Naiyao Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Naiyao Wang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Hongbo Liu
College of Artificial Intelligence, Dalian Maritime University, Dalian, China
5 shared publications Changdong Zhou
2 shared publicationsBo Zhang
1 shared publication- Bo Zhang
College of Artificial Intelligence, Dalian Maritime University, Dalian, China
1 shared publication - Bolin Song
College of Artificial Intelligence, Dalian Maritime University, Dalian 116026, People’s Republic of China
1 shared publication - Changdong Zhou
College of Artificial Intelligence, Dalian Maritime University, Dalian, 116026, China
1 shared publication
Latest Publications
- 8 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Unifying day and night: Towards all-time image deraining via joint prior representation learning
- 8 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Unifying day and night: Towards all-time image deraining via joint prior representation learning
- 14 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109103
HIVE: A hypergraph-based game-theoretic interactive value decomposition engine for multi-lateral agents collaboration
- 14 May 2026
- Published by Elsevier in Neural Networks
- Vol. 203, 109103
HIVE: A hypergraph-based game-theoretic interactive value decomposition engine for multi-lateral agents collaboration
- 12 May 2026
- Published by Elsevier in Ocean Engineering
- Vol. 359
BI-PIPE: Brain-inspired brisk inference pathway intention prediction for embodied navigation of unmanned surface vessel
- 12 May 2026
- Published by Elsevier in Ocean Engineering
- Vol. 359
BI-PIPE: Brain-inspired brisk inference pathway intention prediction for embodied navigation of unmanned surface vessel
- Open Access
- 1 May 2026
- Published by Elsevier in Digital Communications and Networks
- Vol. 12 (8) , 1233-1246
NEEM: A Neighborhood Entropy Energy-Based Model for High-Dimensional Data Distribution Estimation in Intelligent Communication Networks
- 1 May 2026
- Published by Elsevier in Digital Communications and Networks
- Vol. 12 (8) , 1233-1246
Open AccessNEEM: A Neighborhood Entropy Energy-Based Model for High-Dimensional Data Distribution Estimation in Intelligent Communication Networks
- Open Access
- 19 September 2025
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (3) , 035059
Physics-inspired self-learning framework for unsupervised depth estimation on non-Lambertian surfaces
The prediction of scene depth from monocular images has become crucial in fields such as spatial perception and computer vision. However, unsupervised depth estimation methods based on view synthesis often ignore the significant impact of non-Lambertian surfaces and ghosting artifacts. In this study, we propose a self-learning depth reconstruction framework. This framework introduces a depth consistency loss to compensate for the failure of the photometric assumption in non-Lambertian regions. Additionally, we design an intrinsic consistency loss that leverages variance as a game-theoretic strategy to ensure the robustness of our model. Finally, we introduce a physics-inspired ghosting mask to eliminate ghosting artifacts. We also design a multi-path transformer layer that integrates the Transformer’s global dependency modeling capability into CNNs, thereby enhancing the model’s performance. Experimental results show that our model demonstrates excellent performance in non-Lambertian regions. Compared with state-of-the-art methods that merely rely on the photometric assumption, our method achieves average improvements of 9.29% and 2.86% on the Sq Rel and RMSE metrics across three network models. Furthermore, it exhibits outstanding zero-shot generalization capability on external datasets. The source code is available at https://github.com/IkeFwd/Icdepth.
