Data-parallel ray tracing is a crucial technique for rendering large-scale scenes that exceed the memory capacity of a single compute node. It partitions scene data across multiple nodes and accesses remote data through inter-node communication. However, the resulting communication overhead remains a significant bottleneck for practical performance. Existing approaches mitigate this bottleneck by enhancing data locality through dynamic scheduling during rendering, typically employing spatial partitioning to enable access prediction. Although effective in some scenarios, these methods incur significant redundancy in base geometry when applied to large-scale instanced scenes. In this paper, we introduce the first object-space-based dynamic scheduling algorithm, which uses object groups as the scheduling units to eliminate redundant storage of base data in instanced scenes. Additionally, we propose two data access frequency prediction methods to guide asynchronous data prefetching, enhancing rendering efficiency. Compared to the state-of-the-art method, our approach achieves an average rendering speedup of 77.6%, with a maximum improvement of up to 146.1%, while incurring only a 5% increase in scene memory consumption.

Redirected walking (RDW) expands the virtually reachable areas within confined physical spaces by real-walking locomotion. However, existing RDW controllers struggle with extracting spatial features, hindering the improvement for physical obstacle avoidance. To overcome this, we propose a novel spatial walkability-aware redirection controller utilizing deep reinforcement learning (DRL), which learns to enhance obstacle avoidance capability by leveraging comprehensive spatial features. Based on information entropy, we innovatively introduce the spatial walkability entropy (SWE) metric to characterize the walkability and safety of each physical position by assessing the difficulty of reaching its surroundings. Guided by this, we design a novel joint reward that considers both the SWE distribution and the user's virtual-physical alignment, providing ample guidance for learning. Moreover, unlike existing controllers employing traditional reset strategies, we propose a novel reset method that maximizes regional entropy to guide users towards more open areas, reducing the re-collision risk. Extensive simulation experiments compare our controller with state-of-the-art (SOTA) redirection controllers. The results demonstrate that our controller significantly reduces physical collisions across various virtual-physical scenarios. Moreover, live user experiments confirm that our controller offers a superior roaming experience in practical settings.

Redirected walking (RDW) allows users to explore vast virtual spaces by walking in confined real spaces, yet suffers from frequent boundary collisions due to physical constraints. The major solution is to use the reset strategy to steer users away from boundaries. However, most reset methods guide users to fixed spots or follow constant patterns, neglecting spatial features and users' movement trends. In this article, we propose an innovative predictive reset method based on spatial probability density distribution to jointly involve impacts of spatial feature and walking intention for forecasting the user's possible positional distribution, and thereby determines the optimal reset direction by maximizing walking expectation. Given a space, we calculate the stationary layout energy to indicate traveling difficulties of all positions. Meanwhile, we exploit a novel intention inference model to anticipate the probability distribution of the user's presence across adjacent positions. Furthermore, we incorporate the obstacle energy attenuation to predict the obstacle avoidance behaviors. All aforementioned factors are amalgamated into a potential region energy map, and then we integrate energy maps of virtual and real spaces into a fusion energy map to enable the prediction considering both spaces simultaneously. Thus, the optimal reset direction is derived by maximizing the fusion energy. Simulation and user studies are conducted on a broad dataset containing plentiful virtual and real spaces. The results demonstrate that our method effectively reduces the physical collisions and increase the continuous walking distance compared to prevalent reset methods, while exhibiting superior applicability when combined with various RDW controllers.

