Zhi Zheng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhi Zheng has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Yi Wan
Wuhan University
5 shared publications - Yongjun Zhang
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
5 shared publications Mingtao Xiong
2 shared publications- Xinyi Liu
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
2 shared publications - Xuejun Huang
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
2 shared publications Yingying Pei
2 shared publications
Latest Publications
- 14 October 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 243, 281-295
SkySplat++: Hierarchical 3D Gaussian Splatting for generalizable sparse-view reconstruction from multi-temporal satellite imagery
- 14 October 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 243, 281-295
SkySplat++: Hierarchical 3D Gaussian Splatting for generalizable sparse-view reconstruction from multi-temporal satellite imagery
- Open Access
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 14820-14833
Three-Dimensional Reconstruction From a Single Satellite Image via Iterative RGB-D Completion
Reconstructing 3D scenes from a single satellite image remains challenging because reliable metric depth is unavailable and many regions are occluded, which limits the geometric observability and appearance evidence required for faithful reconstruction. To address these issues, we propose SSRecon, a diffusion-driven framework for single-image satellite 3D reconstruction via iterative RGB-D completion. SSRecon fits the RPC model to a pinhole approximation, estimates depth with a language-conditioned diffusion model, and performs RGB and depth inpainting using Stable Diffusion and a step-segmented gradient-guidance scheme, respectively. The input image together with the estimated depth forms the first RGB-D frame to initialize a 3D Gaussian Splatting representation, which is then refined by repeatedly rendering novel views, completing missing regions, and updating the scene representation. Experiments on DFC2019 and SpaceNet4 show that SSRecon improves perceptual realism and cross-view consistency across diverse target poses without auxiliary semantics or height inputs. In the pure single-image setting, SSRecon increases CLIP-Score by 0.65 on DFC2019 and 0.76 on SpaceNet4 over the strongest baseline, with consistent gains in CLIP-IQA quality and sharpness.
- 23 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19 (19391404) , 14820-14833
Open AccessThree-Dimensional Reconstruction From a Single Satellite Image via Iterative RGB-D Completion
Reconstructing 3D scenes from a single satellite image remains challenging because reliable metric depth is unavailable and many regions are occluded, which limits the geometric observability and appearance evidence required for faithful reconstruction. To address these issues, we propose SSRecon, a diffusion-driven framework for single-image satellite 3D reconstruction via iterative RGB-D completion. SSRecon fits the RPC model to a pinhole approximation, estimates depth with a language-conditioned diffusion model, and performs RGB and depth inpainting using Stable Diffusion and a step-segmented gradient-guidance scheme, respectively. The input image together with the estimated depth forms the first RGB-D frame to initialize a 3D Gaussian Splatting representation, which is then refined by repeatedly rendering novel views, completing missing regions, and updating the scene representation. Experiments on DFC2019 and SpaceNet4 show that SSRecon improves perceptual realism and cross-view consistency across diverse target poses without auxiliary semantics or height inputs. In the pure single-image setting, SSRecon increases CLIP-Score by 0.65 on DFC2019 and 0.76 on SpaceNet4 over the strongest baseline, with consistent gains in CLIP-IQA quality and sharpness.
