No description available.

Game engines such as Unreal Engine 5 are widely used to create photo-realistic renderings. To run these renderings at high quality without experiencing any performance issues,high-performance hardware is often required. In situations where the hardware is lacking,users may be forced to lower the quality and resolution of renderings to maintain goodperformance. While this may be acceptable in some situations, it limits the benefit that apowerful tool like Unreal Engine 5 can provide. This thesis aims to explore the possibilityof using a Real-ESRGAN, fine-tuned on a custom data set, to increase both the resolutionand quality of screenshots taken in Unreal Engine 5. By doing this, users can lower theresolution and quality of their Unreal Engine 5 rendering while still being able to generatehigh quality screenshots similar to those produced when running the rendering at higherresolution and higher quality. To accomplish this, a custom data set was created by randomizing camera positionsand capturing screenshots in an Unreal Engine 5 rendering. This data set was used to finetune a pre-trained Real-ESRGAN model. The fine-tuned model could then generate imagesfrom low resolution and low quality screenshots taken in Unreal Engine 5. The resultingimages were analyzed and evaluated using both quantitative and qualitative methods.The conclusions drawn from this thesis indicate that images generated using the finetuned weights are of high quality. This conclusion is supported by quantitative measurements, demonstrating that the generated images and the ground truth images are similar.Furthermore, visual inspection conducted by the authors confirms that the generated images are similar to the reference images, despite occasional artifacts.

No description available.

No description available.

Video from aerial surveillance can provide a rich source of data for analysts. From the time-critical perspective of wilderness search and rescue operations, information extracted from aerial videos can mean the difference between a successful search and an unsuccessful search. When using low-cost, payload-limited mini-UAVs, as opposed to more expensive platforms, several challenges arise, including jittery video, narrow fields of view, low resolution, and limited time on screen for key features. These challenges make it difficult for analysts to extract key information in a timely manner. Traditional approaches may address some of these issues, but no existing system effectively addresses all of them in a unified and efficient manner. Building upon a hierarchical dense image correspondence technique, we create a unifying framework for reducing jitter, enhancing resolution, and expanding the field of view while lengthening the time that features remain on screen. It also provides for easy extraction of moving objects in the scene. Our method incorporates locally adaptive warps which allows for robust image alignment even in the presence of parallax and without the aid of internal or external camera parameters. We accelerate the image registration process using commodity Graphics Processing Units (GPUs) to accomplish all of these tasks in near real-time with no external telemetry data.

The Sun is of fundamental importance to life on earth and is studied by scientists from many disciplines. It exhibits phenomena on a wide range of observable scales, timescales and wavelengths and due to technological developments there is a continuing increase in the rate at which solar data is becoming available for study which presents both opportunities and challenges. Two satellites recently launched to observe the sun are STEREO (Solar TErrestrial RElations Observatory), providing simultaneous views of the SUN from two different viewpoints and SDO (Solar Dynamics Observatory) which aims to study the solar atmosphere on small scales and times and in many wavelengths. The STEREO and SDO missions are providing huge volumes of data at rates of about 15 GB per day (initially it was 30 GB per day) and 1.5 terabytes per day respectively. Accessing these huge data volumes efficiently at both high spatial and high time resolutions is important to support scientific discovery but requires increasingly efficient tools to browse, locate and process specific data sets. This thesis investigates the development of new technologies for processing information contained in multiple and overlapping images of the same scene to produce images of improved quality. This area in general is titled Super Resolution (SR), and offers a technique for reducing artefacts and increasing the spatial resolution. Another challenge is to generate 3D images such as Anaglyphs from uncalibrated pairs of SR images. An automated method to generate SR images is presented here. The SR technique consists of three stages: image registration, interpolation and filtration. Then a method to produce enhanced, near real-time, 3D solar images from uncalibrated pairs of images is introduced. Image registration is an essential enabling step in SR and Anaglyph processing. An accurate point-to-point mapping between views is estimated, with multiple images registered using only information contained within the images themselves. The performances of the proposed methods are evaluated using benchmark evaluation techniques. A software application called the SOLARSTUDIO has been developed to integrate and run all the methods introduced in this thesis. SOLARSTUDIO offers a number of useful image processing tools associated with activities highly focused on solar images including: Active Region (AR) segmentation, anaglyph creation, solar limb extraction, solar events tracking and video creation.

This work focuses on the high frequency restoration of video sequences captured by a hybrid camera, using key-frames as high frequency samples. The proposed method outlines a hierarchy to the super-resolution process, and is aimed at maximizing both speed and performance. Additionally, an advanced image processing simulator (EngineX) was developed to fine tune the algorithm. / Super-resolution algorithms are designed to enhance the detail level of a particular image or video sequence. However, it is very difficult to achieve in practice due to the problem being ill-posed, and often requires regularization based on assumptions about texture or edges. The process can be aided using high-resolution key-frames such as those generated from a hybrid camera. A hybrid camera is capable of capturing footage in multiple spatial and temporal resolutions. The typical output consists of a high resolution stream captured at low frame rate, and a low resolution stream captured at a high frame rate. Key-frame based super-resolution algorithms exploit the spatial and temporal correlation between the high resolution and low resolution streams to reconstruct a high resolution and high frame rate output stream. The proposed algorithm outlines a hierarchy to the super-resolution process, combining several different classical and novel methods. A residue formulation decides which pixels are required to be further reconstructed if a particular hierarchy stage fails to provide the expected results when compared to the low resolution prior. The hierarchy includes the optical flow based estimation which warps high frequency information from adjacent key-frames to the current frame. Specialized candidate pixel selection reduces the total number of pixels considered in the NLM stage. Occlusion is handled by a final fallback stage in the hierarchy. Additionally, the running time for a CIF sequence of 30 frames has been significantly reduced to within 3 minutes by identifying which pixels require reconstruction with a particular method. A custom simulation environment implements the proposed method as well as many common image processing algorithms. EngineX provides a graphical interface where video sequences and image processing methods can be manipulated and combined. The framework allows for advanced features such as multithreading, parameter sweeping, and block level abstraction which aided the development of the proposed super-resolution algorithm. Both speed and performance were fine tuned using the simulator which is the key to its improved quality over other traditional super-resolution schemes. / Thesis / Master of Applied Science (MASc)

This dissertation includes a collection of studies that aim to improve the way we represent and visualize volume data. The advancement of medical imaging has revolutionized healthcare, providing crucial anatomical insights for accurate diagnosis and treatment planning. Our first study introduces an innovative technique to enhance the utility of medical images, transitioning from monochromatic scans to vivid 3D representations. It presents a framework for reference-based automatic color transfer, establishing deep semantic correspondences between a colored reference image and grayscale medical scans. This methodology extends to volumetric rendering, eliminating the need for manual intervention in parameter tuning. Next, it delves into deep learning-based super-resolution for volume data. By leveraging color information and supplementary features, the proposed system efficiently upscales low-resolution renderings to achieve higher fidelity results. Temporal reprojection further strengthens stability in volumetric rendering. The third contribution centers on the compression and representation of volumetric data, leveraging coordinate-based networks and multi-resolution hash encoding. This approach demonstrates superior compression quality and training efficiency compared to other state-of-the-art neural volume representation techniques. Furthermore, we introduce a meta-learning technique for weight initialization to expedite convergence during training. These findings collectively underscore the potential for transformative advancements in large-scale data visualization and related applications.

No description available.

No description available.