Zobrazeno 1 - 10
of 155
pro vyhledávání: '"Seitz, Steven M."'
This paper describes an efficient algorithm for solving noisy linear inverse problems using pretrained diffusion models. Extending the paradigm of denoising diffusion implicit models (DDIM), we propose constrained diffusion implicit models (CDIM) tha
Externí odkaz:
http://arxiv.org/abs/2411.00359
Given an input painting, we reconstruct a time-lapse video of how it may have been painted. We formulate this as an autoregressive image generation problem, in which an initially blank "canvas" is iteratively updated. The model learns from real artis
Externí odkaz:
http://arxiv.org/abs/2409.20556
Autor:
Wang, Xiaojuan, Zhou, Boyang, Curless, Brian, Kemelmacher-Shlizerman, Ira, Holynski, Aleksander, Seitz, Steven M.
We present a method for generating video sequences with coherent motion between a pair of input key frames. We adapt a pretrained large-scale image-to-video diffusion model (originally trained to generate videos moving forward in time from a single i
Externí odkaz:
http://arxiv.org/abs/2408.15239
We present Infinite Texture, a method for generating arbitrarily large texture images from a text prompt. Our approach fine-tunes a diffusion model on a single texture, and learns to embed that statistical distribution in the output domain of the mod
Externí odkaz:
http://arxiv.org/abs/2405.08210
Autor:
Gao, Alice, Jayakumar, Samyukta, Maniglia, Marcello, Curless, Brian, Kemelmacher-Shlizerman, Ira, Seitz, Aaron R., Seitz, Steven M.
We consider the question of how to best achieve the perception of eye contact when a person is captured by camera and then rendered on a 2D display. For single subjects photographed by a camera, conventional wisdom tells us that looking directly into
Externí odkaz:
http://arxiv.org/abs/2404.17104
Head Related Transfer Functions (HRTFs) play a crucial role in creating immersive spatial audio experiences. However, HRTFs differ significantly from person to person, and traditional methods for estimating personalized HRTFs are expensive, time-cons
Externí odkaz:
http://arxiv.org/abs/2311.03560
We present a method to generate full-body selfies from photographs originally taken at arms length. Because self-captured photos are typically taken close up, they have limited field of view and exaggerated perspective that distorts facial shapes. We
Externí odkaz:
http://arxiv.org/abs/2308.14740
Autor:
Chatterjee, Ishan, Kim, Maruchi, Jayaram, Vivek, Gollakota, Shyamnath, Kemelmacher-Shlizerman, Ira, Patel, Shwetak, Seitz, Steven M.
We present ClearBuds, the first hardware and software system that utilizes a neural network to enhance speech streamed from two wireless earbuds. Real-time speech enhancement for wireless earbuds requires high-quality sound separation and background
Externí odkaz:
http://arxiv.org/abs/2206.13611
Nonprehensile manipulation involves long horizon underactuated object interactions and physical contact with different objects that can inherently introduce a high degree of uncertainty. In this work, we introduce a novel Real-to-Sim reward analysis
Externí odkaz:
http://arxiv.org/abs/2111.07986
Autor:
Park, Keunhong, Sinha, Utkarsh, Hedman, Peter, Barron, Jonathan T., Bouaziz, Sofien, Goldman, Dan B, Martin-Brualla, Ricardo, Seitz, Steven M.
Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to reconstruct such non-rigid scenes is through the use of a learned def
Externí odkaz:
http://arxiv.org/abs/2106.13228