Intuitive motion control is essential for virtual reality, allowing users to manipulate objects naturally while receiving realistic and responsive visual feedback. 3D Gaussian splatting provides real-time, photorealistic scene rendering, making it promising for virtual reality applications. Still, it falls short in accurate motion control of dynamic objects due to its unstructured global motion representation and redundant motion learning. To address these problems, we propose a motion hierarchical Gaussian based dynamic control method. First, a motion hierarchical Gaussian representation is introduced and initialized with semantic and deformation information. Then a motion hierarchical decomposition method is proposed to optimize the local motion in the representation. The representation is next optimized by a local motion analysis based refinement method. We also design a set of motion control operations for the motion hierarchical Gaussian. Experimental results show that our method achieves high-precision motion reconstruction, accurate motion decomposition, real-time, intuitively and immersive VR motion control.

Transferring existing Human-Object Interaction (HOI) motion to novel objects is essential for robotics, virtual reality. Traditional approaches only model spatial surface correspondences between humans and source objects or between source and target objects, ignoring the internal topological structures of humans, the internal topology of objects, the non-surface spatial topological relationships, and temporal motion relations. In this paper, we propose a spatial-temporal relation guided motion transfer framework. Firstly, we define a spatial-temporal relation interaction graph representation(STRIG) to model the human internal topology, object internal topology and human-object global topology together with the temporal motion relation. We propose a STRIGs-guided motion transfer diffusion model for generating spatially, semantically and temporally consistent HOI motions that are adapted to novel objects. To tackle the absence of ground-truth motions after transfer, we introduce a spatial-temporal relation optimization strategy. Extensive experiments demonstrate that our method consistently outperforms other approaches in terms of motion transfer quality, performance, and sequence stability, with particularly robustness under large variations in target object topology.

Object grouping task is an important research direction for fast manipulation of a large number of objects. It can help users to improve the efficiency of multi-object manipulation. However, the current research on this aspect is still immature. For this task, in this paper, based on the brush metaphor, we propose a method for grouping objects based on bare hands in virtual reality scenes. We design a number of interactions to facilitate the user's grouping of objects in the three-dimensional virtual space. Object grouping in virtual reality could encompass two subtasks: group generation and group modification. The emphasis of these tasks varies, with the former focusing on creating groups from ungrouped objects and the latter focusing on modifying group members once they are generated. The results of the empirical study show that our method has better performance in accomplishing both sub-tasks compared to the Ray method, Screen method and Cone method.

Rendering quality and performance greatly affect the user's immersion in VR experiences. 3D Gaussian Splatting-based methods can achieve photo-realistic rendering with speeds of over 100 fps in static scenes, but the speed drops below 10 fps in monocular dynamic scenes. Foveated rendering provides a possible solution to accelerate rendering without compromising visual perceptual quality. However, 3DGS and foveated rendering are not compatible. In this paper, we propose Fov-GS, a foveated 3D Gaussian splatting method for rendering dynamic scenes in real time. We introduce a 3D Gaussian forest representation that represents the scene as a forest. To construct the 3D Gaussian forest, we propose a 3D Gaussian forest initialization method based on dynamic-static separation. Subsequently, we propose a 3D Gaussian forest optimization method based on deformation field and Gaussian decomposition to optimize the forest and deformation field. To achieve real-time dynamic scene rendering, we present a 3D Gaussian forest rendering method based on HVS models. Experiments demonstrate that our method not only achieves higher rendering quality in the foveal and salient regions compared to the SOTA methods but also dramatically improves rendering performance, achieving up to 11.33X speedup. We also conducted a user study, and the results prove that the perceptual quality of our method has a high visual similarity with the ground truth.

3D scene graph generation is essential for spatial computing in Extended Reality (XR), providing structured semantics for task planning and intelligent perception. However, unlike instance-segmentation-driven setups, generating semantic scene graphs still suffer from limited accuracy due to coarse and noisy point cloud data typically acquired in practice, and from the lack of interactive strategies to incorporate users' spatialized and intuitive guidance. We identify three key challenges: designing controllable interaction forms, involving guidance in inference, and generalizing from local corrections. To address these, we propose SGSG, a Stroke-Guided Scene Graph generation method that enables users to interactively refine 3D semantic relationships and improve predictions in real time. We propose three types of strokes and a lightweight SGstrokes dataset tailored for this modality. Our model integrates stroke guidance representation and injection for spatio-temporal feature learning and reasoning correction, along with intervention losses that combine consistency-repulsive and geometry-sensitive constraints to enhance accuracy and generalization. Experiments and the user study show that SGSG outperforms state-of-the-art methods 3DSSG and SGFN in overall accuracy and precision, surpasses JointSSG in predicate-level metrics, and reduces task load across all control conditions, establishing SGSG as a new benchmark for interactive 3D scene graph generation and semantic understanding in XR. Implementation resources are available at: https://github.com/Sycamore-Ma/SGSG-runtime.

Passive haptics utilize the shape of a physical object to convey feedback to the user and enhance immersion in virtual reality. Haptic retargeting is a passive haptic interaction method. Its mapping of physical objects to virtual objects solves the matching problem between virtual and physical objects in the passive haptic method. However, most existing haptic retargeting methods improve efficiency without considering the important factor of user comfort. In this article, we propose an efficient and comfortable haptic retargeting method based on reset point optimization. First, we construct two maps indicating user interaction comfort: the RULA score map and the dominant hand gain map. Subsequently, we propose a reset point optimization algorithm based on these two maps. Moreover, we also optimize the selection of the physical proxy and the placement location when the reset occurs. The user study results show a significant improvement in the efficiency and comfort of our method compared to state-of-the-art methods.

