Ying Wang

Ms. Ying Wang


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2024 in Aerospace
Verified
Journal Article
Open access
PDF file
TFTao Fu
Tao Fu
YZYu Zhou
Yu Zhou
YWYing Wang
Ying Wang
Jian LiuJian Liu
Jian Liu
ZZZhang Zhang
Zhang Zhang
CBChen Bo
Chen Bo
As space technology advances, an increasing number of spacecrafts are being launched into space, making it essential to monitor and maintain satellites to ensure safe and stable operations. Acquiring 3D information of space targets enables the accurate assessment of their shape, size, and surface damage, providing critical support for on-orbit service activities. Existing 3D reconstruction techniques for space targets, which mainly rely on laser point cloud measurements or image sequences, cannot adapt to scenarios with limited observation data and viewpoints. We propose a novel method to achieve a high-quality 3D reconstruction of space targets. The proposed approach begins with a preliminary 3D reconstruction using the neural radiance field (NeRF) model, guided by observed optical images of the space target and depth priors extracted from a customized monocular depth estimation network (MDE). A NeRF is then employed to synthesize optical images from unobserved viewpoints. The corresponding depth information for these viewpoints, derived from the same depth estimation network, is integrated as a supervisory signal to iteratively refine the 3D reconstruction. By exploiting MDE and the NeRF, the proposed scheme iteratively optimizes the 3D reconstruction of spatial objects from seen viewpoints to unseen viewpoints. To minimize excessive noise from unseen viewpoints, we also incorporate a confident modeling mechanism with relative depth ranking loss functions. Experimental results demonstrate that the proposed method achieves superior 3D reconstruction quality under sparse input, outperforming traditional NeRF and DS-NeRF models in terms of perceptual quality and geometric accuracy.

24 January 2025 in Sensors
Verified
Journal Article
Open access
PDF file
YWYing Wang
Ying Wang
TFTao Fu
Tao Fu
YZYu Zhou
Yu Zhou
QKQinglei Kong
Qinglei Kong
WYWenshuai Yu
Wenshuai Yu
CBChen Bo
Chen Bo
Oblique photogrammetry imagery often suffers from uneven resolution and blurred details, leading to poor surface texture quality in 3D reconstructions, particularly for building facades. To address these challenges, we propose a novel Attention-Frequency Edge-Enhanced 3D Texture Enhancement Network (TENet) and introduce a comprehensive 3D texture enhancement pipeline. This pipeline applies 2D texture super-resolution techniques to 3D models for fine-grained texture restoration, enhancing the surface texture quality. TENet leverages attention mechanisms and frequency-domain techniques to improve texture sharpness and edge accuracy. Our approach includes a Region-Resolution Adaptive Enhancement Module (RAEM) and a Frequency-Domain Edge Enhancement Mechanism (FDEEM) to enhance local details and restore critical edge features. The experimental results demonstrate that TENet outperforms existing methods, significantly improving texture quality and 3D reconstruction performance. Ablation studies confirmed the effectiveness of each component in enhancing 3D texture reconstruction. The network is validated for real-world applications, showing its ability to significantly reduce edge artifacts and restore clear, accurate textures in real-world 3D surface models.