact us\") pricing models. Not sure what market…",[85,90],{"value":86,"source":87,"evidence":88},"iOS","maker",[89],{"id":52},{"value":91,"source":74,"evidence":92},"Structure from motion and SLAM with camera and IMU fusion",[93],{"id":94,"by":78,"text":95},"6357129","You've explained it well! And you're exactly right, thanks to the accelerometer we get distances in real-world units. The trick is very closely integrating computer vision and…","unknown","launched","company",{"praise":100,"objections":118,"requests":142,"questions":155,"alternatives":167},[101,113],{"value":102,"source":74,"evidence":103},"Impressive demo and technology",[104,108,109],{"id":105,"by":106,"text":107},"6356752","rmah","This technology is awesome! If it's half as impressive in real life as the demo suggests you have done a fantastic job creating some really innovative technology. I wish you the…",{"id":65,"by":66,"text":67},{"id":110,"by":111,"text":112},"6357260","cookingrobot","I would love to see this combined with object extraction to make 3d models from the measurements. Here's an amazing demo: http:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Oie1ZXWceqM",{"value":114,"source":74,"evidence":115},"Useful for indoor navigation and room measurement",[116,117],{"id":65,"by":66,"text":67},{"id":69,"by":70,"text":71},[119,123,134],{"value":120,"source":74,"evidence":121},"Pricing gap between evaluation and enterprise tiers",[122],{"id":81,"by":82,"text":83},{"value":124,"source":74,"evidence":125},"Demos are fragile and drift over time in long scans",[126,130],{"id":127,"by":128,"text":129},"6357170","karpathy","These are usually implemented using Structure from Motion techniques, but more specifically in this case SLAM (Simultaneous Localization and Mapping). There are two sources of…",{"id":131,"by":132,"text":133},"6357632","rismay","Very true: \"Be skeptical.\" Also very true: \"Another issue is dealing with drift over time, as errors in estimation build up and if you're scanning the same area your model will…",{"value":135,"source":74,"evidence":136},"Accelerometer too noisy to give absolute distance",[137,138],{"id":58,"by":59,"text":60},{"id":139,"by":140,"text":141},"6357819","sytelus","Accelerators are worthless to measure distances even if they were super precise. This is because you have to do double integration to get distance and the errors only…",[143,148],{"value":144,"source":74,"evidence":145},"Combine with object extraction to make 3D models",[146,147],{"id":110,"by":111,"text":112},{"id":139,"by":140,"text":141},{"value":149,"source":74,"evidence":150},"Video stabilisation use case",[151],{"id":152,"by":153,"text":154},"6356238","dharma1","looks cool. You could probably use this for stabilising video footage",[156,160],{"value":157,"source":74,"evidence":158},"What technology extracts distance from 2D images",[159],{"id":54,"by":55,"text":56},{"value":161,"source":74,"evidence":162},"Is error accumulation small enough for continuous use",[163],{"id":164,"by":165,"text":166},"6357173","jeremyflores","Really amazing product! Is the form on your site the most expedient way to get in touch\u002Fget access to the SDK? Also, is the error accumulation small enough so that you could use…",[168,173],{"value":169,"source":74,"evidence":170},"Structure from motion and SLAM research approaches",[171,172],{"id":58,"by":59,"text":60},{"id":127,"by":128,"text":129},{"value":174,"source":74,"evidence":175},"Apple Core Motion sensor fusion",[176],{"id":131,"by":132,"text":133},{"comments":40,"answered":38,"key":178},[179],{"id":180,"text":181},"6357035","Yep, that's pretty accurate. I'll let our PhD guy come explain a bit more himself. Sorry, we're a bit busy with our exhibit at Disrupt, bit we'll be able to answer more questions…",{"commenters":183,"max_depth":184,"maker_replies":40,"first_comment_mins":185,"lifespan_hours":34},16,4,61,[187,189,190,192,194,196,199,202,204,207,208,210,212,214,217,218,221,223,224,225],[65,38,43,188,66,38],"project\u002Fpositive\u002Fidea",[69,38,43,188,70,38],[81,40,40,191,82,38],"project\u002Fcritical\u002Fpricing",[77,40,44,193,78,38],"maker\u002Fneutral\u002Fpricing",[164,40,44,195,165,38],"project\u002Fneutral\u002Fperformance",[197,40,44,198,78,38],"6357215","maker\u002Fneutral\u002Fnone",[200,40,43,201,82,38],"6360094","project\u002Fpositive\u002Fnone",[54,33,44,203,55,38],"project\u002Fneutral\u002Fidea",[205,33,44,203,206,38],"6356928","woah",[58,33,44,203,59,38],[180,33,38,209,11,40],"maker\u002Fneutral\u002Fidea",[94,33,43,211,78,38],"maker\u002Fpositive\u002Fidea",[139,33,44,213,140,38],"project\u002Fmixed\u002Fperformance",[215,33,38,216,59,38],"6357863","commenter\u002Fneutral\u002Fidea",[127,33,44,213,128,38],[219,33,44,203,220,38],"6357214","iandanforth",[131,33,40,222,132,38],"project\u002Fcritical\u002Fperformance",[105,44,43,188,106,38],[110,184,43,188,111,38],[152,43,43,188,153,38],[],[228,233,238,243,247,252],{"id":229,"name":230,"points":231,"category":232},"6335784","BeeLine Reader",739,"productivity",{"id":234,"name":235,"points":236,"category":237},"6358394","Voxel Quest",203,"games",{"id":239,"name":240,"points":241,"category":242},"6354716","Crime Doesn't Climb",145,"learning_science",{"id":244,"name":245,"points":246,"category":20},"6367635","Mote.io",60,{"id":248,"name":249,"points":250,"category":251},"6355127","bdon.org",58,"infrastructure",{"id":253,"name":254,"points":255,"category":256},"6361318","GoJS",48,"languages",false,"v2",{"id":260,"name":5,"line":6,"ai":257,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":261,"top":18,"kw":262,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":263,"url":9,"mix":264,"praise":102,"objection":120,"sub":21},6355818,0.29,[24,25,26,27,28],"55133353330530331555",[32,32,33,33],1793990897542]