Recently, self-supervised denoising methods have attracted significant attention due to the considerable challenge posed by constructing a large-scale real noise dataset for supervised training. The most representative self-supervised denoisers are based on blind-spot networks (BSNs), which exclude the central pixel of receptive field. However, excluding any input pixel potentially leads to the loss of vital information required for accurate predictions, especially when the excluded pixel corresponds to the output position. In addition, a standard BSN has struggled to effectively reduce real-world noise due to the spatial correlation of noise, though it makes the significant results with independently distributed synthetic noise. In this paper, we propose a novel self-supervised real-world image denoising framework called Complementary-BSN based on two reciprocal branches (Mask-Map branch and Enhanced-PD-BSN branch) with an efficient loss function to employ the pixels information ignored by masked convolution and provide additional optimization target for self-supervised output. Specifically, we exploit a block-wise random-placing (BRP) scheme for further weaken the noisy correlation to avoid the illusion of image structure recovery due to existing complex noise and make Complementary-BSN more suitable for real noise. Additionally, we develop an efficient strategy (multi-stride PD (MPD)) to fuse multiple PD strides for inference, narrowing the restoration gap between textural and flat regions. Extensive experiments on real-world datasets demonstrate that our method achieves superior performance to other state-of-the-art (SOTA) self-supervised denoising methods. The code is available athttps://github.com/cuijin7382/Complementary-BSN.

Abstract When the lighting conditions are poor and the environmental light is weak, the image captured by the imaging device often has lower brightness and is accompanied by a lot of noise. The paper designs a progressive self‐calibration network model (PSCNet) for recovering high‐quality low‐light‐enhanced images. First, shallow features in low‐light images can be better focused and extracted with the help of attention mechanism. Next, the feature mapping is passed to the encoder and decoder modules, where the transformer and encoder‐decoder jump connection structures can be better combined with the semantic information of the context to learn rich deep feature information. Finally, the self‐calibration module can adaptively cascade the features decoded by the decoder and input them into the residual attention module quickly and accurately. Meanwhile, the LBP features of the image are also fused into the feature information of the residual attention module to enhance the detailed texture information of the image. Qualitative analysis and quantitative comparison of a large number of experimental results show that this method outperforms existing methods.

The poor quality of images recorded in low-light environments affects their further applications. To improve the visibility of low-light images, we propose a recurrent network based on filter-cluster attention (FCA), the main body of which consists of three units: difference concern, gate recurrent, and iterative residual. The network performs multi-stage recursive learning on low-light images, and then extracts deeper feature information. To compute more accurate dependence, we design a novel FCA that focuses on the saliency of feature channels. FCA and self-attention are used to highlight the low-light regions and important channels of the feature. We also design a dense connection pyramid (DenCP) to extract the color features of the low-light inversion image, to compensate for the loss of the image’s color information. Experimental results on six public datasets show that our method has outstanding performance in subjective and quantitative comparisons.

Pansharpening is an important technology for remote sensing imaging systems to obtain high-resolution multispectral (HRMS) images. It mainly obtains high-resolution multi-spectral (HRMS) images with uniform spectral distribution and rich spatial details by fusing low-resolution multi-spectral (LRMS) images and high-spatial-resolution panchromatic (PAN) images. Therefore, how to extract features completely and reconstruct images with high quality is critical to obtain ideal fusion images. In this paper, we propose a new pansharpening method, called the Cross Attention-based Depth Unfolding Iteration Network for Pan-sharpening remote sensing images (CADUI), which achieves the desired fusion effect by iteratively optimizing the deep prior regularization and combining it with a cross-attention mechanism. The network consists of two parts: optimized iterations of deep prior regularization (DEIN-Block) and cross-attention mechanism (CAFM-Block). Among them, DEIN-Block introduces the depth prior as an implicit regularization and improves the adaptability and representation ability of the relevant data of the reconstructed image through iteration. CAFM-Block realizes dual-branch fusion through cross-attention fusion and channel-attention fusion to achieve better fusion results. Simulation experiments and real experiments are carried out on the standard datasets QuikBird (QB) and WorldView-2 (WV2). Through quantitative comparison and qualitative analysis, it is proved that the method is superior to the existing methods.

