Omnidirectional Images Research Articles

Spherical Pseudo-Cylindrical Representation for Omnidirectional Image Super-resolution

Omnidirectional images have attracted significant attention in recent years due to the rapid development of virtual reality technologies. Equirectangular projection (ERP), a naive form to store and transfer omnidirectional images, however, is challenging for existing two-dimensional (2D) image super-resolution (SR) methods due to its inhomogeneous distributed sampling density and distortion across latitude. In this paper, we make one of the first attempts to design a spherical pseudo-cylindrical representation, which not only allows pixels at different latitudes to adaptively adopt the best distinct sampling density but also is model-agnostic to most off-the-shelf SR methods, enhancing their performances. Specifically, we start by upsampling each latitude of the input ERP image and design a computationally tractable optimization algorithm to adaptively obtain a (sub)-optimal sampling density for each latitude of the ERP image. Addressing the distortion of ERP, we introduce a new viewport-based training loss based on the original 3D sphere format of the omnidirectional image, which inherently lacks distortion. Finally, we present a simple yet effective recursive progressive omnidirectional SR network to showcase the feasibility of our idea. The experimental results on public datasets demonstrate the effectiveness of the proposed method as well as the consistently superior performance of our method over most state-of-the-art methods both quantitatively and qualitatively.

Omnidirectional Image Super-resolution via Bi-projection Fusion

With the rapid development of virtual reality, omnidirectional images (ODIs) have attracted much attention from both the industrial community and academia. However, due to storage and transmission limitations, the resolution of current ODIs is often insufficient to provide an immersive virtual reality experience. Previous approaches address this issue using conventional 2D super-resolution techniques on equirectangular projection without exploiting the unique geometric properties of ODIs. In particular, the equirectangular projection (ERP) provides a complete field-of-view but introduces significant distortion, while the cubemap projection (CMP) can reduce distortion yet has a limited field-of-view. In this paper, we present a novel Bi-Projection Omnidirectional Image Super-Resolution (BPOSR) network to take advantage of the geometric properties of the above two projections. Then, we design two tailored attention methods for these projections: Horizontal Striped Transformer Block (HSTB) for ERP and Perspective Shift Transformer Block (PSTB) for CMP. Furthermore, we propose a fusion module to make these projections complement each other. Extensive experiments demonstrate that BPOSR achieves state-of-the-art performance on omnidirectional image super-resolution. The code is available at https://github.com/W-JG/BPOSR.

Autoregressive Omni-Aware Outpainting for Open-Vocabulary 360-Degree Image Generation

A 360-degree (omni-directional) image provides an all-encompassing spherical view of a scene. Recently, there has been an increasing interest in synthesising 360-degree images from conventional narrow field of view (NFoV) images captured by digital cameras and smartphones, for providing immersive experiences in various scenarios such as virtual reality. Yet, existing methods typically fall short in synthesizing intricate visual details or ensure the generated images align consistently with user-provided prompts. In this study, autoregressive omni-aware generative network (AOG-Net) is proposed for 360-degree image generation by outpainting an incomplete 360-degree image progressively with NFoV and text guidances joinly or individually. This autoregressive scheme not only allows for deriving finer-grained and text-consistent patterns by dynamically generating and adjusting the process but also offers users greater flexibility to edit their conditions throughout the generation process. A global-local conditioning mechanism is devised to comprehensively formulate the outpainting guidance in each autoregressive step. Text guidances, omni-visual cues, NFoV inputs and omni-geometry are encoded and further formulated with cross-attention based transformers into a global stream and a local stream into a conditioned generative backbone model. As AOG-Net is compatible to leverage large-scale models for the conditional encoder and the generative prior, it enables the generation to use extensive open-vocabulary text guidances. Comprehensive experiments on two commonly used 360-degree image datasets for both indoor and outdoor settings demonstrate the state-of-the-art performance of our proposed method. Our code is available at https://github.com/zhuqiangLu/AOG-NET-360.

