Ning Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ning Li has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Haifeng Zhao
School of Computer Science and Technology, Anhui University, Hefei, Anhui, China
5 shared publications - Mingwei Cao
Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei 230601, China
5 shared publications - Feng Xue
School of Software, Hefei University of Technology, Hefei, China
2 shared publications - Qiuju Wang
School of Computer Science and Technology, Anhui University, China
2 shared publications - Zhihan Lv
School of Computer Science and Technology, Xidian University, Xian, China
2 shared publications - Ruijun Liu
Beihang University
1 shared publication
Latest Publications
- Open Access
- 30 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
UMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions
Deep learning-based multi-view stereo (MVS) techniques have advanced substantially in recent years. However, because large-scale, annotated datasets are limited, interest has grown in unsupervised MVS methods that do not require ground-truth depth. One primary challenge for these unsupervised approaches is handling occluded regions, as they rely on photometric consistency. To address these issues, we propose Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions (UMVS). Our UMVS comprises three core modules. First, a feature-level perceptual consistency module minimizes reconstruction errors by comparing high-level semantic feature disparities across images. Second, a structured occlusion-generation module improves depth estimation accuracy and completeness by generating augmented samples tailored for contrastive learning. Third, the DLA-Net module serves as a normalization component to overcome the limitations of a narrow receptive field. By aggregating global contextual information, DLA-Net improves depth map estimation accuracy. We evaluated the proposed UMVS on the DTU and Tanks & Temples datasets, and the results demonstrate its effectiveness and superiority.
- 30 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
Open AccessUMVS: Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions
Deep learning-based multi-view stereo (MVS) techniques have advanced substantially in recent years. However, because large-scale, annotated datasets are limited, interest has grown in unsupervised MVS methods that do not require ground-truth depth. One primary challenge for these unsupervised approaches is handling occluded regions, as they rely on photometric consistency. To address these issues, we propose Unsupervised Multi-View Stereo for Large-Scale Scenes With Heavy Occlusions (UMVS). Our UMVS comprises three core modules. First, a feature-level perceptual consistency module minimizes reconstruction errors by comparing high-level semantic feature disparities across images. Second, a structured occlusion-generation module improves depth estimation accuracy and completeness by generating augmented samples tailored for contrastive learning. Third, the DLA-Net module serves as a normalization component to overcome the limitations of a narrow receptive field. By aggregating global contextual information, DLA-Net improves depth map estimation accuracy. We evaluated the proposed UMVS on the DTU and Tanks & Temples datasets, and the results demonstrate its effectiveness and superiority.
- Open Access
PSATM: Planar Structure Awareness-Based Texture Mapping for 3D Reconstruction of Photovoltaic Scenes
In the field of 3D reconstruction for photovoltaic scenes, current texture mapping techniques frequently encounter significant texture segmentation and apparent joins in uniform plane regions, such as solar panels, because they lack geometric structural assumptions. To tackle these challenges, we introduce a new texture-mapping strategy for 3D solar panel scene reconstruction that focuses on planar structure awareness. We term the proposed method PSATM. Initially, we suggest a global constraint and a local refinement process to incorporate clear geometric structure details. This process automatically detects and labels planar regions through a region-growing approach. Next, we integrate a planar structure-aware module into the smoothness term of the Markov Random Field (MRF) energy function. This module uses dihedral angles and plane membership to adjust label transition costs, enhancing texture coherence within planar regions and maintaining smooth transitions at genuine geometric breaks. Furthermore, we establish a boundary treatment technique relying on local geometric support. This method combines area-based weighting and normal consistency to modify erroneous labels, successfully removing small remnants and smoothing texture edges. We tested the proposed PSATM with texture patch counts and visual quality measures on actual solar panel scenes. The results indicate that the proposed PSATM considerably reduces texture segmentation errors and improves texture flow and overall visual quality compared to the existing method.
