Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Voleti, Vikram"'
We present Stable Video 4D (SV4D), a latent video diffusion model for multi-frame and multi-view consistent dynamic 3D content generation. Unlike previous methods that rely on separately trained generative models for video generation and novel view s
Externí odkaz:
http://arxiv.org/abs/2407.17470
We introduce HouseCrafter, a novel approach that can lift a floorplan into a complete large 3D indoor scene (e.g., a house). Our key insight is to adapt a 2D diffusion model, which is trained on web-scale images, to generate consistent multi-view col
Externí odkaz:
http://arxiv.org/abs/2406.20077
Autor:
Voleti, Vikram
Generative modeling for computer vision has shown immense progress in the last few years, revolutionizing the way we perceive, understand, and manipulate visual data. This rapidly evolving field has witnessed advancements in image generation, 3D anim
Autor:
Voleti, Vikram, Yao, Chun-Han, Boss, Mark, Letts, Adam, Pankratz, David, Tochilkin, Dmitry, Laforte, Christian, Rombach, Robin, Jampani, Varun
We present Stable Video 3D (SV3D) -- a latent video diffusion model for high-resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent work on 3D generation propose techniques to adapt 2D generative models for novel view
Externí odkaz:
http://arxiv.org/abs/2403.12008
Autor:
Deitke, Matt, Liu, Ruoshi, Wallingford, Matthew, Ngo, Huong, Michel, Oscar, Kusupati, Aditya, Fan, Alan, Laforte, Christian, Voleti, Vikram, Gadre, Samir Yitzhak, VanderBilt, Eli, Kembhavi, Aniruddha, Vondrick, Carl, Gkioxari, Georgia, Ehsani, Kiana, Schmidt, Ludwig, Farhadi, Ali
Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same progress, in part due to the challenges of acquiri
Externí odkaz:
http://arxiv.org/abs/2307.05663
Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject these diffusion-based generat
Externí odkaz:
http://arxiv.org/abs/2305.16397
Autor:
Lim, Jae Hyun, Kovachki, Nikola B., Baptista, Ricardo, Beckham, Christopher, Azizzadenesheli, Kamyar, Kossaifi, Jean, Voleti, Vikram, Song, Jiaming, Kreis, Karsten, Kautz, Jan, Pal, Christopher, Vahdat, Arash, Anandkumar, Anima
Diffusion models have recently emerged as a powerful framework for generative modeling. They consist of a forward process that perturbs input data with Gaussian white noise and a reverse process that learns a score function to generate samples by den
Externí odkaz:
http://arxiv.org/abs/2302.07400
Creating high-performance generalizable deep neural networks for phytoplankton monitoring requires utilizing large-scale data coming from diverse global water sources. A major challenge to training such networks lies in data privacy, where data colle
Externí odkaz:
http://arxiv.org/abs/2212.08990
Publikováno v:
NeurIPS 2022 Workshop on Score-Based Methods
Generative models based on denoising diffusion techniques have led to an unprecedented increase in the quality and diversity of imagery that is now possible to create with neural generative models. However, most contemporary state-of-the-art methods
Externí odkaz:
http://arxiv.org/abs/2210.12254
Autor:
Voleti, Vikram, Oreshkin, Boris N., Bocquelet, Florent, Harvey, Félix G., Ménard, Louis-Simon, Pal, Christopher
Inverse Kinematics (IK) systems are often rigid with respect to their input character, thus requiring user intervention to be adapted to new skeletons. In this paper we aim at creating a flexible, learned IK solver applicable to a wide variety of hum
Externí odkaz:
http://arxiv.org/abs/2208.08274