Perceptual Quality Assessment of Omnidirectional Images: A Benchmark and Computational Model

Compared with traditional 2D images, omnidirectional images (also referred to as 360 ∘ images) have more complicated perceptual characteristics due to the particularities of imaging and display. How humans perceive omnidirectional images in an immersive environment and form the immersive quality of experience are important problems. Thus, it is crucial to measure the quality of omnidirectional images under different viewing conditions, which suffer from realistic distortions. In this article, we build a large-scale subjective assessment database for omnidirectional images and carry out a comprehensive psychophysical experiment to study the relationships between different factors (viewing conditions and viewing behaviors) and the perceptual quality of omnidirectional images. In addition, we collect both subjective ratings and head movement data. A thorough analysis of the collected subjective data is also provided, where we make several interesting findings. Moreover, with the proposed database, we propose a novel transformer-based omnidirectional image quality assessment model. To be consistent with the human viewing process, viewing conditions and behaviors are naturally incorporated into the proposed model. Specifically, the proposed model mainly consists of three parts: viewport sequence generation, multi-scale feature extraction, and perceptual quality prediction. Extensive experimental results conducted on the proposed database demonstrate the effectiveness of the proposed method over existing image quality assessment methods.

Latitude-Adaptive Integer Bit Allocation for Quantization of Omnidirectional Images

Omnidirectional images have gained significant popularity and drawn great attention nowadays, which poses challenges to omnidirectional image processing in solving the bottleneck of storage and transmission. Projecting onto a two-dimensional image plane is generally used to compress an omnidirectional image. However, the most commonly used projection format, the equirectangular projection (ERP), results in a significant amount of redundant samples in the polar areas, thus incurring extra bitrate and geometric distortion. We derive the optimal latitude-adaptive bit allocation for each image tile. Subsequently, we propose a greedy algorithm for non-negative integer bit allocation (NNIBA) for non-uniform quantization under an omnidirectional image quality metric WMSE. In our experiment, we design quantization tables based on JPEG and compare our approach with other sampling-related methods. Our method achieves an average bit saving of 7.9% compared with JPEG while outperforming other sampling-related methods. Besides, we compare our non-uniform quantization approach with two proposed bit allocation methods, achieving an average improvement of 0.35 dB and 2.66 dB under WS-PSNR, respectively. The visual quality assessment also confirms the superiority of our method.

Electrolytic capacitor surface defect detection based on deep convolution neural network

The existing methods for detecting surface defects in electrolytic capacitors are typically based on conventional machine vision, with limited feature extraction capabilities, poor versatility, slow detection speed, and the inability to achieve accurate and real-time defect detection. In this study, a real-time object detection algorithm based on an improved single shot multibox detector (SSD) is proposed to achieve omnidirectional surface defect detection of electrolytic capacitors. First, an electrolytic capacitor surface image acquisition device was established to capture omnidirectional surface images of the capacitors, and an electrolytic capacitor surface defect dataset was created. Next, the visual geometry group (VGG)-16 network structure was replaced with the MobileNetv2 network structure, effectively reducing the model’s parameter count and improving inference speed. Moreover, the Multibox Loss function was replaced with the Focal Loss function to increase the model’s attention to difficult-to-classify samples and improve model accuracy. Additionally, a transfer learning network model was designed to apply the model to electrolytic capacitors of different colors using small sample learning. Finally, the performance of the improved network model was tested on a dataset of electrolytic capacitor surface defects. The experimental results demonstrate that the parameters quantity of improved model is 3.50 M, the mAP value reaches 92.67 %, which is improved by 2.54 %, and the Macro-F1 value reaches 92.15 %, which is 11.32 % higher than that before improvement. Thus, the proposed improved SSD model provides a theoretical basis and technical prerequisites for automated and intelligent surface defect detection in electrolytic capacitors.

Toward Smart, Flexible, and Omnidirectional Self-Powered Photodetection by an All-Solution-Processed In2O3/Pbl2 Heterojunction.

Amorphous In2O3 film is emerging as a promising oxide semiconductor for next-generation electronics and optoelectronics owing to high mobility and wide band gap. However, the persistent photocurrent phenomenon and high carrier concentration in amorphous In2O3 film are challenging the photodetection performances, resulting in a long response time and low Ilight/Idark ratio. In this work, the In2O3/PbI2 heterojunction is constructed by an all-solution synthesis process to inhibit the persistent photocurrent phenomenon and large dark current. Benefiting from the built-in electric field at the heterojunction interface, the In2O3/PbI2 heterojunction photodetector exhibits excellent self-powered photodetection performances with an ultralow dark current of 10-12 A, a high Ilight/Idark ratio of 104, and fast response times of 0.6/0.6 ms. Furthermore, the entire solution synthesis process and amorphous characteristics enable the fabrication of an In2O3/PbI2 heterojunction photodetector on arbitrary substrates to realize specific functions. When configured onto the polyimide substrate, the In2O3/PbI2 heterojunction photodetector shows excellent mechanical flexibility, bending endurance, and photoresponse stability. When implanted onto the transparent substrate, the In2O3/PbI2 heterojunction photodetector exhibits an outstanding omnidirectional self-powdered photodetection performance and imaging capability. All results pave the way for an all-solution-processed amorphous In2O3 film in advanced high-performance photodetectors.

