Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
1–10 of 45 posts
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#2Can other companies use YouTube database for free say for research in Computer vision?
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#3Here is the actual paper https://arxiv.org/pdf/1904.11111.pdf
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#4I can’t wait until techniques like this find their way in to open source photogrammetry pipelines. I came up with a way of training neural nets for robotics using a monocular camera, photogrammetry, and a simulation environment with the captured 3D scene, but the photogrammetry was error prone and computationally intensive even on a beefy cloud server.
I’d love for OpenSFM or OpenMVS (check github) to get this kind of software.
Also would love to see an implementation of this on github, but hopefully that will follow in time.
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#5Can other companies use YouTube database for free say for research in Computer vision?
I believe yes if the content is under Creative Commons License.
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#6Can other companies use YouTube database for free say for research in Computer vision?
I think it's a gray area, but researchers often just do it. Better to ask for forgiveness than permission I guess. You could never collect datasets like ImageNet if you had to obtain individual permissions.
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#7You can tell that the authors have a very fast internet connection by the fact that this website weights in at 91.6 Mbyte and takes over a minute to fully load on a 25 Mbit connection.
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#8The best part of this paper is that they used mannequin challenge videos as their training dataset. That's super clever.
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#9Can other companies use YouTube database for free say for research in Computer vision?
Likely to fall under fair use, both for the research aspect and given the very low impact on factors 3&4 of 17USC107 for videos used to train neural nets.
Re: Moving Camera, Moving People: A Deep Learning Approach to Depth Prediction
#10This is a great hack, but I'd love to see more detail on how they did pose initialization to approximate ground truth on depth/pose from the Mannequin set. The paper says they are using ORB-SLAM2, but AFAIK ORB still needs a height label.
Maybe it's the case that this system doesn't actually return an X,Y,Z camera pose, but rather just a pixel specific depth, and not a recovered pose for new inputs.