Rui 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
Research Subjects
Rui Li has a total of 102 co-authors. Here are the top co-authors by number of shared publications:
Jinqiu Sun
4 shared publicationsYanning Zhang
4 shared publications- Yanning Zhang
Northwestern Polytechnical University
4 shared publications Yu Zhu
4 shared publications- Jiaqi Yang
Northwestern Polytechnical University
3 shared publications - Jinqiu Sun
School of Astronautics, Northwestern Polytechnical University, Xian, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12358-12366
SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12358-12366
Open AccessSalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation
- 13 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-15
Disentangling Global Orientation with Test-Time Rectification for Unsupervised Non-rigid Point Cloud Correspondence
Unsupervised non-rigid point cloud correspondence aims to identify dense matches between deformable point cloud pairs without ground truth annotations. While existing methods effectively handle shape deformations, they often struggle under complex global orientation changes involving large rotation angles and arbitrary rotation axes. In this paper, we propose a robust test-time point cloud correspondence method that disentangles complex orientation changes from non-rigid shape deformation. We achieve this by modeling global orientation changes as rigid transformations via deformation-invariant priors from pre-trained models to disentangle complex orientation changes while remaining insensitive to shape deformation. Moreover, to resolve symmetry ambiguities induced by complex orientation changes, we augment point clouds with rotational symmetry transformations along learned axes to capture subtle disambiguating cues. To evaluate the impact of arbitrary and complex orientation changes, we construct corrupted versions of existing datasets encompassing varying rotation scales and axes. Extensive experiments reveal the effectiveness of our proposed method.
- 13 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-15
Disentangling Global Orientation with Test-Time Rectification for Unsupervised Non-rigid Point Cloud Correspondence
Unsupervised non-rigid point cloud correspondence aims to identify dense matches between deformable point cloud pairs without ground truth annotations. While existing methods effectively handle shape deformations, they often struggle under complex global orientation changes involving large rotation angles and arbitrary rotation axes. In this paper, we propose a robust test-time point cloud correspondence method that disentangles complex orientation changes from non-rigid shape deformation. We achieve this by modeling global orientation changes as rigid transformations via deformation-invariant priors from pre-trained models to disentangle complex orientation changes while remaining insensitive to shape deformation. Moreover, to resolve symmetry ambiguities induced by complex orientation changes, we augment point clouds with rotational symmetry transformations along learned axes to capture subtle disambiguating cues. To evaluate the impact of arbitrary and complex orientation changes, we construct corrupted versions of existing datasets encompassing varying rotation scales and axes. Extensive experiments reveal the effectiveness of our proposed method.
- 26 February 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 203, 8-14
VoMarkSplat: Robust watermarking for 3D Gaussian splatting with patch and multi-convolutional voting
- 26 February 2026
- Published by Elsevier in Pattern Recognition Letters
- Vol. 203, 8-14
VoMarkSplat: Robust watermarking for 3D Gaussian splatting with patch and multi-convolutional voting
- 16 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7526-7539
Robust Context Modeling for Unsupervised Non-Rigid Point Cloud Correspondence
We address the “long-range ambiguity” problem for unsupervised non-rigid point cloud correspondence, where corresponding points own inconsistent features while different local regions are spatially or geometrically similar. Previous methods struggle with this problem, since local reference frames (LRF) or coordinate-based methods struggle to exclude locally similar or spatially near mismatches, and widely used independent geometric relations might be inconsistent under non-rigid deformation, introducing extra ambiguity. To this end, we propose a novel robust context modeling module (RCM) to alleviate long-range ambiguity in two aspects: 1) RCM tackles the ambiguity problem by introducing inter-relation attention (IRA), which mines robust cues from the interplay between relative geometric relations. 2) RCM enhances features with accessible long-range information from IRAs, following a local-to-global manner. Our method shows significant improvements in multiple benchmarks, with accurate correspondence over rotation and large deformation perturbation. Specifically, our method achieves a new state-of-the-art performance with correspondence accuracy of 33.9% and mean error of 4.2 on the SURREAL benchmark.
