Single-view depth estimation from omnidirectional images has gained popularity with its wide range of applications such as autonomous driving and scene reconstruction. Although data-driven learning-based methods demonstrate significant potential in this field, scarce training data and ineffective 360 estimation algorithms are still two key limitations hindering accurate estimation across diverse domains. In this work, we first establish a large-scale dataset with varied settings called Depth360 to tackle the training data problem. This is achieved by exploring the use of a plenteous source of data, 360 videos from the internet, using a test-time training method that leverages unique information in each omnidirectional sequence. With novel geometric and temporal constraints, our method generates consistent and convincing depth samples to facilitate single-view estimation. We then propose an end-to-end two-branch multi-task learning network, SegFuse, that mimics the human eye to effectively learn from the dataset and estimate high-quality depth maps from diverse monocular RGB images. With a peripheral branch that uses equirectangular projection for depth estimation and a foveal branch that uses cubemap projection for semantic segmentation, our method predicts consistent global depth while maintaining sharp details at local regions. Experimental results show favorable performance against the state-of-the-art methods.

<jats:title>Abstract</jats:title>
<jats:p>We present a novel concept <jats:italic>audio–visual object removal</jats:italic> in 360-degree videos, in which a target object in a 360-degree video is removed in both the visual and auditory domains synchronously. Previous methods have solely focused on the visual aspect of object removal using video inpainting techniques, resulting in videos with unreasonable remaining sounds corresponding to the removed objects. We propose a solution which incorporates direction acquired during the video inpainting process into the audio removal process. More specifically, our method identifies the sound corresponding to the visually tracked target object and then synthesizes a three-dimensional sound field by subtracting the identified sound from the input 360-degree video. We conducted a user study showing that our multi-modal object removal supporting both visual and auditory domains could significantly improve the virtual reality experience, and our method could generate sufficiently synchronous, natural and satisfactory 360-degree videos.</jats:p>

By overlaying virtual imagery onto the real world, mixed reality facilitates diverse applications and has drawn increasing attention. Enhancing physical in-hand objects with a virtual appearance is a key component for many applications that require users to interact with tools such as surgery simulations. However, due to complex hand articulations and severe hand-object occlusions, resolving occlusions in hand-object interactions is a challenging topic. Traditional tracking-based approaches are limited by strong ambiguities from occlusions and changing shapes, while reconstruction-based methods show a poor capability of handling dynamic scenes. In this article, we propose a novel real-time optimization system to resolve hand-object occlusions by spatially reconstructing the scene with estimated hand joints and masks. To acquire accurate results, we propose a joint learning process that shares information between two models and jointly estimates hand poses and semantic segmentation. To facilitate the joint learning system and improve its accuracy under occlusions, we propose an occlusion-aware RGB-D hand data set that mitigates the ambiguity through precise annotations and photorealistic appearance. Evaluations show more consistent overlays compared with literature, and a user study verifies a more realistic experience.

With 360 imaging devices becoming widely accessible, omnidirectional content has gained popularity in multiple fields. The ability to estimate depth from a single omnidirectional image can benefit applications such as robotics navigation and virtual reality. However, existing depth estimation approaches produce sub-optimal results on real-world omnidirectional images with dynamic foreground objects. On the one hand, capture-based methods cannot obtain the foreground due to the limitations of the scanning and stitching schemes. On the other hand, it is challenging for synthesis-based methods to generate highly-realistic virtual foreground objects that are comparable to the real-world ones. In this paper, we propose to augment datasets with realistic foreground objects using an image-based approach, which produces a foreground-aware photorealistic dataset for machine learning algorithms. By exploiting a novel scale-invariant RGB-D correspondence in the spherical domain, we repurpose abundant non-omnidirectional datasets to include realistic foreground objects with correct distortions. We further propose a novel auxiliary deep neural network to estimate both the depth of the omnidirectional images and the mask of the foreground objects, where the two tasks facilitate each other. A new local depth loss considers small regions of interests and ensures that their depth estimations are not smoothed out during the global gradient’s optimization. We demonstrate the system using human as the foreground due to its complexity and contextual importance, while the framework can be generalized to any other foreground objects. Experimental results demonstrate more consistent global estimations and more accurate local estimations compared with state-of-the-arts.

Due to the need to interact with virtual objects, the hand-object interaction has become an important element in mixed reality (MR) applications. In this paper, we propose a novel approach to handle the occlusion of augmented 3D object manipulation with hands by exploiting the nature of hand poses combined with tracking-based and model-based methods, to achieve a complete mixed reality experience without necessities of heavy computations, complex manual segmentation processes or wearing special gloves. The experimental results show a frame rate faster than real-time and a great accuracy of rendered virtual appearances, and a user study verifies a more immersive experience compared to past approaches. We believe that the proposed method can improve a wide range of mixed reality applications that involve hand-object interactions.