Semantic segmentation of remotely sensed urban scene images is widely demanded in areas such as land cover mapping, urban change detection, and environmental protection. With the development of deep learning, methods based on convolutional neural networks (CNNs) have been dominant due to their powerful ability to represent hierarchical feature information. However, the limitations of the convolution operation itself limit the network’s ability to extract global contextual information. With the successful use of transformer in computer vision in recent years, transformer has shown great potential for modeling global contextual information. However, transformer is not sufficiently capable of capturing local detailed information. In this article, to explore the potential of the joint CNN and transformer mechanism for semantic segmentation of remotely sensed urban scenes, we propose a CNN and transformer multiscale fusion network (CTMFNet) based on encoding–decoding for urban scene understanding. To couple local–global context information more efficiently, we designed a dual backbone attention fusion module (DAFM) to couple the local and global context information of the dual-branch encoder. In addition, to bridge the semantic gap between scales, we built a multi-layer dense connectivity network (MDCN) as our decoder. The MDCN enables the full flow of semantic information between multiple scales to be fused with each other through upsampling and residual connectivity. We conducted extensive subjective and objective comparison experiments and ablation experiments on both the International Society of Photogrammetry and Remote Sensing (ISPRS) Vaihingen and ISPRS Potsdam datasets. Numerous experimental results have proven the superiority of our method compared to currently popular methods.

Real walking techniques can provide the user with a more natural, highly immersive walking experience compared to the experience of other locomotion techniques. In contrast to the direct mapping between the virtual space and an equal-sized physical space that can be simply realized, the nonequivalent mapping that enables the user to explore a large virtual space by real walking within a confined physical space is complex. To address this issue, the redirected walking (RDW) technique is proposed by many works to adjust the user's virtual and physical movements based on some redirection manipulations. In this manner, subtle or overt motion deviations can be injected between the user's virtual and physical movements, allowing the user to undertake real walking in large virtual spaces by using different redirection controller methods. In this paper, we present a brief review to describe major concepts and methodologies in the field of redirected walking. First, we provide the fundamentals and basic criteria of RDW, and then we describe the redirection manipulations that can be applied to adjust the user's movements during virtual exploration. Furthermore, we clarify the redirection controller methods that properly adopt strategies for combining different redirection manipulations and present a classification of these methods by several categories. Finally, we summarize several experimental metrics to evaluate the performance of redirection controller methods and discuss current challenges and future work. Our study systematically classifies the relevant theories, concepts, and methods of RDW, and provides assistance to the newcomers in understanding and implementing the RDW technique.

Redirected walking (RDW) enables users to explore large virtual spaces by real walking in small real spaces. How to effectively reduce physical collisions and decrease user perceptions of redirection are important for most RDW methods. This article proposes a segmented redirection mapping method to calculate and map the roadmap of a large virtual space with inner obstacles to a mapped roadmap within a small real space. We adopt a Voronoi-based pruning method to extract the roadmap of the virtual space and design an RDW platform to interactively modify the virtual roadmap. We propose a roadmap mapping method based on divide-and-conquer and dynamic planning strategies to subdivide the virtual roadmap into several sub-virtual roads that are mapped individually. By recording connections of different sub-virtual roads, our method is applicable to virtual roadmaps with loop structures. During mapping, we apply the reset and redirection gains of the RDW technique as optimal aims and restrict conditions to obtain the mapped roadmap, which has small path curving and contains as few resets as possible. By real walking along the mapped roadmap, users perceive moving along the virtual roadmap to explore the entire virtual space. The experiment shows that our method works effectively for various virtual spaces with or without inner obstacles. Furthermore, our method is flexible in obtaining mapped roadmaps of different real spaces when the virtual space is fixed. Compared to prevalent RDW methods, our method can significantly reduce physical boundary collisions and maintain user experience of virtual roaming.

