Zobrazeno 1 - 10
of 18
pro vyhledávání: '"Khakhulin, Taras"'
Autor:
Işık, Mustafa, Rünz, Martin, Georgopoulos, Markos, Khakhulin, Taras, Starck, Jonathan, Agapito, Lourdes, Nießner, Matthias
Representing human performance at high-fidelity is an essential building block in diverse applications, such as film production, computer games or videoconferencing. To close the gap to production-level quality, we introduce HumanRF, a 4D dynamic neu
Externí odkaz:
http://arxiv.org/abs/2305.06356
We present a new method for lightweight novel-view synthesis that generalizes to an arbitrary forward-facing scene. Recent approaches are computationally expensive, require per-scene optimization, or produce a memory-expensive representation. We star
Externí odkaz:
http://arxiv.org/abs/2210.01602
Autor:
Drobyshev, Nikita, Chelishev, Jenya, Khakhulin, Taras, Ivakhnenko, Aleksei, Lempitsky, Victor, Zakharov, Egor
In this work, we advance the neural head avatar technology to the megapixel resolution while focusing on the particularly challenging task of cross-driving synthesis, i.e., when the appearance of the driving image is substantially different from the
Externí odkaz:
http://arxiv.org/abs/2207.07621
We present a system for realistic one-shot mesh-based human head avatars creation, ROME for short. Using a single photograph, our model estimates a person-specific head mesh and the associated neural texture, which encodes both local photometric and
Externí odkaz:
http://arxiv.org/abs/2206.08343
Autor:
Khakhulin, Taras, Korzhenkov, Denis, Solovev, Pavel, Sterkin, Gleb, Ardelean, Timotei, Lempitsky, Victor
Representing scenes with multiple semi-transparent colored layers has been a popular and successful choice for real-time novel view synthesis. Existing approaches infer colors and transparency values over regularly-spaced layers of planar or spherica
Externí odkaz:
http://arxiv.org/abs/2201.05023
Autor:
Anokhin, Ivan, Demochkin, Kirill, Khakhulin, Taras, Sterkin, Gleb, Lempitsky, Victor, Korzhenkov, Denis
Existing image generator networks rely heavily on spatial convolutions and, optionally, self-attention blocks in order to gradually synthesize images in a coarse-to-fine manner. Here, we present a new architecture for image generators, where the colo
Externí odkaz:
http://arxiv.org/abs/2011.13775
Publikováno v:
Phys. Rev. A 102, 062614 (2020)
Tensor networks are the main building blocks in a wide variety of computational sciences, ranging from many-body theory and quantum computing to probability and machine learning. Here we propose a parallel algorithm for the contraction of tensor netw
Externí odkaz:
http://arxiv.org/abs/2004.10892
Autor:
Anokhin, Ivan, Solovev, Pavel, Korzhenkov, Denis, Kharlamov, Alexey, Khakhulin, Taras, Silvestrov, Alexey, Nikolenko, Sergey, Lempitsky, Victor, Sterkin, Gleb
Modeling daytime changes in high resolution photographs, e.g., re-rendering the same scene under different illuminations typical for day, night, or dawn, is a challenging image manipulation task. We present the high-resolution daytime translation (Hi
Externí odkaz:
http://arxiv.org/abs/2003.08791
Publikováno v:
NeurIPS 2020 Learning Meets Combinatorial Algorithms Workshop
We propose a Reinforcement Learning based approach to approximately solve the Tree Decomposition (TD) problem. TD is a combinatorial problem, which is central to the analysis of graph minor structure and computational complexity, as well as in the al
Externí odkaz:
http://arxiv.org/abs/1910.08371
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.