RealityCap
Dev tools
computer vision sdk
SHOW HN2013
How HN took it
7 positive, 7 neutral or asking, 2 mixed, 2 critical, out of 18 comments about the project. Thread score +0.29.
Idea: 6 for, 0 againstPricing: 0 for, 1 againstPerformance: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Impressive demo and technology
From 3 comments
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…
rmah on HNReally 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…
z-e-r-o on HNI would love to see this combined with object extraction to make 3d models from the measurements. Here's an amazing demo: http://www.youtube.com/watch?v=Oie1ZXWceqM
cookingrobot on HN
Useful for indoor navigation and room measurement
From 2 comments
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…
z-e-r-o on HNI 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.
junto on HN
Objections
Pricing gap between evaluation and enterprise tiers
From 1 comment
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…
chrisdevereux on HN
Demos are fragile and drift over time in long scans
From 2 comments
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…
karpathy on HNVery 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…
rismay on HN
Accelerometer too noisy to give absolute distance
From 2 comments
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…
yetanotherphd on HNAccelerators 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…
sytelus on HN
Requests
Combine with object extraction to make 3D models
From 2 comments
I would love to see this combined with object extraction to make 3d models from the measurements. Here's an amazing demo: http://www.youtube.com/watch?v=Oie1ZXWceqM
cookingrobot on HNAccelerators 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…
sytelus on HN
Video stabilisation use case
From 1 comment
looks cool. You could probably use this for stabilising video footage
dharma1 on HN
Questions
What technology extracts distance from 2D images
From 1 comment
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?
feniv on HN
Is error accumulation small enough for continuous use
From 1 comment
Really amazing product! Is the form on your site the most expedient way to get in touch/get access to the SDK? Also, is the error accumulation small enough so that you could use…
jeremyflores on HN
Alternatives named
Structure from motion and SLAM research approaches
From 2 comments
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…
yetanotherphd on HNThese are usually implemented using Structure from Motion techniques, but more specifically in this case SLAM (Simultaneous Localization and Mapping). There are two sources of…
karpathy on HN
Apple Core Motion sensor fusion
From 1 comment
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…
rismay on HN