- Open Access
- 14 February 2026
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 146
Three-dimensional time series building reconstruction framework in global south based on openly available satellite data
- 14 February 2026
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 146
Open AccessThree-dimensional time series building reconstruction framework in global south based on openly available satellite data
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 31409-31426
LOSC: Optical-SAR Image Registration Based on Local Oriented Scale Contour Feature Descriptor
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 19, 31409-31426
Open AccessLOSC: Optical-SAR Image Registration Based on Local Oriented Scale Contour Feature Descriptor
- Open Access
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 21200-21212
Mamba-LCD: Robust Urban Change Detection in Low-Light Remote Sensing Images
Remote sensing-based urban change detection has seen substantial progress with the development of deep learning. Nevertheless, its performance under low-light imaging conditions, such as nighttime, twilight, and cloudy or rainy weather, remains limited due to image degradation, reduced contract, and weak spatial features. To address these challenges, we propose MambaLCD, a novel change detection method that integrates a Siamese visual state space encoder, a bi-temporal feature fusion module, and a mask decoder. The encoder captures spatial dependencies via multi-directional state-space scanning, while the fusion module enhances semantic consistency through illumination-aware recalibration. The decoder integrates multi-scale features using attention-inspired pooling for precise pixel-level change masks. Comprehensive experiments on three benchmark datasets including S2Looking, WHU-CD and LEVIR-CD demonstrate the effectiveness of Mamba-LCD. Specifically, on the low-lightdominated S2Looking dataset, Mamba-LCD outperforms 10 state-of-the-art CNN-, Transformer-, and Mamba-based methods, surpassing the previous best results by 0.73 and 1.58, respectively. Moreover, it maintains competitive performance on LEVIR-CD and WHU-CD under normal lighting. We further conducted ablation studies to evaluate the impact of different activation functions and fusion strategies. The results suggest the robustness and adaptability of Mamba-LCD, indicating its potential for urban monitoring across diverse illumination scenarios.
- 1 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 21200-21212
Open AccessMamba-LCD: Robust Urban Change Detection in Low-Light Remote Sensing Images
Remote sensing-based urban change detection has seen substantial progress with the development of deep learning. Nevertheless, its performance under low-light imaging conditions, such as nighttime, twilight, and cloudy or rainy weather, remains limited due to image degradation, reduced contract, and weak spatial features. To address these challenges, we propose MambaLCD, a novel change detection method that integrates a Siamese visual state space encoder, a bi-temporal feature fusion module, and a mask decoder. The encoder captures spatial dependencies via multi-directional state-space scanning, while the fusion module enhances semantic consistency through illumination-aware recalibration. The decoder integrates multi-scale features using attention-inspired pooling for precise pixel-level change masks. Comprehensive experiments on three benchmark datasets including S2Looking, WHU-CD and LEVIR-CD demonstrate the effectiveness of Mamba-LCD. Specifically, on the low-lightdominated S2Looking dataset, Mamba-LCD outperforms 10 state-of-the-art CNN-, Transformer-, and Mamba-based methods, surpassing the previous best results by 0.73 and 1.58, respectively. Moreover, it maintains competitive performance on LEVIR-CD and WHU-CD under normal lighting. We further conducted ablation studies to evaluate the impact of different activation functions and fusion strategies. The results suggest the robustness and adaptability of Mamba-LCD, indicating its potential for urban monitoring across diverse illumination scenarios.
- Open Access
- 12 June 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 131
A context-structural feature decoupling change detection network for detecting earthquake-triggered damage
- 12 June 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 131
Open AccessA context-structural feature decoupling change detection network for detecting earthquake-triggered damage
- 9 January 2024
- Published by Wiley in The Photogrammetric Record
- Vol. 39 (185) , 36-66
Digital surface model generation from high‐resolution satellite stereos based on hybrid feature fusion network
- 9 January 2024
- Published by Wiley in The Photogrammetric Record
- Vol. 39 (185) , 36-66
Digital surface model generation from high‐resolution satellite stereos based on hybrid feature fusion network
- Open Access
- 5 January 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 127
Robust registration of multi-modal remote sensing images based on multi-dimensional oriented self-similarity features
- 5 January 2024
- Published by Elsevier in International Journal of Applied Earth Observation and Geoinformation
- Vol. 127
Open AccessRobust registration of multi-modal remote sensing images based on multi-dimensional oriented self-similarity features
- Open Access
- 3 October 2019
- Published by Nanyang Technological University
Interactive view-dependent rendering over networks
- 3 October 2019
- Published by Nanyang Technological University
Open AccessInteractive view-dependent rendering over networks