Stripe Sensitive Convolution for Omnidirectional Image Dehazing.

The haze in a scenario may affect the 360 photo/video quality and the immersive 360 ° virtual reality (VR) experience. The recent single image dehazing methods, to date, have been only focused on plane images. In this work, we propose a novel neural network pipeline for single omnidirectional image dehazing. To create the pipeline, we build the first hazy omnidirectional image dataset, which contains both synthetic and real-world samples. Then, we propose a new stripe sensitive convolution (SSConv) to handle the distortion problems due to the equirectangular projections. The SSConv calibrates distortion in two steps: 1) extracting features using different rectangular filters and, 2) learning to select the optimal features by a weighting of the feature stripes (a series of rows in the feature maps). Subsequently, using SSConv, we design an end-to-end network that jointly learns haze removal and depth estimation from a single omnidirectional image. The estimated depth map is leveraged as the intermediate representation and provides global context and geometric information to the dehazing module. Extensive experiments on challenging synthetic and real-world omnidirectional image datasets demonstrate the effectiveness of SSConv, and our network attains superior dehazing performance. The experiments on practical applications also demonstrate that our method can significantly improve the 3-D object detection and 3-D layout performances for hazy omnidirectional images.

Intrinsic Omnidirectional Image Decomposition With Illumination Pre-Extraction.

Capturing an omnidirectional image with a 360-degree field of view entails capturing intricate spatial and lighting details of the scene. Consequently, existing intrinsic image decomposition methods face significant challenges when attempting to separate reflectance and shading components from a low dynamic range (LDR) omnidirectional images. To address this, our article introduces a novel method specifically designed for the intrinsic decomposition of omnidirectional images. Leveraging the unique characteristics of the 360-degree scene representation, we employ a pre-extraction technique to isolate specific illumination information. Subsequently, we establish new constraints based on these extracted details and the inherent characteristics of omnidirectional images. These constraints limit the illumination intensity range and incorporate spherical-based illumination variation. By formulating and solving an objective function that accounts for these constraints, our method achieves a more accurate separation of reflectance and shading components. Comprehensive qualitative and quantitative evaluations demonstrate the superiority of our proposed method over state-of-the-art intrinsic decomposition methods.

GLPanoDepth: Global-to-Local Panoramic Depth Estimation.

Depth estimation is a fundamental task in many vision applications. With the popularity of omnidirectional cameras, it becomes a new trend to tackle this problem in the spherical space. In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image. An omnidirectional image has a full field-of-view, providing much more complete descriptions of the scene than perspective images. However, fully-convolutional networks that most current solutions rely on fail to capture rich global contexts from the panorama. To address this issue and also the distortion of equirectangular projection in the panorama, we propose Cubemap Vision Transformers (CViT), a new transformer-based architecture that can model long-range dependencies and extract distortion-free global features from the panorama. We show that cubemap vision transformers have a global receptive field at every stage and can provide globally coherent predictions for spherical signals. As a general architecture, it removes any restriction that has been imposed on the panorama in many other monocular panoramic depth estimation methods. To preserve important local features, we further design a convolution-based branch in our pipeline (dubbed GLPanoDepth) and fuse global features from cubemap vision transformers at multiple scales. This global-to-local strategy allows us to fully exploit useful global and local features in the panorama, achieving state-of-the-art performance in panoramic depth estimation.

Perceptual Information Completion-Based Siamese Omnidirectional Image Quality Assessment Network

Perceptual Information Completion-Based Siamese Omnidirectional Image Quality Assessment Network

Saliency-Guided No-Reference Omnidirectional Image Quality Assessment via Scene Content Perceiving

Saliency-Guided No-Reference Omnidirectional Image Quality Assessment via Scene Content Perceiving

Performance Evaluation of Objective Quality Assessment Methods for Omnidirectional Images Under Emerging Compressions

Performance Evaluation of Objective Quality Assessment Methods for Omnidirectional Images Under Emerging Compressions

Learning Content-Weighted Pseudocylindrical Representation for 360° Image Compression.