In extended reality (XR) applications, enhancing user perception often necessitates head-mounted display (HMD) removal. However, existing methods suffer from low time performance and suboptimal reconstruction quality. In this paper, we propose a half face mapping 3D Gaussian splatting avatar based HMD removal method (HFM-GS), which can perform real-time and high-fidelity online restoration of the complete face in HMD-occluded videos for XR applications after a short un-occluded face registration. We establish a mapping field between the upper and lower face Gaussians to enhance the adaptability to deformation. Then, we introduce correlation weight-based sampling to improve time performance and handle variations in the number of Gaussians. At last, we ensure model robustness through Gaussian Segregation Strategy. Compared to two state-of-the-art methods, our method achieves better quality and time performance. The results of the user study show that fidelity is significantly improved with our method.

Rendering animatable and realistic hand avatars is pivotal for enhancing user experiences in human-centered AR/VR applications. While recent initiatives have utilized neural radiance fields to forge hand avatars with lifelike appearances, these methods are often hindered by high computational demands and the necessity for extensive training views. In this paper, we introduce GaussianHand, the first Gaussian-based real-time 3D rendering approach that enables efficient free-view and free-pose hand avatar animation from sparse view images. Our approach encompasses two key innovations. We first propose Hand Gaussian Blend Shapes that effectively models hand surface geometry while ensuring consistent appearance across various poses. Second, we introduce the Neural Residual Skeleton, equipped with Residual Skinning Weights, designed to rectify inaccuracies involved in Linear Blend Skinning deformations due to geometry offsets. Experiments demonstrate that our method not only achieves far more realistic rendering quality with as few as 5 or 20 training views, compared to the 139 views required by existing methods, but also excels in efficiency, achieving up to 125 frames per second for real-time rendering and remarkably surpassing recent methods.

The demand for fluid simulation and rendering in virtual reality (VR) is increasing. However, achieving high visual quality while maintaining real-time efficiency remains a challenge. Traditional foveated rendering methods balance the simulation quality in the foveated region but neglect the physical realism in the peripheral areas, and fail to account for the perceptual degradation caused by frame rate fluctuations during adaptive updates. To address these challenges, we propose a novel visual perception driven fluid rendering method ViP-Fluid, which further enhances rendering quality while balancing efficiency. Our approach employs a spatiotemporal saliency model for multi-granularity simulation and rendering of Lagrangian fluid systems, and introduces a Perception Threshold for Physical Process Elapsing (PTPE) metric, which guides our temporal acceleration strategy. Through a series of objective experiments, we demonstrate the advantages of our method in rendering quality and performance efficiency. ViP-Fluid demonstrates superior metrics not only in the foveated region but also in the salient and overall regions, achieving up to 2.15 times speed-up compared to the high-resolution Position Based Fluids (PBF) benchmark. Subsequent user experiments further validate the visual perception advantages of ViP-Fluid over both traditional and state-of-the-art methods, confirming the spatiotemporal fidelity of our acceleration strategy as well as a user preference for our approach.

We propose a new scene-aware foveated rendering method, which incorporates the scene awareness and characteristics of the human visual system into the mapping-based foveated rendering framework. First, we generate the conservative visual importance map that encodes the visual features of the scene, visual acuity, and gaze motion. Second, we construct the pixel size control map using a convolution kernel method. Third, we utilize the pixel size control map to guide the foveated rendering. At last, a temporal coherent refinement strategy is used to maintain the smooth foveated rendering for the adjacent frames. Compared to the state-of-the-art mapping-based foveated rendering methods using the same compression ratio, our method achieves smaller MSE, higher PSNR, and SSIM in the fovea, periphery, salient regions, and the whole image. We also conducted user studies, and the results proved that the perceptual quality of our method has a high visual similarity with the around truth rendered with the full resolution.

Neural radiance fields (NeRF) has achieved revolutionary breakthrough in the novel view synthesis task for complex 3D scenes. However, this new paradigm struggles to meet the requirements for real-time rendering and high perceptual quality in virtual reality. In this paper, we propose VPRF, a novel visual perceptual based radiance fields representation method, which for the first time integrates the visual acuity and contrast sensitivity models of human visual system (HVS) into the radiance field rendering framework. Initially, we encode both the appearance and visual sensitivity information of the scene into our radiance field representation. Then, we propose a visual perceptual sampling strategy, allocating computational resources according to the HVS sensitivity of different regions. Finally, we propose a sampling weight-constrained training scheme to ensure the effectiveness of our sampling strategy and improve the representation of the radiance field based on the scene content. Experimental results demonstrate that our method renders more efficiently, with higher PSNR and SSIM in the foveal and salient regions compared to the state-of-the-art FoV-NeRF. The results of the user study confirm that our rendering results exhibit high-fidelity visual perception.

Foveated rendering provides an idea for accelerating rendering algorithms without sacrificing the perceived rendering quality in virtual reality applications. In this paper, we propose a foveated stochastic lightcuts method to render high-quality many-lights illumination effects in high perception-sensitive regions. First, we introduce a spatiotemporal-luminance based lightcuts generation method to generate lightcuts with different accuracy for different visual perception-sensitive regions. Then we propose a multi-resolution light samples selection method to select the light sample for each node in the lightcuts more efficiently. Our method supports full-dynamic scenes containing over 250k dynamic light sources and dynamic diffuse/specular/glossy objects. It provides frame rates up to 110fps for high-quality many-lights illumination effects in high perception-sensitive regions of the HVS in VR HMDs. Compared with the state-of-the-art stochastic lightcuts method using the same rendering time, our method achieves smaller mean squared errors in the fovea and periphery. We also conduct user studies to prove that the perceived quality of our method has a high visual similarity with the results of the ground truth rendered by using the stochastic lightcuts with 2048 light samples per pixel.