Zobrazeno 1 - 10
of 249
pro vyhledávání: '"Wang, Yinhuai"'
Autor:
Wang, Yinhuai, Zhao, Qihan, Yu, Runyi, Zeng, Ailing, Lin, Jing, Luo, Zhengyi, Tsui, Hok Wai, Yu, Jiwen, Li, Xiu, Chen, Qifeng, Zhang, Jian, Zhang, Lei, Tan, Ping
Mastering basketball skills such as diverse layups and dribbling involves complex interactions with the ball and requires real-time adjustments. Traditional reinforcement learning methods for interaction skills rely on labor-intensive, manually desig
Externí odkaz:
http://arxiv.org/abs/2408.15270
Humans interact with objects all the time. Enabling a humanoid to learn human-object interaction (HOI) is a key step for future smart animation and intelligent robotics systems. However, recent progress in physics-based HOI requires carefully designe
Externí odkaz:
http://arxiv.org/abs/2312.04393
Existing unsupervised low-light image enhancement methods lack enough effectiveness and generalization in practical applications. We suppose this is because of the absence of explicit supervision and the inherent gap between real-world scenarios and
Externí odkaz:
http://arxiv.org/abs/2308.09279
Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-required. They need to train a time-dependent classifier or a condition-de
Externí odkaz:
http://arxiv.org/abs/2303.09833
Recently, using diffusion models for zero-shot image restoration (IR) has become a new hot paradigm. This type of method only needs to use the pre-trained off-the-shelf diffusion models, without any finetuning, and can directly handle various IR task
Externí odkaz:
http://arxiv.org/abs/2303.00354
Autor:
Yu, Runyi, Wang, Zhennan, Wang, Yinhuai, Li, Kehan, Zhao, Yian, Zhang, Jian, Song, Guoli, Chen, Jie
The Position Embedding (PE) is critical for Vision Transformers (VTs) due to the permutation-invariance of self-attention operation. By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find th
Externí odkaz:
http://arxiv.org/abs/2212.05262
Most existing Image Restoration (IR) models are task-specific, which can not be generalized to different degradation operators. In this work, we propose the Denoising Diffusion Null-Space Model (DDNM), a novel zero-shot framework for arbitrary linear
Externí odkaz:
http://arxiv.org/abs/2212.00490
Consistency and realness have always been the two critical issues of image super-resolution. While the realness has been dramatically improved with the use of GAN prior, the state-of-the-art methods still suffer inconsistencies in local structures an
Externí odkaz:
http://arxiv.org/abs/2211.13524
Emerging high-quality face restoration (FR) methods often utilize pre-trained GAN models (\textit{i.e.}, StyleGAN2) as GAN Prior. However, these methods usually struggle to balance realness and fidelity when facing various degradation levels. Besides
Externí odkaz:
http://arxiv.org/abs/2203.08444
Neural radiance fields (NeRF) bring a new wave for 3D interactive experiences. However, as an important part of the immersive experiences, the defocus effects have not been fully explored within NeRF. Some recent NeRF-based methods generate 3D defocu
Externí odkaz:
http://arxiv.org/abs/2203.05189