Zobrazeno 1 - 10
of 104
pro vyhledávání: '"Herrmann, Charles"'
We present WonderWorld, a novel framework for interactive 3D scene extrapolation that enables users to explore and shape virtual environments based on a single input image and user-specified text. While significant improvements have been made to the
Externí odkaz:
http://arxiv.org/abs/2406.09394
Text-conditioned diffusion models can generate impressive images, but fall short when it comes to fine-grained control. Unlike direct-editing tools like Photoshop, text conditioned models require the artist to perform "prompt engineering," constructi
Externí odkaz:
http://arxiv.org/abs/2404.03145
Autor:
Bar-Tal, Omer, Chefer, Hila, Tov, Omer, Herrmann, Charles, Paiss, Roni, Zada, Shiran, Ephrat, Ariel, Hur, Junhwa, Liu, Guanghui, Raj, Amit, Li, Yuanzhen, Rubinstein, Michael, Michaeli, Tomer, Wang, Oliver, Sun, Deqing, Dekel, Tali, Mosseri, Inbar
We introduce Lumiere -- a text-to-video diffusion model designed for synthesizing videos that portray realistic, diverse and coherent motion -- a pivotal challenge in video synthesis. To this end, we introduce a Space-Time U-Net architecture that gen
Externí odkaz:
http://arxiv.org/abs/2401.12945
Autor:
Wu, Xiaotong, Lai, Wei-Sheng, Shih, YiChang, Herrmann, Charles, Krainin, Michael, Sun, Deqing, Liang, Chia-Kai
DSLR cameras can achieve multiple zoom levels via shifting lens distances or swapping lens types. However, these techniques are not possible on smartphone devices due to space constraints. Most smartphone manufacturers adopt a hybrid zoom system: com
Externí odkaz:
http://arxiv.org/abs/2401.01461
We present a differentiable model that infers explicit boundaries, including curves, corners and junctions, using a mechanism that we call boundary attention. Boundary attention is a boundary-aware local attention operation that, when applied densely
Externí odkaz:
http://arxiv.org/abs/2401.00935
While methods for monocular depth estimation have made significant strides on standard benchmarks, zero-shot metric depth estimation remains unsolved. Challenges include the joint modeling of indoor and outdoor scenes, which often exhibit significant
Externí odkaz:
http://arxiv.org/abs/2312.13252
Autor:
Yu, Hong-Xing, Duan, Haoyi, Hur, Junhwa, Sargent, Kyle, Rubinstein, Michael, Freeman, William T., Cole, Forrester, Sun, Deqing, Snavely, Noah, Wu, Jiajun, Herrmann, Charles
We introduce WonderJourney, a modularized framework for perpetual 3D scene generation. Unlike prior work on view generation that focuses on a single type of scenes, we start at any user-provided location (by a text description or an image) and genera
Externí odkaz:
http://arxiv.org/abs/2312.03884
Autor:
Zhang, Junyi, Herrmann, Charles, Hur, Junhwa, Chen, Eric, Jampani, Varun, Sun, Deqing, Yang, Ming-Hsuan
While pre-trained large-scale vision models have shown significant promise for semantic correspondence, their features often struggle to grasp the geometry and orientation of instances. This paper identifies the importance of being geometry-aware for
Externí odkaz:
http://arxiv.org/abs/2311.17034
Autor:
Sargent, Kyle, Li, Zizhang, Shah, Tanmay, Herrmann, Charles, Yu, Hong-Xing, Zhang, Yunzhi, Chan, Eric Ryan, Lagun, Dmitry, Fei-Fei, Li, Sun, Deqing, Wu, Jiajun
We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges introduced
Externí odkaz:
http://arxiv.org/abs/2310.17994
Autor:
Rashtchian, Cyrus, Herrmann, Charles, Ferng, Chun-Sung, Chakrabarti, Ayan, Krishnan, Dilip, Sun, Deqing, Juan, Da-Cheng, Tomkins, Andrew
Probes are small networks that predict properties of underlying data from embeddings, and they provide a targeted, effective way to illuminate the information contained in embeddings. While analysis through the use of probes has become standard in NL
Externí odkaz:
http://arxiv.org/abs/2307.05610