Zobrazeno 1 - 10
of 575
pro vyhledávání: '"Zhang, Yunfan"'
Image aesthetics assessment (IAA) is attracting wide interest with the prevalence of social media. The problem is challenging due to its subjective and ambiguous nature. Instead of directly extracting aesthetic features solely from the image, user co
Externí odkaz:
http://arxiv.org/abs/2405.01326
Autor:
Zhang, Yunfan, Huang, Hong, Xiong, Zhiwei, Shen, Zhiqi, Lin, Guosheng, Wang, Hao, Vun, Nicholas
Controllable 3D indoor scene synthesis stands at the forefront of technological progress, offering various applications like gaming, film, and augmented/virtual reality. The capability to stylize and de-couple objects within these scenarios is a cruc
Externí odkaz:
http://arxiv.org/abs/2401.13203
We present a method named iComMa to address the 6D camera pose estimation problem in computer vision. Conventional pose estimation methods typically rely on the target's CAD model or necessitate specific network training tailored to particular object
Externí odkaz:
http://arxiv.org/abs/2312.09031
Image aesthetics assessment (IAA) aims to estimate the aesthetics of images. Depending on the content of an image, diverse criteria need to be selected to assess its aesthetics. Existing works utilize pre-trained vision backbones based on content kno
Externí odkaz:
http://arxiv.org/abs/2309.02861
This paper investigates an open research task of reconstructing and generating 3D point clouds. Most existing works of 3D generative models directly take the Gaussian prior as input for the decoder to generate 3D point clouds, which fail to learn dis
Externí odkaz:
http://arxiv.org/abs/2303.15805
In this paper, we discuss a class of two-stage hierarchical games with multiple leaders and followers, which is called Nash-Stackelberg-Nash (N-S-N) games. Particularly, we consider N-S-N games under decision-dependent uncertainties (DDUs). DDUs refe
Externí odkaz:
http://arxiv.org/abs/2202.11880
Publikováno v:
In Journal of Molecular Structure 15 August 2024 1310
Publikováno v:
In Tribology International August 2024 196
Publikováno v:
In Electric Power Systems Research January 2025 238
We propose a method to compress full-resolution video sequences with implicit neural representations. Each frame is represented as a neural network that maps coordinate positions to pixel values. We use a separate implicit network to modulate the coo
Externí odkaz:
http://arxiv.org/abs/2112.11312