Tao Li
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
Tao Li has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Xiucheng Dong
Xihua University
5 shared publicationsHongwei Lin
3 shared publicationsQunbing Zhou
3 shared publications- Honggang Chen
College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China
2 shared publications Songning Luo
2 shared publicationsTing Hu
School of Electrical Engineering and Electronic Information, Xihua University, Chengdu, China
2 shared publications
Latest Publications
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 16486-16501
Geometric Locality Preserving Vision Mamba for Image-Guided Depth Completion
- 1 November 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (11) , 16486-16501
Geometric Locality Preserving Vision Mamba for Image-Guided Depth Completion
- Open Access
- 1 November 2024
- Published by China Science Publishing & Media Ltd. in Journal of Computer-Aided Design & Computer Graphics
- Vol. 36 (11) , 1710-1718
Single Depth Map Completion with Multiple Auxiliary Tasks
The aim of depth map completion is to restore dense depth maps from sparse depth maps. To address the problems of edge blurring and semantic information missing in current algorithms, we propose a single depth map completion algorithm based on multiple auxiliary tasks. The completion strategy used in our algorithms is coarse-to-refine, where the coarse completion sub-network uses selective kernel convolution to effectively extract the input information, and the refine completion sub-network consists of a depth map completion master task and related auxiliary tasks. The grayscale reconstruction auxiliary task aims to learn rich semantic information from grayscale images, and then transfer the learned semantic information to depth map completion master task by a feature fusion branch to alleviate the problems of details missing and structure blending. The edge prediction auxiliary task focuses on improving accuracy and sharpness of depth edge. The feature fusion branch between the depth map completion master task and grayscale reconstruction auxiliary task mainly uses spatial and channel attention mechanisms to achieve adaptive fusion of multi-task features to enhance relevant features and suppress irrelevant features. The experiments on the NYUv2 dataset show that the proposed algorithm has better visual completion performance. And our RMSE and REL in the case of 200 sampling points is 0.199 and 0.033, respectively, which outperforms the comparison algorithms.
- 1 November 2024
- Published by China Science Publishing & Media Ltd. in Journal of Computer-Aided Design & Computer Graphics
- Vol. 36 (11) , 1710-1718
Open AccessSingle Depth Map Completion with Multiple Auxiliary Tasks
The aim of depth map completion is to restore dense depth maps from sparse depth maps. To address the problems of edge blurring and semantic information missing in current algorithms, we propose a single depth map completion algorithm based on multiple auxiliary tasks. The completion strategy used in our algorithms is coarse-to-refine, where the coarse completion sub-network uses selective kernel convolution to effectively extract the input information, and the refine completion sub-network consists of a depth map completion master task and related auxiliary tasks. The grayscale reconstruction auxiliary task aims to learn rich semantic information from grayscale images, and then transfer the learned semantic information to depth map completion master task by a feature fusion branch to alleviate the problems of details missing and structure blending. The edge prediction auxiliary task focuses on improving accuracy and sharpness of depth edge. The feature fusion branch between the depth map completion master task and grayscale reconstruction auxiliary task mainly uses spatial and channel attention mechanisms to achieve adaptive fusion of multi-task features to enhance relevant features and suppress irrelevant features. The experiments on the NYUv2 dataset show that the proposed algorithm has better visual completion performance. And our RMSE and REL in the case of 200 sampling points is 0.199 and 0.033, respectively, which outperforms the comparison algorithms.