Open AccessPSATM: Planar Structure Awareness-Based Texture Mapping for 3D Reconstruction of Photovoltaic Scenes
In the field of 3D reconstruction for photovoltaic scenes, current texture mapping techniques frequently encounter significant texture segmentation and apparent joins in uniform plane regions, such as solar panels, because they lack geometric structural assumptions. To tackle these challenges, we introduce a new texture-mapping strategy for 3D solar panel scene reconstruction that focuses on planar structure awareness. We term the proposed method PSATM. Initially, we suggest a global constraint and a local refinement process to incorporate clear geometric structure details. This process automatically detects and labels planar regions through a region-growing approach. Next, we integrate a planar structure-aware module into the smoothness term of the Markov Random Field (MRF) energy function. This module uses dihedral angles and plane membership to adjust label transition costs, enhancing texture coherence within planar regions and maintaining smooth transitions at genuine geometric breaks. Furthermore, we establish a boundary treatment technique relying on local geometric support. This method combines area-based weighting and normal consistency to modify erroneous labels, successfully removing small remnants and smoothing texture edges. We tested the proposed PSATM with texture patch counts and visual quality measures on actual solar panel scenes. The results indicate that the proposed PSATM considerably reduces texture segmentation errors and improves texture flow and overall visual quality compared to the existing method.
- 2 August 2026
- Published by Springer Nature
- p. 313-325
DOMVS: Unsupervised Multi-view Stereo for Dealing With Occlusion Scenes
- 2 August 2026
- Published by Springer Nature
- p. 313-325
DOMVS: Unsupervised Multi-view Stereo for Dealing With Occlusion Scenes
- Open Access
- 20 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (5) , 1-22
APMVS: Learning Multi-View Stereo Based on Adjacent Stage and Pair-Wise Stage Uncertainty Estimation
Many multi-view stereo (MVS) networks with a cascaded structure can effectively estimate depth while saving memory. However, the accuracy of the depth map in the fine stage depends on the depth map estimated in the coarse stage. Additionally, the multi-stage depth maps generated by the cascaded structure are used to compute losses but are not reused, resulting in a loss of inter-stage differentiation information. To address these issues, we propose a dual-uncertainty estimation MVS method that learns an MVS network based on adjacent stage and pair-wise stage uncertainty estimation, named APMVS. The core of the proposed APMVS is to employ dual-uncertainty estimation to mitigate the adverse effects of the cascaded structure. Specifically, it involves two estimation modules: adjacent stage uncertainty (ASU) and pair-wise stage uncertainty (PSU). The ASU estimation module dynamically adjusts the depth-hypothesis range by leveraging uncertainty from the previous stage, thereby improving the accuracy of depth-map prediction in the current stage. The PSU estimation module estimates the uncertainty between each pair of stages. Thus, regions with high uncertainty have minimal impact. We evaluate the proposed APMVS on the DTU, Tanks and Temples, and BlendedMVS datasets. Experimental results show that our method achieves superior reconstruction quality compared with other state-of-the-art methods.
- 20 April 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Multimedia Computing, Communications, and Applications
- Vol. 22 (5) , 1-22
Open AccessAPMVS: Learning Multi-View Stereo Based on Adjacent Stage and Pair-Wise Stage Uncertainty Estimation
Many multi-view stereo (MVS) networks with a cascaded structure can effectively estimate depth while saving memory. However, the accuracy of the depth map in the fine stage depends on the depth map estimated in the coarse stage. Additionally, the multi-stage depth maps generated by the cascaded structure are used to compute losses but are not reused, resulting in a loss of inter-stage differentiation information. To address these issues, we propose a dual-uncertainty estimation MVS method that learns an MVS network based on adjacent stage and pair-wise stage uncertainty estimation, named APMVS. The core of the proposed APMVS is to employ dual-uncertainty estimation to mitigate the adverse effects of the cascaded structure. Specifically, it involves two estimation modules: adjacent stage uncertainty (ASU) and pair-wise stage uncertainty (PSU). The ASU estimation module dynamically adjusts the depth-hypothesis range by leveraging uncertainty from the previous stage, thereby improving the accuracy of depth-map prediction in the current stage. The PSU estimation module estimates the uncertainty between each pair of stages. Thus, regions with high uncertainty have minimal impact. We evaluate the proposed APMVS on the DTU, Tanks and Temples, and BlendedMVS datasets. Experimental results show that our method achieves superior reconstruction quality compared with other state-of-the-art methods.
- 22 March 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (5) , 215
SpatioGS: spatiotemporal-aware density control for dynamic scene rendering with Gaussian splatting
- 22 March 2026
- Published by Springer Nature in The Visual Computer
- Vol. 42 (5) , 215
SpatioGS: spatiotemporal-aware density control for dynamic scene rendering with Gaussian splatting