no code implementations • 3 Jun 2025 • Haoyuan Wang, Chen Liu, Minh-Ngoc Tran, Chao Wang
This paper introduces a novel multivariate volatility modeling framework, named Long Short-Term Memory enhanced BEKK (LSTM-BEKK), that integrates deep learning into multivariate GARCH processes.
no code implementations • 15 Apr 2025 • Yanrui Bin, WenBo Hu, Haoyuan Wang, Xinya Chen, Bing Wang
Surface normal estimation serves as a cornerstone for a spectrum of computer vision applications.
no code implementations • 18 Mar 2025 • Rui Yang, Jiayi Tong, Haoyuan Wang, Hui Huang, Ziyang Hu, Peiyu Li, Nan Liu, Christopher J. Lindsell, Michael J. Pencina, Yong Chen, Chuan Hong
The random forest classifier achieved AUROC 0. 692 with LLM-driven scores, improving to 0. 733 with semantic embeddings and 0. 747 with article usage metrics.
no code implementations • 17 Feb 2025 • Haoyuan Wang, Zihao Dong, Hongliang Lei, Zejia Zhang, Weizhuang Shi, Wei Luo, Weiwei Wan, Jian Huang
To reduce the human labor cost of demonstration collection, we proposed a low-cost demonstration collection method based on Nonlinear Model Predictive Control (NMPC).
Deep Reinforcement Learning
Deformable Object Manipulation
+2
no code implementations • CVPR 2025 • Haoyuan Wang, Zhenwei Wang, Xiaoxiao Long, Cheng Lin, Gerhard Hancke, Rynson W.H. Lau
Finally, we propose a large-scale synthetic dataset rich in material diversity for our model training.
no code implementations • CVPR 2024 • Haoyuan Wang, WenBo Hu, Lei Zhu, Rynson W. H. Lau
Our method has two stages: the geometry of the target object and the pre-filtered environmental radiance fields are reconstructed in the first stage, and materials of the target object are estimated in the second stage with the proposed NeP and material-aware cone sampling strategy.
1 code implementation • ICCV 2023 • Haoyuan Wang, Xiaogang Xu, Ke Xu, Rynson WH. Lau
Neural Radiance Field (NeRF) is a promising approach for synthesizing novel views, given a set of images and the corresponding camera poses of a scene.
2 code implementations • ECCV 2022 • Haoyuan Wang, Ke Xu, and Rynson W.H. Lau
Existing image enhancement methods are typically designed to address either the over- or under-exposure problem in the input image.
Ranked #3 on
Image Enhancement
on Exposure-Errors
no code implementations • 9 Jul 2020 • Xiangru Tang, Haoyuan Wang, Xiang Pan, Jiyang Qi
Abstract visual reasoning connects mental abilities to the physical world, which is a crucial factor in cognitive development.