Open Access. Powered by Scholars. Published by Universities.®
Graphics and Human Computer Interfaces Commons™
Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
-
- Air gestures (1)
- Android launcher (1)
- Antialiasing (1)
- Autoencoders (1)
- Automobile (1)
-
- BRDF (1)
- Computational photography (1)
- Convolutional autoencoder neural networks (1)
- Deep learning super sampling (DLSS) (1)
- Deferred rendering (1)
- Encoder-decoders (1)
- Face segmentation (1)
- Face swapping (1)
- Frame generation (1)
- Generative Adversarial Network (GAN) (1)
- Generative adversarial networks (1)
- Gesture tablature (1)
- Global illumination (1)
- High resolution imaging (1)
- Human-computer interaction (1)
- Image processing (1)
- Image reconstruction (1)
- Image resizing (1)
- Infotainment (1)
- Latency (1)
- Light field probes (1)
- Linear 3D morphable models (1)
- Low-light imaging (1)
- Motion vectors (1)
- Multi-band blending (1)
Articles 1 - 9 of 9
Full-Text Articles in Graphics and Human Computer Interfaces
Deep-Learning Realtime Upsampling Techniques In Video Games, Biruk Mengistu
Deep-Learning Realtime Upsampling Techniques In Video Games, Biruk Mengistu
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
This paper addresses the challenge of keeping up with the ever-increasing graphical complexity of video games and introduces a deep-learning approach to mitigating it. As games get more and more demanding in terms of their graphics, it becomes increasingly difficult to maintain high-quality images while also ensuring good performance. This is where deep learning super sampling (DLSS) comes in. The paper explains how DLSS works, including the use of convolutional autoencoder neural networks and various other techniques and technologies. It also covers how the network is trained and optimized, as well as how it incorporates temporal antialiasing and frame generation …
Exploring Methods Used In Face Swapping, Joshua Eklund
Exploring Methods Used In Face Swapping, Joshua Eklund
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Face swapping involves replacing the face in one image (the target) with a face in a different image (the source) while maintaining the pose and expression of the target face. Previous methods of face swapping required extensive computer power and man hours. As such, new methods are being developed that are quicker, less resource intensive, and more accessible to the non-expert. This paper provides background information on key methods used for face swapping and outlines three recently developed approaches: one based on generative adversarial networks, one based on linear 3D morphable models, and one based on encoder-decoders.
Recent Advances In Smartphone Computational Photography, Paul Friederichsen
Recent Advances In Smartphone Computational Photography, Paul Friederichsen
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Smartphone cameras present many challenges, most of which come from the need for them to be physically small. Their small size puts a fundamental limit on their ability to resolve detail and collect light, which makes low-light photography and zooming difficult. This paper presents two approaches to improve smartphone photography through software techniques. The first is handheld super-resolution which uses natural hand movement to improve the resolution smartphone images, especially when zoomed. The second approach is a system which improves low light photography in smartphones.
Single Image Super-Resolution, Yujing Song
Single Image Super-Resolution, Yujing Song
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Super-Resolution (SR) of a single image is a classic problem in computer vision. The goal of image super-resolution is to produce a high-resolution image from a low-resolution image. This paper presents a popular model, super-resolution convolutional neural network (SRCNN), to solve this problem. This paper also examines an improvement to SRCNN using a methodology known as generative adversarial net- work (GAN) which is better at adding texture details to the high resolution output.
Touchscreen Smartphone User Interfaces For Older Adults, Ai Sano
Touchscreen Smartphone User Interfaces For Older Adults, Ai Sano
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Today the world is experiencing the rapid growth of the older population. The number of older adults who own digital devices such as smartphones is increasing as well. The current smartphone user interfaces, however, appear not optimized for older adults. When designing smartphone user interfaces for older adults, we must consider their age-related physical and cognitive changes, which most likely affect their user experience. The present paper explores smartphone user interface guidelines for older adults and heuristics for evaluating the usability of Android launchers for older adults as well as a research study that developed an Android launcher for older …
An Overview Of Modern Global Illumination, Skye A. Antinozzi
An Overview Of Modern Global Illumination, Skye A. Antinozzi
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Advancements in graphical hardware call for innovative solutions, which can improve the realism of computer generated lighting. These innovative solutions aim to generate state of the art computer generated lighting through a combination of intelligent global illumination models and the use of modern hardware. The solution described in this paper achieves global illumination by ray tracing over geometry within a 3D scene from distributed light field probes and proceeds to shade the scene with a deferred renderer. Such a solution provides the flexibility and robustness that many other global illumination models have previously lacked while still achieving realistic lighting that …
Image Resizing Using Seam Carving, Kristin Rachor
Image Resizing Using Seam Carving, Kristin Rachor
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Image resizing has become more necessary with the increased popularity of cell phones, tablets and other electronic devices with varying screen sizes. This paper presents methods for resizing images and videos while attempting to preserve the important content of that image or video. An algorithm called seam carving can expand or reduce the size of an image while typically maintaining quality and content. Seam carving is not always effective however and there have been recent developments and modifications on this algorithm. This paper presents two advancements on seam carving, one that optimizes image retargeting on images with many repeated objects …
Infotainment Interface Design For Automobiles, Ian R. Buck
Infotainment Interface Design For Automobiles, Ian R. Buck
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
In an increasingly connected, mobile world, situations where users do not interact with their digital lives are becoming few and far between. This can be a problem in situations that demand a user's attention for their safety. Driving is one such situation, and it is doubly important because a significant portion of the western population drives on a daily basis. Researchers have tested different interface designs with the goal of finding one that demands the least cognitive load while still allowing the user to perform the desired task efficiently. In this paper interfaces incorporating auditory cues, voice dictation, and air …
Interpreting Multitouch Gestures, Michael Schuweiler
Interpreting Multitouch Gestures, Michael Schuweiler
Scholarly Horizons: University of Minnesota, Morris Undergraduate Journal
Interpreting multitouch interactions can be as simple as understanding code that handles these multitouches and this code's associated actions. As more touch events are added to an input, inputs become more complex. There are multiple approaches to interpreting these inputs between users and touchscreens. Researchers in this field find answers to common problems and provide developers with tools that make interactions with multitouch devices easier to describe and incorporate into their systems. These tools are then used to create gestures through different approaches, specifically through demonstration and by declaration. In this paper, these researchers' tools are described and compared.