Question of Fig. 13 in the Paper

[Unrealluver]

Question of Fig. 13 in the Paper

[mattdeitke]

I think they're mocking the sparks of AGI paper in Figure 13 (given the 🤨 emoji) 🙂.

I think many inpainting methods can already do these tasks. For instance, here's the example of using generative fill in photoshop, with 3 different generations:

Any inpainting method has to reason about its surroundings and fill in the blank based on context :)

[JingfengYao]

Thank the authors for the great work!

The same question. Are there some IQ-testing-like images in the training dataset? If not, the performance is really amazing!

[Unrealluver]

I think they're mocking the sparks of AGI paper in Figure 13 (given the 🤨 emoji) 🙂.

I think many inpainting methods can already do these tasks. For instance, here's the example of using generative fill in photoshop, with 3 different generations:

Any inpainting method has to reason about its surroundings and fill in the blank based on context :)

Great！Thanks for trying that! Could you please try more instances with Photoshop, e.g., the end image of the first row and third row?

[ytongbai]

Hi yes, this was a friendly joke and we'll check if we can do more interesting cases later. Thank you all for your kind support and interests, we really appreciate it.

Best,
Yutong