Motion parallax for 360° RGBD video

Deep Scene Synthesis of Atlanta-World Interiors from a Single Omnidirectional Image

We present a new data-driven approach for extracting geometric and structural information from a single spherical panorama of an interior scene, and for using this information to render the scene from novel points of view, enhancing 3D immersion in VR applications. The approach copes with the inherent ambiguities of single-image geometry estimation and novel view synthesis by focusing on the very common case of Atlanta-world interiors, bounded by horizontal floors and ceilings and vertical walls. Based on this prior, we introduce a novel end-to-end deep learning approach to jointly estimate the depth and the underlying room structure of the scene. The prior guides the design of the network and of novel domain-specific loss functions, shifting the major computational load on a training phase that exploits available large-scale synthetic panoramic imagery. An extremely lightweight network uses geometric and structural information to infer novel panoramic views from translated positions at interactive rates, from which perspective views matching head rotations are produced and upsampled to the display size. As a result, our method automatically produces new poses around the original camera at interactive rates, within a working area suitable for producing depth cues for VR applications, especially when using head-mounted displays connected to graphics servers. The extracted floor plan and 3D wall structure can also be used to support room exploration. The experimental results demonstrate that our method provides low-latency performance and improves over current state-of-the-art solutions in prediction accuracy on available commonly used indoor panoramic benchmarks.

D-SAV360: A Dataset of Gaze Scanpaths on 360° Ambisonic Videos

Understanding human visual behavior within virtual reality environments is crucial to fully leverage their potential. While previous research has provided rich visual data from human observers, existing gaze datasets often suffer from the absence of multimodal stimuli. Moreover, no dataset has yet gathered eye gaze trajectories (i.e., scanpaths) for dynamic content with directional ambisonic sound, which is a critical aspect of sound perception by humans. To address this gap, we introduce D-SAV360, a dataset of 4,609 head and eye scanpaths for 360° videos with first-order ambisonics. This dataset enables a more comprehensive study of multimodal interaction on visual behavior in virtual reality environments. We analyze our collected scanpaths from a total of 87 participants viewing 85 different videos and show that various factors such as viewing mode, content type, and gender significantly impact eye movement statistics. We demonstrate the potential of D-SAV360 as a benchmarking resource for state-of-the-art attention prediction models and discuss its possible applications in further research. By providing a comprehensive dataset of eye movement data for dynamic, multimodal virtual environments, our work can facilitate future investigations of visual behavior and attention in virtual reality.

Exemplar-Based Inpainting for 6DOF Virtual Reality Photos

Multi-layer images are currently the most prominent scene representation for viewing natural scenes under full-motion parallax in virtual reality. Layers ordered in diopter space contain color and transparency so that a complete image is formed when the layers are composited in a view-dependent manner. Once baked, the same limitations apply to multi-layer images as to conventional single-layer photography, making it challenging to remove obstructive objects or otherwise edit the content. Object removal before baking can benefit from filling disoccluded layers with pixels from background layers. However, if no such background pixels have been observed, an inpainting algorithm must fill the empty spots with fitting synthetic content. We present and study a multi-layer inpainting approach that addresses this problem in two stages: First, a volumetric area of interest specified by the user is classified with respect to whether the background pixels have been observed or not. Second, the unobserved pixels are filled with multi-layer inpainting. We report on experiments using multiple variants of multi-layer inpainting and compare our solution to conventional inpainting methods that consider each layer individually.

Visualization and Visual Analytics Approaches for Image and Video Datasets: A Survey

Image and video data analysis has become an increasingly important research area with applications in different domains such as security surveillance, healthcare, augmented and virtual reality, video and image editing, activity analysis and recognition, synthetic content generation, distance education, telepresence, remote sensing, sports analytics, art, non-photorealistic rendering, search engines, and social media. Recent advances in Artificial Intelligence (AI) and particularly deep learning have sparked new research challenges and led to significant advancements, especially in image and video analysis. These advancements have also resulted in significant research and development in other areas such as visualization and visual analytics, and have created new opportunities for future lines of research. In this survey paper, we present the current state of the art at the intersection of visualization and visual analytics, and image and video data analysis. We categorize the visualization papers included in our survey based on different taxonomies used in visualization and visual analytics research. We review these papers in terms of task requirements, tools, datasets, and application areas. We also discuss insights based on our survey results, trends and patterns, the current focus of visualization research, and opportunities for future research.

