Tag: cs.GR

General Line Coordinates in 3D

Joshua Martinez, Boris Kovalerchuk Edit "General Line Coordinates in 3D"
arXiv:2403.13014v1 Announce Type: new Abstract: Interpretable interactive visual pattern discovery in lossless 3D visualization is a promising way to advance machine learning. It enables end users who are not data scientists to take control of the model development process as a self-service. It is conducted in 3D General Line Coordinates (GLC) visualization space, which preserves all n-D information in 3D. This paper presents a system which combines three types of GLC: Shifted Paired Coordinates (SPC), Shifted Tripled Coordinates (STC), and General Line Coordinates-Linear (GLC-L) for interactive visual pattern discovery. A transition from 2-D visualization to 3-D visualization allows for a more distinct visual pattern than in 2-D and it also allows for finding the best data viewing positions, which are not available in 2-D. It enables in-depth visual analysis of various class-specific data subsets comprehensible for end users in the original interpretable attributes. Controlling model overgeneralization by end users is an additional benefit of this approach.

Gore Diffusion LoRA Model

Ayush Thakur, Ashwani Kumar Dubey Edit "Gore Diffusion LoRA Model"
arXiv:2403.08812v1 Announce Type: new Abstract: The Emergence of Artificial Intelligence (AI) has significantly impacted our engagement with violence, sparking ethical deliberations regarding the algorithmic creation of violent imagery. This paper scrutinizes the "Gore Diffusion LoRA Model," an innovative AI model proficient in generating hyper-realistic visuals portraying intense violence and bloodshed. Our exploration encompasses the model's technical intricacies, plausible applications, and the ethical quandaries inherent in its utilization. We contend that the creation and implementation of such models warrant a meticulous discourse concerning the convergence of AI, art, and violence. Furthermore, we advocate for a structured framework advocating responsible development and ethical deployment of these potent technologies.

Rip Current Detection in Nearshore Areas through UAV Video Analysis with Almost Local-Isometric Embedding Techniques on Sphere

Anchen Sun, Kaiqi Yang Edit "Rip Current Detection in Nearshore Areas through UAV Video Analysis with Almost Local-Isometric Embedding Techniques on Sphere"
arXiv:2304.11783v2 Announce Type: replace-cross Abstract: Rip currents pose a significant danger to those who visit beaches, as they can swiftly pull swimmers away from shore. Detecting these currents currently relies on costly equipment and is challenging to implement on a larger scale. The advent of unmanned aerial vehicles (UAVs) and camera technology, however, has made monitoring near-shore regions more accessible and scalable. This paper proposes a new framework for detecting rip currents using video-based methods that leverage optical flow estimation, offshore direction calculation, earth camera projection with almost local-isometric embedding on the sphere, and temporal data fusion techniques. Through the analysis of videos from multiple beaches, including Palm Beach, Haulover, Ocean Reef Park, and South Beach, as well as YouTube footage, we demonstrate the efficacy of our approach, which aligns with human experts' annotations.

Perceptual Thresholds for Radial Optic Flow Distortion in Near-Eye Stereoscopic Displays

cs.HC updates on arXiv.org Edit "Perceptual Thresholds for Radial Optic Flow Distortion in Near-Eye Stereoscopic Displays"
We provide the first perceptual quantification of user's sensitivity to radial optic flow artifacts and demonstrate a promising approach for masking this optic flow artifact via blink suppression. Near-eye HMDs allow users to feel immersed in virtual environments by providing visual cues, like motion parallax and stereoscopy, that mimic how we view the physical world. However, these systems exhibit a variety of perceptual artifacts that can limit their usability and the user's sense of presence in VR. One well-known artifact is the vergence-accommodation conflict (VAC). Varifocal displays can mitigate VAC, but bring with them other artifacts such as a change in virtual image size (radial optic flow) when the focal plane changes. We conducted a set of psychophysical studies to measure users' ability to perceive this radial flow artifact before, during, and after self-initiated blinks. Our results showed that visual sensitivity was reduced by a factor of 10 at the start and for ~70 ms after a blink was detected. Pre- and post-blink sensitivity was, on average, ~0.15% image size change during normal viewing and increased to ~1.5-2.0% during blinks. Our results imply that a rapid (under 70 ms) radial optic flow distortion can go unnoticed during a blink. Furthermore, our results provide empirical data that can be used to inform engineering requirements for both hardware design and software-based graphical correction algorithms for future varifocal near-eye displays. Our project website is available at https://gamma.umd.edu/RoF/.

Squidgets: Sketch-based Widget Design and Direct Manipulation of 3D Scene

cs.HC updates on arXiv.org Edit "Squidgets: Sketch-based Widget Design and Direct Manipulation of 3D Scene"
Squidgets or 'sketch-widgets' is a novel stroke-based UI framework for direct scene manipulation. Squidgets is motivated by the observation that sketch strokes comprising visual abstractions of scene elements implicitly provide natural handles for the direct manipulation of scene parameters. Configurations of such strokes can further be explicitly drawn by users to author custom widgets associated with scene attributes. Users manipulate a scene by simply drawing strokes: a squidget is selected by partially matching the drawn stroke against both implicit scene contours and explicitly authored curves, and used in-situ to interactively control scene parameters associated with the squidget. We present an implementation of squidgets within the 3D modeling animation system Maya, and report on an evaluation of squidget creation and manipulation, by both casual users and professional artists.

HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation

cs.MM updates on arXiv.org Edit "HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation"
High Dynamic Range (HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. Due to the high costs associated with HDR imaging, the literature offers various data-driven methods for HDR image reconstruction from Low Dynamic Range (LDR) counterparts. A common limitation of these approaches is missing details in regions of the reconstructed HDR images, which are over- or under-exposed in the input LDR images. To this end, we propose a simple and effective method, HistoHDR-Net, to recover the fine details (e.g., color, contrast, saturation, and brightness) of HDR images via a fusion-based approach utilizing histogram-equalized LDR images along with self-attention guidance. Our experiments demonstrate the efficacy of the proposed approach over the state-of-art methods.

idMotif: An Interactive Motif Identification in Protein Sequences

cs.HC updates on arXiv.org Edit "idMotif: An Interactive Motif Identification in Protein Sequences"
This article introduces idMotif, a visual analytics framework designed to aid domain experts in the identification of motifs within protein sequences. Motifs, short sequences of amino acids, are critical for understanding the distinct functions of proteins. Identifying these motifs is pivotal for predicting diseases or infections. idMotif employs a deep learning-based method for the categorization of protein sequences, enabling the discovery of potential motif candidates within protein groups through local explanations of deep learning model decisions. It offers multiple interactive views for the analysis of protein clusters or groups and their sequences. A case study, complemented by expert feedback, illustrates idMotif's utility in facilitating the analysis and identification of protein sequences and motifs.

Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application

cs.MM updates on arXiv.org Edit "Minecraft-ify: Minecraft Style Image Generation with Text-guided Image Editing for In-Game Application"
In this paper, we first present the character texture generation system \textit{Minecraft-ify}, specified to Minecraft video game toward in-game application. Ours can generate face-focused image for texture mapping tailored to 3D virtual character having cube manifold. While existing projects or works only generate texture, proposed system can inverse the user-provided real image, or generate average/random appearance from learned distribution. Moreover, it can be manipulated with text-guidance using StyleGAN and StyleCLIP. These features provide a more extended user experience with enlarged freedom as a user-friendly AI-tool. Project page can be found at https://gh-bumsookim.github.io/Minecraft-ify/

A Modified de Casteljau Subdivision that Supports Smooth Stitching with Hierarchically Organized Bicubic Bezier Patches

cs.HC updates on arXiv.org Edit "A Modified de Casteljau Subdivision that Supports Smooth Stitching with Hierarchically Organized Bicubic Bezier Patches"
One of the theoretically intriguing problems in computer-aided geometric modeling comes from the stitching of the tensor product Bezier patches. When they share an extraordinary vertex, it is not possible to obtain continuity C1 or G1 along the edges emanating from that extraordinary vertex. Unfortunately, this stitching problem cannot be solved by using higher degree or rational polynomials. In this paper, we present a modified de Casteljau subdivision algorithm that can provide a solution to this problem. Our modified de Casteljau subdivision, when combined with topological modeling, provides a framework for interactive real-time modeling of piecewise smooth manifold meshes with arbitrary topology. The main advantage of the modified subdivision is that the continuity C1 on a given boundary edge does not depend on the positions of the control points on other boundary edges. The modified subdivision allows us to obtain the desired C1 continuity along the edges emanating from the extraordinary vertices along with the desired G1 continuity in the extraordinary vertices.

ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer

cs.MM updates on arXiv.org Edit "ToonAging: Face Re-Aging upon Artistic Portrait Style Transfer"
Face re-aging is a prominent field in computer vision and graphics, with significant applications in photorealistic domains such as movies, advertising, and live streaming. Recently, the need to apply face re-aging to non-photorealistic images, like comics, illustrations, and animations, has emerged as an extension in various entertainment sectors. However, the absence of a network capable of seamlessly editing the apparent age on NPR images means that these tasks have been confined to a naive approach, applying each task sequentially. This often results in unpleasant artifacts and a loss of facial attributes due to domain discrepancies. In this paper, we introduce a novel one-stage method for face re-aging combined with portrait style transfer, executed in a single generative step. We leverage existing face re-aging and style transfer networks, both trained within the same PR domain. Our method uniquely fuses distinct latent vectors, each responsible for managing aging-related attributes and NPR appearance. Adopting an exemplar-based approach, our method offers greater flexibility than domain-level fine-tuning approaches, which typically require separate training or fine-tuning for each domain. This effectively addresses the limitation of requiring paired datasets for re-aging and domain-level, data-driven approaches for stylization. Our experiments show that our model can effortlessly generate re-aged images while simultaneously transferring the style of examples, maintaining both natural appearance and controllability.