Learned 360° image compression methods using equirectangular projection (ERP) often confront a non-uniform sampling issue, inherent to sphere-to-rectangle projection. While uniformly or nearly uniformly sampling representations, along with their corresponding convolution operations, have been proposed to mitigate this issue, these methods often concentrate solely on uniform sampling rates, thus neglecting the content of the image. In this paper, we urge that different contents within 360° images have varying significance and advocate for the adoption of a content-adaptive parametric representation in 360° image compression, which takes into account both the content and sampling rate. We first introduce the parametric pseudocylindrical representation and corresponding convolution operation, upon which we build a learned 360° image codec. Then, we model the hyperparameter of the representation as the output of a network, derived from the image's content and its spherical coordinates. We treat the optimization of hyperparameters for different 360° images as distinct compression tasks and propose a meta-learning algorithm to jointly optimize the codec and the metaknowledge, i.e., the hyperparameter estimation network. A significant challenge is the lack of a direct derivative from the compression loss to the hyperparameter network. To address this, we present a novel method to relax the rate-distortion loss as a function of the hyperparameters, enabling gradient-based optimization of the metaknowledge. Experimental results on omnidirectional images demonstrate that our method achieves state-of-the-art performance and superior visual quality.

Eye Scanpath Prediction-Based No-Reference Quality Assessment of Omnidirectional Images

Eye Scanpath Prediction-Based No-Reference Quality Assessment of Omnidirectional Images

MosaicMVS: Mosaic-Based Omnidirectional Multi-View Stereo for Indoor Scenes

We present MosaicMVS, a novel learning-based depth estimation framework for a mosaic-based omnidirectional multi-view stereo (MVS) camera setup. It uses a regular field of view (FOV) MVS network for an omnidirectional imaging setup with explicit consideration of hypothetical voxel-wise FOV overlaps. The resulting depth predictions are accurate and agree on the omnidirectional multi-view geometry. Unlike existing MVS setups, MosaicMVS camera setup can be easily applied to omnidirectional indoor scenes without having to account for con-straints such as intricate epipolar constraints and the distortion of omnidirectional cameras. We validate the effectiveness of our framework on a new challenging indoor dataset in terms of depth estimation, reconstruction, and view synthesis. We also present new evaluation metric to check reconstruction performance using post-processed masks for accurate evaluation without any ground truth depth map or laser-scanned reconstructions. Experimental results show that our framework outperforms the state-of-the-art MVS methods in a large margin in all test scenes.

Omnidirectional Imaging Sensor Based on Conical Mirror for Pipelines

Omnidirectional Imaging Sensor Based on Conical Mirror for Pipelines

Attentive Deep Image Quality Assessment for Omnidirectional Stitching

Omnidirectional images or videos are commonly generated via the stitching of multiple images or videos, and the quality of omnidirectional stitching strongly influences the quality of experience (QoE) of the generated scenes. Although there were many studies research the omnidirectional image quality assessment (IQA), the evaluation of the omnidirectional stitching quality has not been sufficiently explored. In this paper, we focus on the IQA for the omnidirectional stitching of dual fisheye images. We first establish an omnidirectional stitching image quality assessment (OSIQA) database, which includes 300 distorted images and 300 corresponding reference images generated from 12 raw scenes. The database contains a variety of distortion types caused by omnidirectional stitching, including color distortion, geometric distortion, blur distortion, and ghosting distortion, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">etc.</i> A subjective quality assessment study is conducted on the database and human opinion scores are collected for the distorted omnidirectional images. We then devise a deep learning based objective IQA metric termed Attentive Multi-channel IQA Net. In particular, we extend hyper-ResNet by developing a subnetwork for spatial attention and propose a spatial regularization item. Experimental results show that our proposed FR and NR models achieve the best performance compared with the state-of-the-art FR and NR IQA metrics on the OSIQA database. The OSIQA database as well as the proposed Attentive Multi-channel IQA Net will be released to facilitate future research.

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.

A Method for Generating Network-based Indoor Topology Data using an Omnidirectional Image Dataset

A Method for Generating Network-based Indoor Topology Data using an Omnidirectional Image Dataset