- 16 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (6) , 7526-7539
Robust Context Modeling for Unsupervised Non-Rigid Point Cloud Correspondence
We address the “long-range ambiguity” problem for unsupervised non-rigid point cloud correspondence, where corresponding points own inconsistent features while different local regions are spatially or geometrically similar. Previous methods struggle with this problem, since local reference frames (LRF) or coordinate-based methods struggle to exclude locally similar or spatially near mismatches, and widely used independent geometric relations might be inconsistent under non-rigid deformation, introducing extra ambiguity. To this end, we propose a novel robust context modeling module (RCM) to alleviate long-range ambiguity in two aspects: 1) RCM tackles the ambiguity problem by introducing inter-relation attention (IRA), which mines robust cues from the interplay between relative geometric relations. 2) RCM enhances features with accessible long-range information from IRAs, following a local-to-global manner. Our method shows significant improvements in multiple benchmarks, with accurate correspondence over rotation and large deformation perturbation. Specifically, our method achieves a new state-of-the-art performance with correspondence accuracy of 33.9% and mean error of 4.2 on the SURREAL benchmark.
- 12 May 2025
- Published by Springer Nature
- p. 248-266
TRICKY 2024 Challenge on Monocular Depth from Images of Specular and Transparent Surfaces
- 12 May 2025
- Published by Springer Nature
- p. 248-266
TRICKY 2024 Challenge on Monocular Depth from Images of Specular and Transparent Surfaces
- Open Access
The Third Monocular Depth Estimation Challenge
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.
Open AccessThe Third Monocular Depth Estimation Challenge
This paper discusses the results of the third edition of the Monocular Depth Estimation Challenge (MDEC). The challenge focuses on zero-shot generalization to the challenging SYNS-Patches dataset, featuring complex scenes in natural and indoor settings. As with the previous edition, methods can use any form of supervision, i.e. supervised or self-supervised. The challenge received a total of 19 submissions outperforming the baseline on the test set: 10 among them submitted a report describing their approach, highlighting a diffused use of foundational models such as Depth Anything at the core of their method. The challenge winners drastically improved 3D F-Score performance, from 17.51% to 23.72%.
- Open Access
Unveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios
Monocular depth estimation from RGB images plays a pivotal role in 3D vision. However, its accuracy can deteriorate in challenging environments such as nighttime or adverse weather conditions. While long-wave infrared cameras offer stable imaging in such challenging conditions, they are inherently low-resolution, lacking rich texture and semantics as delivered by the RGB image. Current methods focus solely on a single modality due to the difficulties to identify and integrate faithful depth cues from both sources. To address these issues, this paper presents a novel approach that identifies and integrates dominant cross-modality depth features with a learning-based framework. Concretely, we independently compute the coarse depth maps with separate networks by fully utilizing the individual depth cues from each modality. As the advantageous depth spreads across both modalities, we propose a novel confidence loss steering a confidence predictor network to yield a confidence map specifying latent potential depth areas. With the resulting confidence map, we propose a multi-modal fusion network that fuses the final depth in an end-to-end manner. Harnessing the proposed pipeline, our method demonstrates the ability of robust depth estimation in a variety of difficult scenarios. Experimental results on the challenging MS$^2$ and ViViD++ datasets demonstrate the effectiveness and robustness of our method.
