サクサク読めて、アプリ限定の機能も多数！
トップへ戻る
WWDC25
nvlabs.github.io
EG3D: Efficient Geometry-aware 3D Generative Adversarial Networks Abstract Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generate
Neural gigapixel images Neural SDF NeRF Neural volume We demonstrate near-instant training of neural graphics primitives on a single GPU for multiple tasks. In gigapixel image we represent an image by a neural network. SDF learns a signed distance function in 3D space whose zero level-set represents a 2D surface. NeRF [Mildenhall et al. 2020] uses 2D images and their camera poses to reconstruct a
Tero Karras 1 Miika Aittala 1 Samuli Laine 1 Erik Härkönen 2, 1 Janne Hellsten 1 Jaakko Lehtinen 1, 2 Timo Aila 1 1 NVIDIA 2 Aalto University Abstract We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be gl
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 label such as dirt, grass, tree, sand, or water. We represent the world as a continuous volumetric function and train our model to render view-consistent pho
Video-to-video synthesis (vid2vid) aims at converting an input semantic video, such as videos of human poses or segmentation masks, to an output photorealistic video. While the state-of-the-art of vid2vid has advanced significantly, existing approaches share two major limitations. First, they are data-hungry. Numerous images of a target human subject or a scene are required for training. Second, a
Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods require access to many images in both source and destination classes at training time. We argue this greatly limits their use. Drawing inspiration from the human cap
Semantic Image Synthesis with Spatially-Adaptive Normalization We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the network, which is then processed through stacks of convolution, normalization, and nonlinearity layers. We show that this is
(1) What is CUB? CUB provides state-of-the-art, reusable software components for every layer of the CUDA programming model: Parallel primitives Warp-wide "collective" primitives Cooperative warp-wide prefix scan, reduction, etc. Safely specialized for each underlying CUDA architecture Block-wide "collective" primitives Cooperative I/O, sort, scan, reduction, histogram, etc. Compatible with arbitra
© 2013, NVIDIA CORPORATION. All rights reserved. Code and text by Sean Baxter, NVIDIA Research. (Click here for license. Click here for contact information.) Modern GPU is code and commentary intended to promote new and productive ways of thinking about GPU computing. This project is a library, an algorithms book, a tutorial, and a best-practices guide. If you are new to CUDA, start here. If you'r
このページを最初にブックマークしてみませんか？
『nvlabs.github.io』の新着エントリーを見る
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
