3 types of super-resolution predictions to come

  • 5 Replies
  • 1328 Views
*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *******************
  • Prometheus
  • *
  • 4659
  • First it wiggles, then it is rewarded.
    • Main Project Thread
3 types of super-resolution predictions to come
« on: March 03, 2019, 03:54:50 pm »
I was thinking, wait, there's 3 types!

You can superresolution the amount of pixels of an image.
You can add onto the side around the image like  have tried in the images below attached.
And you can add frames of what comes next in a video sequence of what may happen likely next.

If you do this for 3D pixel blocks, it would be same but cooler. A night ago I was dreaming of running through a endless town at night - no matter where I went, there was a continuation of something around the corner if you get me. Like the attached images, but in 3D. For ex. if I go down a dark street, then there may be a road that goes sideways, and streets have houses on them, dark old houses - if it keeps with context seen earlier.
Emergent          https://openai.com/blog/

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *******************
  • Prometheus
  • *
  • 4659
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: 3 types of super-resolution predictions to come
« Reply #1 on: March 03, 2019, 03:56:46 pm »
I think I've said it before but ya...you can take a small B&W pic, colorize it, zoom in adding details, add surrounding details, make 3D, make into movie, etc.

Extrapolating the data!
Emergent          https://openai.com/blog/

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • *******************
  • Prometheus
  • *
  • 4659
  • First it wiggles, then it is rewarded.
    • Main Project Thread
Re: 3 types of super-resolution predictions to come
« Reply #2 on: March 03, 2019, 04:05:55 pm »
I tried all that in my mind just now. What I think is cool is my 2D vision can emulate looking aroun a 3D speaker going in a 360 in the air...even if haven't seen the backside of it before.

But do get into 3D later, it will be exponentially more powerful. Just how words can describe anything, 2D vision is way better later. However I'm not sure human brains do 3D vision, nor 3D vision+inside matter estimation (not just shells). so maybe we can get way with 2D!
Emergent          https://openai.com/blog/

*

HS

  • Trusty Member
  • **********
  • Millennium Man
  • *
  • 1175
Re: 3 types of super-resolution predictions to come
« Reply #3 on: March 03, 2019, 08:23:54 pm »
Maybe step 4 would be downgrading to cartoon format, so we can avoid the uncanny valley.

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Trusty Member
  • **********************
  • Colossus
  • *
  • 5865
Re: 3 types of super-resolution predictions to come
« Reply #4 on: March 04, 2019, 04:47:35 am »
Any "uncanny valley" is only in the mind of the beholder, and that is nothing more than one man's speculation/theory. Nothing factual to it IMHO.

So venture forth into the realm of AI with its humanoids, androids, robots, Robo-sapiens of all kinds and enjoy Westworld to your heart's content!
You have nothing to fear but...well...you know... O0
In the world of AI, it's the thought that counts!

*

AndyGoode

  • Guest
Re: 3 types of super-resolution predictions to come
« Reply #5 on: March 09, 2019, 12:23:06 am »
However I'm not sure human brains do 3D vision, nor 3D vision+inside matter estimation (not just shells). so maybe we can get way with 2D!

David Marr believes brains *do* perform 3D vision, including 3D representation and manipulation of 3D objects:

(p. 326)
   Unfortunately, we receive little help from the biological sciences about
the kinds of questions raised by the later aspects of the visual process.
Virtually nothing is known about the physiological and anatomical arrange-
ments that mediate the construction of the three-dimensional visual descrip-
tions of the world, and even the best psychological information is for the
most part anecdotal and derived from the neurological rather than psycho-
physical studies.
   Nevertheless, I think it is clear in principle that the brain must con-
truct three-dimensional representations of objects and of the space they
occupy. As Sutherland (1979) has remarked, there are at least two good
reasons for this. First, in order to manipulate objects and avoid bumping
into them, organisms must be able to perceive and represent the disposi-
tion of the objects' surfaces in space. This gives us a minimal requirement
for something like the 2 1/2-D sketch. Second, in order to recognize an
object by its shape, allowing one then to evaluate its significance for action,
some kind of three-dimensional representation must be built from the
image and matched with which other knowledge is already associated. As we have seen,
the two processes of construction and matching cannot be rigorously sep-
arated because a natural aspect of constructing a three-dimensional rep-
resentation may include the continual consultation of an increasingly spe-
cific catalogue of stored shapes.
   This forces us to rely, in our study of these later problems, much more
on a careful consideration of the computational and representational
requirements. Stated baldly, the strong constraints come from what the
representation is to be used for.
   We asked here about the requirements for a shape representation to
be used for recognition, and we came to three main conclusions: A shape
representation for recognition should (1) use an object-centered coordi-
nate system, (2) include volumetric primitives of various sizes, and (3) have
a modular organization. A representation based on a shape's natural axes
(for example, the axes identified by a stick figure) follows directly from
these choices. In addition, we saw that the basic process for deriving a
shape description in such a representation must involve a means for iden-
tifying the natural axes of a shape in its image and a mechanism for trans-
forming viewer-centered axis specifications to specifications in an object-
centered coordinate system.

Marr, David. 1982. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. Cambridge, Massachusetts: The MIT Press.

 


OpenAI Speech-to-Speech Reasoning Demo
by ivan.moony (AI News )
March 28, 2024, 01:31:53 pm
Say good-bye to GPUs...
by MikeB (AI News )
March 23, 2024, 09:23:52 am
Google Bard report
by ivan.moony (AI News )
February 14, 2024, 04:42:23 pm
Elon Musk's xAI Grok Chatbot
by MikeB (AI News )
December 11, 2023, 06:26:33 am
Nvidia Hype
by 8pla.net (AI News )
December 06, 2023, 10:04:52 pm
How will the OpenAI CEO being Fired affect ChatGPT?
by 8pla.net (AI News )
December 06, 2023, 09:54:25 pm
Independent AI sovereignties
by WriterOfMinds (AI News )
November 08, 2023, 04:51:21 am
LLaMA2 Meta's chatbot released
by 8pla.net (AI News )
October 18, 2023, 11:41:21 pm

Users Online

314 Guests, 0 Users

Most Online Today: 396. Most Online Ever: 2369 (November 21, 2020, 04:08:13 pm)

Articles