- 9 May 2024
- Published by Springer Nature in Multimedia Tools and Applications
- p. 1-23
CLGFormer: Cross-Level-Guided transformer for RGB-D semantic segmentation
- 9 May 2024
- Published by Springer Nature in Multimedia Tools and Applications
- p. 1-23
CLGFormer: Cross-Level-Guided transformer for RGB-D semantic segmentation
- 2 February 2024
- Published by Elsevier in Pattern Recognition
- Vol. 150
A transformer-CNN parallel network for image guided depth completion
- 2 February 2024
- Published by Elsevier in Pattern Recognition
- Vol. 150
A transformer-CNN parallel network for image guided depth completion
- 26 June 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (8) , 10463-10481
Gated Recurrent Fusion UNet for Depth Completion
- 26 June 2023
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (8) , 10463-10481
Gated Recurrent Fusion UNet for Depth Completion
- Open Access
- 24 January 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (1) , e0280886
SPNet: Structure preserving network for depth completion
Depth completion aims to predict a dense depth map from a sparse one. Benefiting from the powerful ability of convolutional neural networks, recent depth completion methods have achieved remarkable performance. However, it is still a challenging problem to well preserve accurate depth structures, such as tiny structures and object boundaries. To tackle this problem, we propose a structure preserving network (SPNet) in this paper. Firstly, an efficient multi-scale gradient extractor (MSGE) is proposed to extract useful multi-scale gradient images, which contain rich structural information that is helpful in recovering accurate depth. The MSGE is constructed based on the proposed semi-fixed depthwise separable convolution. Meanwhile, we adopt a stable gradient MAE loss (LGMAE) to provide additional depth gradient constrain for better structure reconstruction. Moreover, a multi-level feature fusion module (MFFM) is proposed to adaptively fuse the spatial details from low-level encoder and the semantic information from high-level decoder, which will incorporate more structural details into the depth modality. As demonstrated by experiments on NYUv2 and KITTI datasets, our method outperforms some state-of-the-art methods in terms of both quantitative and quantitative evaluations.
- 24 January 2023
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 18 (1) , e0280886
Open AccessSPNet: Structure preserving network for depth completion
Depth completion aims to predict a dense depth map from a sparse one. Benefiting from the powerful ability of convolutional neural networks, recent depth completion methods have achieved remarkable performance. However, it is still a challenging problem to well preserve accurate depth structures, such as tiny structures and object boundaries. To tackle this problem, we propose a structure preserving network (SPNet) in this paper. Firstly, an efficient multi-scale gradient extractor (MSGE) is proposed to extract useful multi-scale gradient images, which contain rich structural information that is helpful in recovering accurate depth. The MSGE is constructed based on the proposed semi-fixed depthwise separable convolution. Meanwhile, we adopt a stable gradient MAE loss (LGMAE) to provide additional depth gradient constrain for better structure reconstruction. Moreover, a multi-level feature fusion module (MFFM) is proposed to adaptively fuse the spatial details from low-level encoder and the semantic information from high-level decoder, which will incorporate more structural details into the depth modality. As demonstrated by experiments on NYUv2 and KITTI datasets, our method outperforms some state-of-the-art methods in terms of both quantitative and quantitative evaluations.
- 1 November 2020
- Published by Elsevier in Pattern Recognition
- Vol. 107
Depth image super-resolution using correlation-controlled color guidance and multi-scale symmetric network
- 1 November 2020
- Published by Elsevier in Pattern Recognition
- Vol. 107
Depth image super-resolution using correlation-controlled color guidance and multi-scale symmetric network
- Open Access
- 7 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 122695-122708
Guided Depth Map Super-Resolution Using Recumbent Y Network
Low spatial resolution is a well-known problem for depth maps captured by low-cost consumer depth cameras. Depth map super-resolution (SR) can be used to enhance the resolution and improve the quality of depth maps. In this paper, we propose a recumbent Y network (RYNet) to integrate the depth information and intensity information for depth map SR. Specifically, we introduce two weight-shared encoders to respectively learn multi-scale depth and intensity features, and a single decoder to gradually fuse depth information and intensity information for reconstruction. We also design a residual channel attention based atrous spatial pyramid pooling structure to further enrich the feature’s scale diversity and exploit the correlations between multi-scale feature channels. Furthermore, the violations of co-occurrence assumption between depth discontinuities and intensity edges will generate texture-transfer and depth-bleeding artifacts. Thus, we propose a spatial attention mechanism to mitigate the artifacts by adaptively learning the spatial relevance between intensity features and depth features and reweighting the intensity features before fusion. Experimental results demonstrate the superiority of the proposed RYNet over several state-of-the-art depth map SR methods.
