Yizheng Wu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yizheng Wu has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Zhiguo Cao
Huazhong University of Science and Technology, Wuhan, China
5 shared publications - Guosheng Lin
Nanyang technological university, Singapore, Singapore
3 shared publications - Kewei Wang
Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
3 shared publications - Xingyi Li
Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
3 shared publications - Jiahao Cui
Key Laboratory of Image Processing and Intelligent Control, Ministry of Education, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China
2 shared publications - Zhe Wang
SenseAuto, Beijing, China
2 shared publications
Latest Publications
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-15
Synthetic-to-Real Translation for Class-Agnostic Motion Prediction
Motion understanding is critical for ensuring safety and robustness in autonomous driving systems, driving increasing interest in motion prediction. A key challenge in this domain is the high cost associated with acquiring real-world motion labels. It is therefore ideal if we could transfer motion knowledge from synthetic data to real data. In this context, we explore the potential of synthetic-to-real translation for motion prediction (SRMP). However, the most used naive motion regression methods are notably sensitive to the synthetic-to-real domain shift, resulting in unreliable knowledge translation. To address this, we propose a novel approach integrating a motion knowledge translation framework with two key components: (1) objectness-aware motion prediction, which explicitly models the joint distribution of motion patterns and objectness priors to improve domain-invariant feature learning, and (2) objectnessaided motion enhancement, a motion label refinement mechanism that leverages learned objectness priors to filter motion noise. Furthermore, we present a practical pipeline for generating Motion4D, the first synthetic 4D LiDAR dataset tailored for SRMP research, addressing the lack of synthetic motion benchmarks. Experimental results demonstrate that our approach effectively bridges the domain gaps and yields superior performance on real scenes. Code and dataset will be made publicly available.
- 12 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. PP (15209210) , 1-15
Synthetic-to-Real Translation for Class-Agnostic Motion Prediction
Motion understanding is critical for ensuring safety and robustness in autonomous driving systems, driving increasing interest in motion prediction. A key challenge in this domain is the high cost associated with acquiring real-world motion labels. It is therefore ideal if we could transfer motion knowledge from synthetic data to real data. In this context, we explore the potential of synthetic-to-real translation for motion prediction (SRMP). However, the most used naive motion regression methods are notably sensitive to the synthetic-to-real domain shift, resulting in unreliable knowledge translation. To address this, we propose a novel approach integrating a motion knowledge translation framework with two key components: (1) objectness-aware motion prediction, which explicitly models the joint distribution of motion patterns and objectness priors to improve domain-invariant feature learning, and (2) objectnessaided motion enhancement, a motion label refinement mechanism that leverages learned objectness priors to filter motion noise. Furthermore, we present a practical pipeline for generating Motion4D, the first synthetic 4D LiDAR dataset tailored for SRMP research, addressing the lack of synthetic motion benchmarks. Experimental results demonstrate that our approach effectively bridges the domain gaps and yields superior performance on real scenes. Code and dataset will be made publicly available.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10814-10823
iControl3D: An Interactive System for Controllable 3D Scene Generation
3D content creation has long been a complex and time-consuming process, often requiring specialized skills and resources. While recent advancements have allowed for text-guided 3D object and scene generation, they still fall short of providing sufficient control over the generation process, leading to a gap between the user's creative vision and the generated results. In this paper, we present iControl3D, a novel interactive system that empowers users to generate and render customizable 3D scenes with precise control. To this end, a 3D creator interface has been developed to provide users with fine-grained control over the creation process. Technically, we leverage 3D meshes as an intermediary proxy to iteratively merge individual 2D diffusion-generated images into a cohesive and unified 3D scene representation. To ensure seamless integration of 3D meshes, we propose to perform boundary-aware depth alignment before fusing the newly generated mesh with the existing one in 3D space. Additionally, to effectively manage depth discrepancies between remote content and foreground, we propose to model remote content separately with an environment map instead of 3D meshes. Finally, our neural rendering interface enables users to build a radiance field of their scene online and navigate the entire scene. Extensive experiments have been conducted to demonstrate the effectiveness of our system. The code will be made available at https://github.com/xingyi-li/iControl3D.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 10814-10823
