Zobrazeno 1 - 10
of 81
pro vyhledávání: '"Patney, Anjul"'
Speed and consistency of target-shifting play a crucial role in human ability to perform complex tasks. Shifting our gaze between objects of interest quickly and consistently requires changes both in depth and direction. Gaze changes in depth are dri
Externí odkaz:
http://arxiv.org/abs/2309.15183
Autor:
Xing, Yazhou, Mazumdar, Amrita, Patney, Anjul, Liu, Chao, Yin, Hongxu, Chen, Qifeng, Kautz, Jan, Frosio, Iuri
Low dynamic range (LDR) cameras cannot deal with wide dynamic range inputs, frequently leading to local overexposure issues. We present a learning-based system to reduce these artifacts without resorting to complex acquisition mechanisms like alterna
Externí odkaz:
http://arxiv.org/abs/2308.15462
Image Features Influence Reaction Time: A Learned Probabilistic Perceptual Model for Saccade Latency
We aim to ask and answer an essential question "how quickly do we react after observing a displayed visual target?" To this end, we present psychophysical studies that characterize the remarkable disconnect between human saccadic behaviors and spatia
Externí odkaz:
http://arxiv.org/abs/2205.02437
Previous blind or No Reference (NR) video quality assessment (VQA) models largely rely on features drawn from natural scene statistics (NSS), but under the assumption that the image statistics are stationary in the spatial domain. Several of these mo
Externí odkaz:
http://arxiv.org/abs/2106.13328
Virtual Reality is regaining attention due to recent advancements in hardware technology. Immersive images / videos are becoming widely adopted to carry omnidirectional visual information. However, due to the requirements for higher spatial and tempo
Externí odkaz:
http://arxiv.org/abs/2106.06817
With the development of higher resolution contents and displays, its significant volume poses significant challenges to the goals of acquiring, transmitting, compressing, and displaying high-quality video content. In this paper, we propose a new deep
Externí odkaz:
http://arxiv.org/abs/2009.14110
Autor:
Nie, Weili, Karras, Tero, Garg, Animesh, Debnath, Shoubhik, Patney, Anjul, Patel, Ankit B., Anandkumar, Anima
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: difficulty with high-resolution images, primarily focusing on learning dise
Externí odkaz:
http://arxiv.org/abs/2003.03461
Publikováno v:
In Signal Processing: Image Communication April 2022 103
Autor:
Mitchell, Scott A., Ebeida, Mohamed S., Awad, Muhammad A., Park, Chonhyon, Patney, Anjul, Rushdi, Ahmad A., Swiler, Laura P., Manocha, Dinesh, Wei, Li-Yi
Publikováno v:
ACM Transactions on Graphics (TOG), Volume 37, Issue 2, May 2018, Article No. 22
Blue noise sampling has proved useful for many graphics applications, but remains underexplored in high-dimensional spaces due to the difficulty of generating distributions and proving properties about them. We present a blue noise sampling method wi
Externí odkaz:
http://arxiv.org/abs/1408.1118
Publikováno v:
ACM Transactions on Graphics 34, 4 (July 2015), 147:1-147:13
We present Piko, a framework for designing, optimizing, and retargeting implementations of graphics pipelines on multiple architectures. Piko programmers express a graphics pipeline by organizing the computation within each stage into spatial bins an
Externí odkaz:
http://arxiv.org/abs/1404.6293