Zobrazeno 1 - 10
of 116
pro vyhledávání: '"A. Aittala"'
Autor:
Karras, Tero, Aittala, Miika, Kynkäänniemi, Tuomas, Lehtinen, Jaakko, Aila, Timo, Laine, Samuli
The primary axes of interest in image-generating diffusion models are image quality, the amount of variation in the results, and how well the results align with a given condition, e.g., a class label or a text prompt. The popular classifier-free guid
Externí odkaz:
http://arxiv.org/abs/2406.02507
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
Autor:
Kynkäänniemi, Tuomas, Aittala, Miika, Karras, Tero, Laine, Samuli, Aila, Timo, Lehtinen, Jaakko
Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is clearly harmf
Externí odkaz:
http://arxiv.org/abs/2404.07724
Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets. In this paper, we identify and rectify several causes for uneven and ineffective training in the popular ADM diffusion mod
Externí odkaz:
http://arxiv.org/abs/2312.02696
Autor:
Chan, Eric R., Nagano, Koki, Chan, Matthew A., Bergman, Alexander W., Park, Jeong Joon, Levy, Axel, Aittala, Miika, De Mello, Shalini, Karras, Tero, Wetzstein, Gordon
We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image. Our model samples from the distribution of possible renderings consistent with the input and, even in the presence of ambiguity, is c
Externí odkaz:
http://arxiv.org/abs/2304.02602
We propose a deep learning method for 3D volumetric reconstruction in low-dose helical cone-beam computed tomography. Prior machine learning approaches require reference reconstructions computed by another algorithm for training. In contrast, we trai
Externí odkaz:
http://arxiv.org/abs/2212.07431
Autor:
Balaji, Yogesh, Nah, Seungjun, Huang, Xun, Vahdat, Arash, Song, Jiaming, Zhang, Qinsheng, Kreis, Karsten, Aittala, Miika, Aila, Timo, Laine, Samuli, Catanzaro, Bryan, Karras, Tero, Liu, Ming-Yu
Large-scale diffusion-based generative models have led to breakthroughs in text-conditioned high-resolution image synthesis. Starting from random noise, such text-to-image diffusion models gradually synthesize images in an iterative fashion while con
Externí odkaz:
http://arxiv.org/abs/2211.01324
Autor:
Härkönen, Erik, Aittala, Miika, Kynkäänniemi, Tuomas, Laine, Samuli, Aila, Timo, Lehtinen, Jaakko
Time-lapse image sequences offer visually compelling insights into dynamic processes that are too slow to observe in real time. However, playing a long time-lapse sequence back as a video often results in distracting flicker due to random effects, su
Externí odkaz:
http://arxiv.org/abs/2207.01413
Autor:
Brooks, Tim, Hellsten, Janne, Aittala, Miika, Wang, Ting-Chun, Aila, Timo, Lehtinen, Jaakko, Liu, Ming-Yu, Efros, Alexei A., Karras, Tero
We present a video generation model that accurately reproduces object motion, changes in camera viewpoint, and new content that arises over time. Existing video generation methods often fail to produce new content as a function of time while maintain
Externí odkaz:
http://arxiv.org/abs/2206.03429
We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices. This lets us identify
Externí odkaz:
http://arxiv.org/abs/2206.00364
Fr\'echet Inception Distance (FID) is the primary metric for ranking models in data-driven generative modeling. While remarkably successful, the metric is known to sometimes disagree with human judgement. We investigate a root cause of these discrepa
Externí odkaz:
http://arxiv.org/abs/2203.06026