11–20 of 32 posts
Earlier quoted context omitted.
Wow, that seems way beyond what I would have expected the state of the art to be. Iiuc they're generating arbitrary perspectives of geometry from one or two photos, right?
Not one or two, more like one or two hundred. But otherwise: yeah.
Earlier quoted context omitted.
Not one or two, more like one or two hundred. But otherwise: yeah.
One of the authors said in a talk that it worked with as few as 15 images.
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
Either way, I'm struggling to understand how it might work. Care to say more?
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
Your generic dataset idea is either crazy-brilliant, or I'm stupid: conceivably both. Either way, I'm struggling to understand how it might work. Care to say more?
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
Tensorflow needs to stop breaking their entire codebase every 10 or so minor versions and also make their archived versions for all OS readily available. Do a pip3 install tensorflow==1.15 just for an illustration of what I am talking about.
There are hundreds if not thousands of extensive code TF projects on GitHub that are now almost completely useless because the libraries they require are not readily available. Sure you can use them as a template to translate into TF 2 but as a keeper of an important open source library, tensorflow team has been far less than diligent at making sure projects containing their code do not break as tensorflow pushes out updates.
Earlier quoted context omitted.
Wow, that seems way beyond what I would have expected the state of the art to be. Iiuc they're generating arbitrary perspectives of geometry from one or two photos, right?
Have a look at the google drive files if you click on the data link; it's a lot more than 2 photos. eg. That dinosaur skeleton is derived from 60 photos. The drumkit comes from ~100. ...so it's not magic, it's very close to what you get from standard photogrammetry. The big part of this is that it isn't representing the scene as block of voxels like some other approaches. > The biggest practical tradeoffs between the…
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
Tensorflow 1.15 for python3.. good luck finding that anymore for a Linux repo. Tensorflow needs to stop breaking their entire codebase every 10 or so minor versions and also make their archived versions for all OS readily available. Do a pip3 install tensorflow==1.15 just for an illustration of what I am talking about. There are hundreds if not thousands of extensive code TF projects on GitHub that are now almost com…
But I certainly agree with the frustration with google breaking everything. If I wanted to use Chainer (or for that matter Keras) I would just use that. I don't need tensorflow to imitate it for me and break the alternative approach I was using.
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
Tensorflow 1.15 for python3.. good luck finding that anymore for a Linux repo. Tensorflow needs to stop breaking their entire codebase every 10 or so minor versions and also make their archived versions for all OS readily available. Do a pip3 install tensorflow==1.15 just for an illustration of what I am talking about. There are hundreds if not thousands of extensive code TF projects on GitHub that are now almost com…
I came hoping to find something like neural radiance fields [1] but for generic datasets (ie. latent representations of data that allow you to store the 'data' without storing it explicitly row by row). ...but, this is: > What if, instead, data and queries can be represented as short natural language sentences, and queries can be answered from these sentences? Useful for some things, but not useful for most things. […
A database (simplest case is an array or a dict) isn’t fundamentally different from a function in its interface. To both of them you submit a query/argument and they return some value. A “function” might “compute” the value after the query is submitted, while the database might “store” a pre-computed value. Especially in physical contexts where there is a natural continuity in the thing being represented (think object density/radiance, as opposed to student names), it makes sense to also have the option to interpolate among records in a database.
Neural networks (being generic learnable function approximators) are a nice framework to straddle this boundary for generic cases.
In the specific example of the Nerf, we use a neural network rather than discrediting space and assigning a value per pixel/voxel. A consequent advantage is that we can have an a data description that is adaptive non-uniform in its information density, unlike a voxel grid.
There’s more to say, but I hope this gives a feel :-)