No, that's unlikely. But it does mean that independent verification is difficult, if not impossible, given that we don't have their implementation or working data set.
The snark is unnecessary. Many papers in deep learning display heavily cherry-picked results. Including a source code implementation is one way to ensure that the real world results match the cherry picked results
No, but independent third party verification is a cornerstone of science.
I read many many deep learning papers and very often there are cherry picked results OR poor validation methods. For example, it's common for naive/inexperienced people to predict on the same data that the network is trained on : because it gives much better results due to overfitting.
I'm not saying that's what this paper has done. But if you are indeed going to publish, then your experiment needs to be reproducible, this means including the source code and the data.
TLDR They use a neural net to process an image to find a similar known 3D model to the object in the image as well as parameters for how to deform that model to be like the object in the image, and also then perform a linear combination of some related meshes (this is a follow up to their prior work "Compact Model Representation for 3D Reconstruction"). Pretty exciting work, but still far from being able to robustly do Image2Mesh. I happen to have worked on something quite similar, if any of you are curious: https://deformnet-site.github.io/DeformNet-website/
Interesting, thanks for the link. I tried a few published methods for doing this a year or so and I found they were quite slow. As in, you'd rather just use a stereo camera to quickly generate a decent pointcloud than use a single view plus a network like these. What did you find your performance (ms/frame) was like?
With separate dedicated identifiers and matching reconstruction pipelines, while only caring about a limited number of things, as in our specializing in faces, we can reconstruct 25 to 30 independent people, their heads and shoulder tops only, in real time on a 3.4 GHz i7. Note the reconstruction is accurate only as far as it matters for FR, as in we tend to ignore hair. So the models are bald, but they have the frame to frame facial expressions for everyone. Here's a gif of a degraded lighting test at 70 fps with one head doing a 3D reconstruction independently performed each frame: https://www.dropbox.com/s/0jtee4ofh2vdeg0/BlakeHeadMeshes.gi... I'm just visualizing the face, but the entire head and shoulder tops are reconstructed.
The changing colors and grain are part of a degraded video while tracking the face test. The face detection and portions of the reconstruction are NNs.
Surprised this is getting any notice at all. I work at a facial recognition firm pioneering this technique 20 years ago. (www.CyberExtruder.com) The TLDR description by andreyk pretty much sums the process, as it originated long ago. It is very similar now, just with a team of very smart people iterating over the pipeline for so long has made it sophisticated to the point the TLDR description could be argued as too light.
I even made a 3D avatar API & service, now closed, from the technology 10 years ago. The twitter site is still around, if you want to see the quality of reconstruction possible: https://twitter.com/3DAvatarStore/media
16 comments
[ 2.1 ms ] story [ 50.8 ms ] threadI read many many deep learning papers and very often there are cherry picked results OR poor validation methods. For example, it's common for naive/inexperienced people to predict on the same data that the network is trained on : because it gives much better results due to overfitting.
I'm not saying that's what this paper has done. But if you are indeed going to publish, then your experiment needs to be reproducible, this means including the source code and the data.
EDIT: why the changing colors in that gif?
I even made a 3D avatar API & service, now closed, from the technology 10 years ago. The twitter site is still around, if you want to see the quality of reconstruction possible: https://twitter.com/3DAvatarStore/media