Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Image2Mesh: Single Image 3D Reconstruction

arxiv.org

Post reply on HN
Print view View original

1–10 of 17 posts

Re: Image2Mesh: Single Image 3D Reconstruction

#4

Post by TehCorwiz »

callesgg wrote: post #3
malux85 wrote: post #2

No source code :(

Right, they probably just made it all up.

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.

Re: Image2Mesh: Single Image 3D Reconstruction

#6

Post by cycrutchfield »

callesgg wrote: post #3
malux85 wrote: post #2

No source code :(

Right, they probably just made it all up.

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

Re: Image2Mesh: Single Image 3D Reconstruction

#8

Post by malux85 »

callesgg wrote: post #3
malux85 wrote: post #2

No source code :(

Right, they probably just made it all up.

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.

Post reply on HN