- 7 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 122695-122708
Open AccessGuided Depth Map Super-Resolution Using Recumbent Y Network
Low spatial resolution is a well-known problem for depth maps captured by low-cost consumer depth cameras. Depth map super-resolution (SR) can be used to enhance the resolution and improve the quality of depth maps. In this paper, we propose a recumbent Y network (RYNet) to integrate the depth information and intensity information for depth map SR. Specifically, we introduce two weight-shared encoders to respectively learn multi-scale depth and intensity features, and a single decoder to gradually fuse depth information and intensity information for reconstruction. We also design a residual channel attention based atrous spatial pyramid pooling structure to further enrich the feature’s scale diversity and exploit the correlations between multi-scale feature channels. Furthermore, the violations of co-occurrence assumption between depth discontinuities and intensity edges will generate texture-transfer and depth-bleeding artifacts. Thus, we propose a spatial attention mechanism to mitigate the artifacts by adaptively learning the spatial relevance between intensity features and depth features and reweighting the intensity features before fusion. Experimental results demonstrate the superiority of the proposed RYNet over several state-of-the-art depth map SR methods.
- Open Access
- 31 March 2020
- Published by Emerald Publishing in APSIPA Transactions on Signal and Information Processing
- Vol. 9 (1)
Color-gamut mapping in the non-uniform CIE-1931 space with perceptual hue fidelity constraints for SMPTE ST.2094-40 standard
As high-dynamic range (HDR) and wide-color gamut (WCG) contents become more and more popular in multimedia markets, color mapping of the distributed contents to different rendering devices plays a pivotal role in HDR distribution eco-systems. The widely used and economic gamut-clipping (GC)-based techniques perform poorly in mapping WCG contents to narrow gamut devices; and high-performance color-appearance model (CAM)-based techniques are computationally expensive to commercial applications. In this paper, we propose a novel color gamut mapping (CGM) algorithm to solve the problem. By introducing a color transition/protection zone (TPZ) and a set of perceptual hue fidelity constraints into the CIE-1931 space, the proposed algorithm directly carries out CGM in the perceptually non-uniform space, thus greatly decreases the computational complexity. The proposed TPZ effectively achieves a reasonable compromise between saturation preserving and details protection in out-of-gamut colors. The proposed hue fidelity constraints reference the measurements of human subjects' visual responses, thus effectively preserve the perceptual hue of the original colors. Experimental results show that the proposed algorithm clearly outperforms the GC-CGM, and performs similarly or better than the expensive CAM-CGM. The proposed algorithm is real-time and hardware friendly. It is an important supplement of the SMPTE ST.2094-40 standard.
- 31 March 2020
- Published by Emerald Publishing in APSIPA Transactions on Signal and Information Processing
- Vol. 9 (1)
Open AccessColor-gamut mapping in the non-uniform CIE-1931 space with perceptual hue fidelity constraints for SMPTE ST.2094-40 standard
As high-dynamic range (HDR) and wide-color gamut (WCG) contents become more and more popular in multimedia markets, color mapping of the distributed contents to different rendering devices plays a pivotal role in HDR distribution eco-systems. The widely used and economic gamut-clipping (GC)-based techniques perform poorly in mapping WCG contents to narrow gamut devices; and high-performance color-appearance model (CAM)-based techniques are computationally expensive to commercial applications. In this paper, we propose a novel color gamut mapping (CGM) algorithm to solve the problem. By introducing a color transition/protection zone (TPZ) and a set of perceptual hue fidelity constraints into the CIE-1931 space, the proposed algorithm directly carries out CGM in the perceptually non-uniform space, thus greatly decreases the computational complexity. The proposed TPZ effectively achieves a reasonable compromise between saturation preserving and details protection in out-of-gamut colors. The proposed hue fidelity constraints reference the measurements of human subjects' visual responses, thus effectively preserve the perceptual hue of the original colors. Experimental results show that the proposed algorithm clearly outperforms the GC-CGM, and performs similarly or better than the expensive CAM-CGM. The proposed algorithm is real-time and hardware friendly. It is an important supplement of the SMPTE ST.2094-40 standard.
- 1 August 2019
- Published by Elsevier in Neurocomputing
- Vol. 355, 105-120
Single image super-resolution incorporating example-based gradient profile estimation and weighted adaptive p-norm
- 1 August 2019
- Published by Elsevier in Neurocomputing
- Vol. 355, 105-120
Single image super-resolution incorporating example-based gradient profile estimation and weighted adaptive p-norm