FoV-NeRF: Foveated Neural Radiance Fields for Virtual Reality

Virtual Reality (VR) is becoming ubiquitous with the rise of consumer displays and commercial VR platforms. Such displays require low latency and high quality rendering of synthetic imagery with reduced compute overheads. Recent advances in neural rendering showed promise of unlocking new possibilities in 3D computer graphics via image-based representations of virtual or physical environments. Specifically, the neural radiance fields (NeRF) demonstrated that photo-realistic quality and continuous view changes of 3D scenes can be achieved without loss of view-dependent effects. While NeRF can significantly benefit rendering for VR applications, it faces unique challenges posed by high field-of-view, high resolution, and stereoscopic/egocentric viewing, typically causing low quality and high latency of the rendered images. In VR, this not only harms the interaction experience but may also cause sickness. To tackle these problems toward six-degrees-of-freedom, egocentric, and stereo NeRF in VR, we present the first gaze-contingent 3D neural representation and view synthesis method. We incorporate the human psychophysics of visual- and stereo-acuity into an egocentric neural representation of 3D scenery. We then jointly optimize the latency/performance and visual quality while mutually bridging human perception and neural scene synthesis to achieve perceptually high-quality immersive interaction. We conducted both objective analysis and subjective studies to evaluate the effectiveness of our approach. We find that our method significantly reduces latency (up to 99% time reduction compared with NeRF) without loss of high-fidelity rendering (perceptually identical to full-resolution ground truth). The presented approach may serve as the first step toward future VR/AR systems that capture, teleport, and visualize remote environments in real-time.

Instant Reality: Gaze-Contingent Perceptual Optimization for 3D Virtual Reality Streaming

Media streaming, with an edge-cloud setting, has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed passively, virtual reality applications require 3D assets stored on the edge to facilitate frequent edge-side interactions such as object manipulation and viewpoint movement. Compared to audio and video streaming, 3D asset streaming often requires larger data sizes and yet lower latency to ensure sufficient rendering quality, resolution, and latency for perceptual comfort. Thus, streaming 3D assets faces remarkably additional than streaming audios/videos, and existing solutions often suffer from long loading time or limited quality. To address this challenge, we propose a perceptually-optimized progressive 3D streaming method for spatial quality and temporal consistency in immersive interactions. On the cloud-side, our main idea is to estimate perceptual importance in 2D image space based on user gaze behaviors, including where they are looking and how their eyes move. The estimated importance is then mapped to 3D object space for scheduling the streaming priorities for edge-side rendering. Since this computational pipeline could be heavy, we also develop a simple neural network to accelerate the cloud-side scheduling process. We evaluate our method via subjective studies and objective analysis under varying network conditions (from 3G to 5G) and edge devices (HMD and traditional displays), and demonstrate better visual quality and temporal consistency than alternative solutions.

Real-World Virtual Reality With Head-Motion Parallax

Most of the real-world virtual reality (VR) content available today is captured and rendered from a fixed vantage point. The visual-vestibular conflict arising from the lack of head-motion parallax degrades the feeling of presence in the virtual environment and has been shown to induce nausea and visual discomfort. We present an end-to-end framework for VR with head-motion parallax for real-world scenes. To capture both horizontally and vertically separated perspectives, we use a camera rig with two vertically stacked rings of outward-facing cameras. The data from the rig are processed offline and stored into a compact intermediate representation, which is used to render novel views for a head-mounted display, in accordance with the viewer's head movements. We compare two promising intermediate representations-Stacked OmniStereo and Layered Depth Panoramas-and evaluate them in terms of objective image quality metrics and the occurrence of disocclusion holes in synthesized novel views.

Unsupervised Learning of Depth and Ego-Motion from Cylindrical Panoramic Video with Applications for Virtual Reality

We introduce a convolutional neural network model for unsupervised learning of depth and ego-motion from cylindrical panoramic video. Panoramic depth estimation is an important technology for applications such as virtual reality, 3D modeling, and autonomous robotic navigation. In contrast to previous approaches for applying convolutional neural networks to panoramic imagery, we use the cylindrical panoramic projection which allows for the use of the traditional CNN layers such as convolutional filters and max pooling without modification. Our evaluation of synthetic and real data shows that unsupervised learning of depth and ego-motion on cylindrical panoramic images can produce high-quality depth maps and that an increased field-of-view improves ego-motion estimation accuracy. We create two new datasets to evaluate our approach: a synthetic dataset created using the CARLA simulator, and Headcam, a novel dataset of panoramic video collected from a helmet-mounted camera while biking in an urban setting. We also apply our network to the problem of converting monocular panoramas to stereo panoramas.