[jboy]

Nice work! My startup http://objectai.com/ has just launched something similar, Pizza Photo Editor: https://pizza.pics/

Pizza Photo Editor is still early-stage -- we're still adding features and increasing the coverage of different object classes in our training data set -- but the core tech is there, and it does have an interactive web UI, so it's already fun to play with. :)

Looking at the example inputs & outputs for ObjectCropBot, it's evident that the challenge is not just detecting the object and clipping it approximately, but tracing a tight precise boundary around it. We've found that DNN/ConvNet-based approaches don't offer the necessary precision, so it's necessary to perform some pre- or post-processing using other Computer Vision techniques. At Object AI, we've developed an "object boundary deduction" pipeline that combines ConvNets with other tech. It's interesting that the blog post that you've linked to makes the same observation!

[andreyk]

Wow, this is great! Maybe i'll shelf my efforts a bit , if your online photo editor is this good... I did Google around and find some of these GraphCut-esque refinement techniques, but have yet to find an easily usable one that gave you a good crop with just an outline or tap (or both) - kudos for making one!

As to the lack of precision of ObjectCropBot, I think a lot of that is due to it running based on DeepMask and not SharpMask; Facebook's insight to run the final low-res features back through increasingly less downsized images with sort of skip connections is a good one, and I'd bet the resolution of the results would be a lot better if I just hacked it to use that instead of DeepMask (I think the thing I linked just uses that, pretty much).