Open AccessUnveiling the Depths: A Multi-Modal Fusion Framework for Challenging Scenarios
Monocular depth estimation from RGB images plays a pivotal role in 3D vision. However, its accuracy can deteriorate in challenging environments such as nighttime or adverse weather conditions. While long-wave infrared cameras offer stable imaging in such challenging conditions, they are inherently low-resolution, lacking rich texture and semantics as delivered by the RGB image. Current methods focus solely on a single modality due to the difficulties to identify and integrate faithful depth cues from both sources. To address these issues, this paper presents a novel approach that identifies and integrates dominant cross-modality depth features with a learning-based framework. Concretely, we independently compute the coarse depth maps with separate networks by fully utilizing the individual depth cues from each modality. As the advantageous depth spreads across both modalities, we propose a novel confidence loss steering a confidence predictor network to yield a confidence map specifying latent potential depth areas. With the resulting confidence map, we propose a multi-modal fusion network that fuses the final depth in an end-to-end manner. Harnessing the proposed pipeline, our method demonstrates the ability of robust depth estimation in a variety of difficult scenarios. Experimental results on the challenging MS$^2$ and ViViD++ datasets demonstrate the effectiveness and robustness of our method.
- 19 January 2023
- Published by Elsevier in Pattern Recognition
- Vol. 137
Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance
- 19 January 2023
- Published by Elsevier in Pattern Recognition
- Vol. 137
Learning depth via leveraging semantics: Self-supervised monocular depth estimation with both implicit and explicit semantic guidance
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 5626-5637
Self-Supervised Monocular Depth Estimation With Frequency-Based Recurrent Refinement
Self-supervised monocular depth estimation has succeeded in learning scene geometry from only image pairs or sequences. However, it is still highly ill-posed for self-supervised depth estimation to generate high-quality depth maps with both global high accuracy and local fine details. To address this issue, we propose a novel frequency-based recurrent refinement scheme to improve the self-supervised depth estimation. Since the global and local depth representation can be correlated to high/low frequency coefficients in the frequency domain, we propose a frequency-based recurrent depth coefficient refinement (RDCR) scheme, which progressively refines both low frequency and high frequency depth coefficients with an RNN-based architecture in a multi-level manner. During the recurrent process, the depth coefficients generated from the previous time step are used as the input to generate the current depth coefficients, yielding progressively optimized depth estimations. Meanwhile, considering that the depth details often appear in areas with high image frequency, we further improve depth details during the RDCR process by leveraging the image-based high frequency components. Specifically, in each RDCR module, we enhance the high frequency depth representations by selecting and feeding the informative image-based high frequency features with a learned feature weighting mask. Extensive experiments show that the proposed method achieves globally accurate estimation with fine local details, outperforming other self-supervised methods in both quantitative and qualitative comparisons.
- 8 August 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 25 (15209210) , 5626-5637
Self-Supervised Monocular Depth Estimation With Frequency-Based Recurrent Refinement
Self-supervised monocular depth estimation has succeeded in learning scene geometry from only image pairs or sequences. However, it is still highly ill-posed for self-supervised depth estimation to generate high-quality depth maps with both global high accuracy and local fine details. To address this issue, we propose a novel frequency-based recurrent refinement scheme to improve the self-supervised depth estimation. Since the global and local depth representation can be correlated to high/low frequency coefficients in the frequency domain, we propose a frequency-based recurrent depth coefficient refinement (RDCR) scheme, which progressively refines both low frequency and high frequency depth coefficients with an RNN-based architecture in a multi-level manner. During the recurrent process, the depth coefficients generated from the previous time step are used as the input to generate the current depth coefficients, yielding progressively optimized depth estimations. Meanwhile, considering that the depth details often appear in areas with high image frequency, we further improve depth details during the RDCR process by leveraging the image-based high frequency components. Specifically, in each RDCR module, we enhance the high frequency depth representations by selecting and feeding the informative image-based high frequency features with a learned feature weighting mask. Extensive experiments show that the proposed method achieves globally accurate estimation with fine local details, outperforming other self-supervised methods in both quantitative and qualitative comparisons.
- 1 December 2021
- Published by Elsevier in Pattern Recognition
- Vol. 120
Non-uniform motion deblurring with blurry component divided guidance
- 1 December 2021
- Published by Elsevier in Pattern Recognition
- Vol. 120
Non-uniform motion deblurring with blurry component divided guidance