arXiv subjects

Shaoyu Cai

Publications and source records attributed to Shaoyu Cai.

4 recordsLinked to original sources

arXiv2026

Geometry beneath the Waves: Dense Priors for Sparse-View Underwater 3D Gaussian Splatting

Underwater 3D reconstruction supports applications ranging from marine ecosystem monitoring and subsea inspection to underwater archaeology, education, and immersive visualisation. 3D Gaussian Splatting has made real-time photorealistic novel-view rendering practical, while underwater variants incorporate physically based image-formation models to separate medium effects from scene radiance. Their reconstruction quality, however, remains fundamentally limited by the geometry used for initialisation.

cs.CV↗

arXiv2026

EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality

Immersive virtual reality (VR) applications demand accurate, temporally coherent full-body pose tracking. Recent head-mounted camera-based approaches show promise in egocentric pose estimation, but encounter challenges when applied to VR head-mounted displays (HMDs), including temporal instability, inaccurate lower-body estimation, and the lack of real-time performance. To address these limitations, we present EgoPoseVR, an end-to-end framework for accurate egocentric full-body pose estimation in VR that integrates headset motion cues with egocentric RGB-D observations through a dual-modality fusion pipeline. A spatiotemporal encoder extracts frame- and joint-level representations, which are fused via cross-attention to fully exploit complementary motion cues across modalities. A kinematic optimization module then imposes constraints from HMD signals, enhancing the accuracy and stability of pose estimation. To facilitate training and evaluation, we introduce a large-scale synthetic dataset of over 1.8 million temporally aligned HMD and RGB-D frames across diverse VR scenarios. Experimental results show that EgoPoseVR outperforms state-of-the-art egocentric pose estimation models. A user study in real-world scenes further shows that EgoPoseVR achieved significantly higher subjective ratings in accuracy, stability, embodiment, and intention for future use compared to baseline methods. These results show that EgoPoseVR enables robust full-body pose tracking, offering a practical solution for accurate VR embodiment without requiring additional body-worn sensors or room-scale tracking systems.

cs.CV↗

arXiv2024

ViboPneumo: A Vibratory-Pneumatic Finger-Worn Haptic Device for Altering Perceived Texture Roughness in Mixed Reality

Extensive research has been done in haptic feedback for texture simulation in virtual reality (VR). However, it is challenging to modify the perceived tactile texture of existing physical objects which usually serve as anchors for virtual objects in mixed reality (MR). In this paper, we present ViboPneumo, a finger-worn haptic device that uses vibratory-pneumatic feedback to modulate (i.e., increase and decrease) the perceived roughness of the material surface contacted by the user's fingerpad while supporting the perceived sensation of other haptic properties (e.g., temperature or stickiness) in MR. Our device includes a silicone-based pneumatic actuator that can lift the user's fingerpad on the physical surface to reduce the contact area for roughness decreasing, and an on-finger vibrator for roughness increasing. Our user-perception experimental results showed that the participants could perceive changes in roughness, both increasing and decreasing, compared to the original material surface. We also observed the overlapping roughness ratings among certain haptic stimuli (i.e., vibrotactile and pneumatic) and the originally perceived roughness of some materials without any haptic feedback. This suggests the potential to alter the perceived texture of one type of material to another in terms of roughness (e.g., modifying the perceived texture of ceramics as glass). Lastly, a user study of MR experience showed that ViboPneumo could significantly improve the MR user experience, particularly for visual-haptic matching, compared to the condition of a bare finger. We also demonstrated a few application scenarios for ViboPneumo.

cs.HC↗

arXiv2021

Visual-Tactile Cross-Modal Data Generation using Residue-Fusion GAN with Feature-Matching and Perceptual Losses

Existing psychophysical studies have revealed that the cross-modal visual-tactile perception is common for humans performing daily activities. However, it is still challenging to build the algorithmic mapping from one modality space to another, namely the cross-modal visual-tactile data translation/generation, which could be potentially important for robotic operation. In this paper, we propose a deep-learning-based approach for cross-modal visual-tactile data generation by leveraging the framework of the generative adversarial networks (GANs). Our approach takes the visual image of a material surface as the visual data, and the accelerometer signal induced by the pen-sliding movement on the surface as the tactile data. We adopt the conditional-GAN (cGAN) structure together with the residue-fusion (RF) module, and train the model with the additional feature-matching (FM) and perceptual losses to achieve the cross-modal data generation. The experimental results show that the inclusion of the RF module, and the FM and the perceptual losses significantly improves cross-modal data generation performance in terms of the classification accuracy upon the generated data and the visual similarity between the ground-truth and the generated data.

cs.CV↗