- 19 September 2025
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (3) , 035059
Open AccessPhysics-inspired self-learning framework for unsupervised depth estimation on non-Lambertian surfaces
The prediction of scene depth from monocular images has become crucial in fields such as spatial perception and computer vision. However, unsupervised depth estimation methods based on view synthesis often ignore the significant impact of non-Lambertian surfaces and ghosting artifacts. In this study, we propose a self-learning depth reconstruction framework. This framework introduces a depth consistency loss to compensate for the failure of the photometric assumption in non-Lambertian regions. Additionally, we design an intrinsic consistency loss that leverages variance as a game-theoretic strategy to ensure the robustness of our model. Finally, we introduce a physics-inspired ghosting mask to eliminate ghosting artifacts. We also design a multi-path transformer layer that integrates the Transformer’s global dependency modeling capability into CNNs, thereby enhancing the model’s performance. Experimental results show that our model demonstrates excellent performance in non-Lambertian regions. Compared with state-of-the-art methods that merely rely on the photometric assumption, our method achieves average improvements of 9.29% and 2.86% on the Sq Rel and RMSE metrics across three network models. Furthermore, it exhibits outstanding zero-shot generalization capability on external datasets. The source code is available at https://github.com/IkeFwd/Icdepth.
- 19 December 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 130
SOFT: Self-supervised sparse Optical Flow Transformer for video stabilization via quaternion
- 19 December 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 130
SOFT: Self-supervised sparse Optical Flow Transformer for video stabilization via quaternion
- 30 October 2023
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 43 (3) , 305-329
DUEL: Depth visUal Ego-motion Learning for autonomous robot obstacle avoidance
Reliable obstacle avoidance, which is essential for safe autonomous robot interaction with the real world, raises various challenges such as difficulties with obstacle perception and latent factor cognition impacting multi-modal obstacle avoidance. In this paper, we propose a Depth visUal Ego-motion Learning (DUEL) model, consisting of a cognitive generation network, a policy decision network and a potential partition network, to learn autonomous obstacle avoidance from expert policies. The DUEL model takes advantage of binocular vision to perceive scene depth. This serves as the input to the cognitive generation network which generates obstacle avoidance policies by maximizing its causal entropy. The policy decision network then optimizes the generation of the policies referring to expert policies. The generated obstacle avoidance policies are simultaneously transferred to the potential partition network to capture the latent factors contained within expert policies and perform multi-modal obstacle avoidance. These three core networks iteratively optimize the multi-modal policies relying on causal entropy and mutual information theorems, which are proven theoretically. Experimental comparisons with state-of-the-art models on 7 metrics demonstrate the effectiveness of the DUEL model. It achieves the best performance with an average ADE (Average Displacement Error) of 0.29 and average FDE (Final Displacement Error) of 0.55 across five different scenarios. Results show that the DUEL model can maintain an average obstacle avoidance success rate of 97% for both simulated and real world scenarios with multiple obstacles, demonstrating its success at capturing latent factors from expert policies. Our source codes are available at https://github.com/ACoTAI/DUEL .
- 30 October 2023
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 43 (3) , 305-329
DUEL: Depth visUal Ego-motion Learning for autonomous robot obstacle avoidance
Reliable obstacle avoidance, which is essential for safe autonomous robot interaction with the real world, raises various challenges such as difficulties with obstacle perception and latent factor cognition impacting multi-modal obstacle avoidance. In this paper, we propose a Depth visUal Ego-motion Learning (DUEL) model, consisting of a cognitive generation network, a policy decision network and a potential partition network, to learn autonomous obstacle avoidance from expert policies. The DUEL model takes advantage of binocular vision to perceive scene depth. This serves as the input to the cognitive generation network which generates obstacle avoidance policies by maximizing its causal entropy. The policy decision network then optimizes the generation of the policies referring to expert policies. The generated obstacle avoidance policies are simultaneously transferred to the potential partition network to capture the latent factors contained within expert policies and perform multi-modal obstacle avoidance. These three core networks iteratively optimize the multi-modal policies relying on causal entropy and mutual information theorems, which are proven theoretically. Experimental comparisons with state-of-the-art models on 7 metrics demonstrate the effectiveness of the DUEL model. It achieves the best performance with an average ADE (Average Displacement Error) of 0.29 and average FDE (Final Displacement Error) of 0.55 across five different scenarios. Results show that the DUEL model can maintain an average obstacle avoidance success rate of 97% for both simulated and real world scenarios with multiple obstacles, demonstrating its success at capturing latent factors from expert policies. Our source codes are available at https://github.com/ACoTAI/DUEL .