Abstract In realistic low‐light environments, images captured by imaging devices often have problems such as low brightness and low contrast, serious loss of detail information, and a large amount of noise, posing major challenges to computer vision tasks. Low‐light image enhancement can effectively improve the overall quality of the image, which has important significance and application value. In this study, an attention‐based multi‐channel feature fusion enhancement network (M‐FFENet) is proposed to process low‐light images. In this network, a feature extraction model is first used to obtain the deep features of the downsampled low‐light images and fit them to an affine bilateral grid. Second, the addition of attention‐based residual dense blocks (ARDB) allows the network to focus on more details and spatial information. Meanwhile, all color channels are considered. The channel features and bilateral meshes are then linearly interpolated using the feature reconfiguration model (FRM) to obtain high‐quality features containing rich color and texture information. Next, the feature fusion module (FFM) is used to fuse features that contain different information. Enhancement model is used to further recover texture and detail in the image. Finally, the enhanced image is output. Numerous experimental results have shown that the method achieves better results in both quantitative and qualitative aspects compared to other methods.

The curvature gain of redirected walking method enables users to explore virtual spaces that are larger than real spaces. The estimation of human sensitivity for curvature gain is important for redirected walking. Herein, we conduct two experiments under different path conditions. By adopting the psychophysical “method of limits” to be a new approach, the first experiment re-estimates the sensitivity for a curved path and further proves that people are more sensitive for right-curved paths than left-curved paths. The second experiment investigates the characteristics of preorder paths on the sensitivity to postorder paths, and finds that the existing of preorder paths significantly increases the sensitivity for the postorder path. Moreover, we find an interesting moderation effect on the direction consistency of preorder and postorder paths: the larger curved preorder path can significantly decrease the sensitivity for postorder path when they have the same direction. If their directions diverge, the effect of preorder path is not significant.

Low‐rank approximation has shown great potential in various image tasks. It is found that there is a specific functional relationship about singular values between the original image and a series of noisy images, which can be used to construct the singular values of a noise‐free image. In this study, the authors propose a novel denoising method based on the above facts and low‐rank approximation theory. Firstly, they estimate the noise energy distribution of the group matrix in the singular value decomposition (SVD) domain using the energy characteristics of the image with different noise levels. The energy distribution of the noise is shrunk to obtain the energy distribution of the true signal. Then, based on the optimal energy compaction property of SVD, the low‐rank property of matrix is constrained in the SVD domain to obtain the low‐rank approximation of the matrix. Moreover, an iterative back projection method is adopted in this study to suppress residual noise. A new noise standard deviation estimation approach, targeted at the back projection process, is proposed to effectively optimise the denoising results during the iteration. Experimental results show that the authors’ method efficiently decreases the noise and achieves comparable denoising performance to the state‐of‐the‐art methods regarding both quantitative measurement and visual effect.

Natural image priors play an important role in image denoising, and various prior-based methods have been widely proposed for noise removal. However, these methods tend to smooth the fine image textures while suppressing noise, degrading the image visual quality. To address this problem, in this paper, we propose an adaptive texture-preserving denoising method. In contrast to most existing prior-based denoising methods, two types of priors [gradient histogram matching priors and nonlocal self-similarity (NSS) priors] are proposed, and their combination is used for image denoising. We introduce a hyper-Laplacian distribution of the gradient histogram matching prior, which enforces the gradient histogram of the denoised image to be as close as possible to the estimated reference histogram from the original image. Meanwhile, the proposed model obtained by introducing the NSS priors effectively preserves fine image details and generates sharp image edges. To improve the accuracy of the method, a content-adaptive parameter selection scheme based on edge detection filters is proposed. Moreover, the optimization problem with two types of priors and the content-adaptive parameter added into the objective function becomes a challenging non-convex optimization problem. To effectively solve this problem, we have developed a new numerical solution based on augmented Lagrangian multipliers and alternating minimization scheme. The experimental results demonstrate that the proposed method effectively preserves the texture features of the denoised images and outperforms several variational methods and other state-of-the-art methods in terms of various evaluation indices and visual quality, especially at medium and high noise levels.