https://www.youtube.com/watch?v=4kTD5KkCMQw
Make_stone_look_smooth.meme
Make_stone_look_smooth.meme
YouTube
Mollifiers
In this video I talk about mollifiers, which is a super neat way of turning any function into a smooth one. This is used in image processing, as well as PDEs. Using this, I also show that harmonic functions must be infinitely differentiable, which is a nice…
∅
Photo
Deep Learning for Symbolic Mathematics
Abstract:
Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica.
https://arxiv.org/abs/1912.01412
#abstract
Abstract:
Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica.
https://arxiv.org/abs/1912.01412
#abstract
GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds
Abstract:
We present GANcraft, an unsupervised neural rendering framework for generating photorealistic images of large 3D block worlds such as those created in Minecraft. Our method takes a semantic block world as input, where each block is assigned a semantic label such as dirt, grass, or water. We represent the world as a continuous volumetric function and train our model to render view-consistent photorealistic images for a user-controlled camera. In the absence of paired ground truth real images for the block world, we devise a training technique based on pseudo-ground truth and adversarial training. This stands in contrast to prior work on neural rendering for view synthesis, which requires ground truth images to estimate scene geometry and view-dependent appearance. In addition to camera trajectory, GANcraft allows user control over both scene semantics and output style. Experimental results with comparison to strong baselines show the effectiveness of GANcraft on this novel task of photorealistic 3D block world synthesis.
https://youtu.be/1Hky092CGFQ
https://nvlabs.github.io/GANcraft/
#abstract
Abstract:
We present GANcraft, an unsupervised neural rendering framework for generating photorealistic images of large 3D block worlds such as those created in Minecraft. Our method takes a semantic block world as input, where each block is assigned a semantic label such as dirt, grass, or water. We represent the world as a continuous volumetric function and train our model to render view-consistent photorealistic images for a user-controlled camera. In the absence of paired ground truth real images for the block world, we devise a training technique based on pseudo-ground truth and adversarial training. This stands in contrast to prior work on neural rendering for view synthesis, which requires ground truth images to estimate scene geometry and view-dependent appearance. In addition to camera trajectory, GANcraft allows user control over both scene semantics and output style. Experimental results with comparison to strong baselines show the effectiveness of GANcraft on this novel task of photorealistic 3D block world synthesis.
https://youtu.be/1Hky092CGFQ
https://nvlabs.github.io/GANcraft/
#abstract
YouTube
NVIDIA GANcraft
Convert user-created 3D block worlds to realistic worlds!
More details at https://nvlabs.github.io/GANcraft/.
More details at https://nvlabs.github.io/GANcraft/.