Jiahao Chang

Jiahao Chang

Auto-generated profile, based on publicly available information

Jiahao Chang

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 January 2024 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
JCJiahao Chang
Jiahao Chang
JHJianfeng He
Jianfeng He
TZTianzhu Zhang
Tianzhu Zhang
JYJiyang Yu
Jiyang Yu
FWFeng Wu
Feng Wu
Recent learning-based methods demonstrate their strong ability to estimate depth for multi-view stereo reconstruction. However, most of these methods directly extract features via regular or deformable convolutions, and few works consider the alignment of the receptive fields between views while constructing the cost volume. Through analyzing the constraint and inference of previous MVS networks, we find that there are still some shortcomings that hinder the performance. To deal with the above issues, we propose an Epipolar-Guided Multi-View Stereo Network with Interval-Aware Label (EI-MVSNet), which includes an epipolar-guided volume construction module and an interval-aware depth estimation module in a unified architecture for MVS. The proposed EI-MVSNet enjoys several merits. First, in the epipolar-guided volume construction module, we construct cost volume with features from aligned receptive fields between different pairs of reference and source images via epipolar-guided convolutions, which take rotation and scale changes into account. Second, in the interval-aware depth estimation module, we attempt to supervise the cost volume directly and make depth estimation independent of extraneous values by perceiving the upper and lower boundaries, which can achieve fine-grained predictions and enhance the reasoning ability of the network. Extensive experimental results on two standard benchmarks demonstrate that our EI-MVSNet performs favorably against state-of-the-art MVS methods. Specifically, our EI-MVSNet ranks $1_{st}$ on both intermediate and advanced subsets of the Tanks and Temples benchmark, which verifies the high precision and strong robustness of our model.

3 April 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
YZYihao Zhi
Yihao Zhi
WSWanhu Sun
Wanhu Sun
JCJiahao Chang
Jiahao Chang
CYChongjie Ye
Chongjie Ye
WFWensen Feng
Wensen Feng
XHXiaoguang Han
Xiaoguang Han
In recent years, significant progress has been witnessed in the field of neural 3D avatar reconstruction. Among all related tasks, building an animatable avatar from monocular videos is one of the most challenging ones, yet it also has a wide range of applications. The “animatable” means that we need to transfer any arbitrary and unseen poses onto the avatar and generate new 3D videos. Thanks to the rise of the powerful representation of NeRF, generating a high-fidelity animatable avatar from videos has become easier and more accessible. Despite their impressive visual results, the substantial training and rendering overhead dramatically hamper their applications. 3D Gaussian Splatting, as a timely new representation, has demonstrated its high-quality and high-efficiency rendering. This has led to many concurrent works to introduce 3D-GS to animatable avatar building. Although they demonstrate very high-fidelity renderings for poses similar to the training video frames, poor results are produced when the poses are far from training. We argue that this is primarily because the Gaussian points lack structures. Thus, we suggest involving DMTet to represent the coarse geometry of the avatar. In our representation, the majority of Gaussian points are bound to the mesh vertices, while some free Gaussian is allowed to expand to better fit the given video. Furthermore, we develop a dual-space optimization framework to jointly optimize the DMTet, Gaussian points, and skinning weights under two spaces. In this sense, Gaussian points are transformed in a constrained way, which dramatically improves the generalization ability for unseen poses. This is well demonstrated via extensive experiments.

14 December 2025
Verified
Conference Paper
Open access
YZYihao Zhi
Yihao Zhi
CLChenghong Li
Chenghong Li
HLHongjie Liao
Hongjie Liao
XYXihe Yang
Xihe Yang
ZSZhengwentai Sun
Zhengwentai Sun
XHXiaoguang Han
Xiaoguang Han

8 May 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CLChenghong Li
Chenghong Li
HLHongjie Liao
Hongjie Liao
YZYihao Zhi
Yihao Zhi
XYXihe Yang
Xihe Yang
ZSZhengwentai Sun
Zhengwentai Sun
XHXiaoguang Han
Xiaoguang Han
In this era, the success of large language models and text-to-image models can be attributed to the driving force of large-scale datasets. However, in the realm of 3D vision, while significant progress has been achieved in object-centric tasks through large-scale datasets like Objaverse and MVImgNet, human-centric tasks have seen limited advancement, largely due to the absence of a comparable large-scale human dataset. To bridge this gap, we present MVHumanNet++, a dataset that comprises multi-view human action sequences of 4,500 human identities. The primary focus of our work is on collecting human data that features a large number of diverse identities and everyday clothing using multi-view human capture systems, which facilitates easily scalable data collection. Our dataset contains 9,000 daily outfits, 60,000 motion sequences and 645 million frames with extensive annotations, including human masks, camera parameters, 2D and 3D keypoints, SMPL/SMPLX parameters, and corresponding textual descriptions. Additionally, the proposed MVHumanNet++ dataset is enhanced with newly processed normal maps and depth maps, significantly expanding its applicability and utility for advanced human-centric research. To explore the potential of our proposed MVHumanNet++ dataset in various 2D and 3D visual tasks, we conducted several pilot studies to demonstrate the performance improvements and effective applications enabled by the scale provided by MVHumanNet++. As the current largest-scale 3D human dataset, we hope that the release of MVHumanNet++ dataset with annotations will foster further innovations in the domain of 3D human-centric tasks at scale. MVHumanNet++ is publicly available at https://kevinlee09.github.io/research/MVHumanNet++/.

20 November 2026
Verified
Conference Paper
Open access
JZJinjian Zhao
Jinjian Zhao
JCJiahao Chang
Jiahao Chang
YWYushuang Wu
Yushuang Wu
XWXianzu Wu
Xianzu Wu
YCYan-Pei Cao
Yan-Pei Cao
XHXiaoguang Han
Xiaoguang Han

20 November 2026
Verified
Conference Paper
Open access
HZHuimin Zhang
Huimin Zhang
JCJiahao Chang
Jiahao Chang
LSLuyue Shi
Luyue Shi
XYXihe Yang
Xihe Yang
HLHongsheng Li
Hongsheng Li
XHXiaoguang Han
Xiaoguang Han