Open AccessiControl3D: An Interactive System for Controllable 3D Scene Generation
3D content creation has long been a complex and time-consuming process, often requiring specialized skills and resources. While recent advancements have allowed for text-guided 3D object and scene generation, they still fall short of providing sufficient control over the generation process, leading to a gap between the user's creative vision and the generated results. In this paper, we present iControl3D, a novel interactive system that empowers users to generate and render customizable 3D scenes with precise control. To this end, a 3D creator interface has been developed to provide users with fine-grained control over the creation process. Technically, we leverage 3D meshes as an intermediary proxy to iteratively merge individual 2D diffusion-generated images into a cohesive and unified 3D scene representation. To ensure seamless integration of 3D meshes, we propose to perform boundary-aware depth alignment before fusing the newly generated mesh with the existing one in 3D space. Additionally, to effectively manage depth discrepancies between remote content and foreground, we propose to model remote content separately with an environment map instead of 3D meshes. Finally, our neural rendering interface enables users to build a radiance field of their scene online and navigate the entire scene. Extensive experiments have been conducted to demonstrate the effectiveness of our system. The code will be made available at https://github.com/xingyi-li/iControl3D.
- 5 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 9567-9582
Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches.
- 5 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 46 (12) , 9567-9582
Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8157-8171
Pseudo Label Fusion With Uncertainty Estimation for Semi-Supervised Cropping Box Regression
Cropping box regression algorithms re-frame the images with predicted cropping boxes for better composition quality, which can save considerable manpower and time for massive image retouching work. Yet, recent learning-based cropping box regression algorithms require expert annotations, which makes the scale of training limited. This consequently incurs a performance bottleneck. To address this issue, previous works seek the help from auxiliary datasets of related tasks, e.g. , the composition classification. However, the domain gap between related tasks and the likewise restricted scale of auxiliary datasets are still limiting factors. Hence, our work provides a novel semi-supervised framework that can learn better re-framing knowledge with unlimited unlabeled data. We make use of the unlabeled data via pseudo-labeling, where the model learns from the pseudo labels generated from a temporal ensemble version of itself. To prevent the model learns from its own mistakes, a.k.a . the problem of confirmation bias, we propose to rectify the mistakes by fusing multiple candidate pseudo labels into the better ones. The fusion procedure is based on the uncertainty estimation for each boundary of the candidate cropping boxes. The multiple candidates are from the proposed aesthetic region proposal network. Extensive experimental results explain how the uncertainty-based pseudo label fusion procedure overcomes the confirmation bias and demonstrate the superiority of our semi-supervised cropping box regression framework.
- 13 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 8157-8171
Pseudo Label Fusion With Uncertainty Estimation for Semi-Supervised Cropping Box Regression
Cropping box regression algorithms re-frame the images with predicted cropping boxes for better composition quality, which can save considerable manpower and time for massive image retouching work. Yet, recent learning-based cropping box regression algorithms require expert annotations, which makes the scale of training limited. This consequently incurs a performance bottleneck. To address this issue, previous works seek the help from auxiliary datasets of related tasks, e.g. , the composition classification. However, the domain gap between related tasks and the likewise restricted scale of auxiliary datasets are still limiting factors. Hence, our work provides a novel semi-supervised framework that can learn better re-framing knowledge with unlimited unlabeled data. We make use of the unlabeled data via pseudo-labeling, where the model learns from the pseudo labels generated from a temporal ensemble version of itself. To prevent the model learns from its own mistakes, a.k.a . the problem of confirmation bias, we propose to rectify the mistakes by fusing multiple candidate pseudo labels into the better ones. The fusion procedure is based on the uncertainty estimation for each boundary of the candidate cropping boxes. The multiple candidates are from the proposed aesthetic region proposal network. Extensive experimental results explain how the uncertainty-based pseudo label fusion procedure overcomes the confirmation bias and demonstrate the superiority of our semi-supervised cropping box regression framework.