Chaoda Zheng

Chaoda Zheng

Auto-generated profile, based on publicly available information

Chaoda Zheng

School of Computer Science and Engineering, South China University of Technology, Guangzhou, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
26 May 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YXYong Xu
Yong Xu
CZChaoda Zheng
Chaoda Zheng
RXRuotao Xu
Ruotao Xu
YQYuhui Quan
Yuhui Quan
HLHaibin Ling
Haibin Ling
In recent years, multi-view learning has emerged as a promising approach for 3D shape recognition, which identifies a 3D shape based on its 2D views taken from different viewpoints. Usually, the correspondences inside a view or across different views encode the spatial arrangement of object parts and the symmetry of the object, which provide useful geometric cues for recognition. However, such view correspondences have not been explicitly and fully exploited in existing work. In this paper, we propose a correspondence-aware representation (CAR) module, which explicitly finds potential intra-view correspondences and cross-view correspondences via $k$ NN search in semantic space and then aggregates the shape features from the correspondences via learned transforms. Particularly, the spatial relations of correspondences in terms of their viewpoint positions and intra-view locations are taken into account for learning correspondence-aware features. Incorporating the CAR module into a ResNet-18 backbone, we propose an effective deep model called CAR-Net for 3D shape classification and retrieval. Extensive experiments have demonstrated the effectiveness of the CAR module as well as the excellent performance of the CAR-Net.

13 October 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
CZChaoda Zheng
Chaoda Zheng
XYXu Yan
Xu Yan
HZHaiming Zhang
Haiming Zhang
BWBaoyuan Wang
Baoyuan Wang
SCShenghui Cheng
Shenghui Cheng
ZLZhen Li
Zhen Li
3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a crucial role in autonomous driving. Current approaches all follow the Siamese paradigm based on appearance matching. However, LiDAR point clouds are usually textureless and incomplete, which hinders effective appearance matching. Besides, previous methods greatly overlook the critical motion clues among targets. In this work, beyond 3D Siamese tracking, we introduce a motion-centric paradigm to handle LiDAR SOT from a new perspective. Following this paradigm, we propose a matching-free two-stage tracker M$^{2}$2-Track . At the 1 st -stage, $M^{2}$ -Track localizes the target within successive frames via m otion transformation. Then it refines the target box through m otion-assisted shape completion at the 2 nd -stage. Due to the motion-centric nature, our method shows its impressive generalizability with limited training labels and provides good differentiability for end-to-end cycle training. This inspires us to explore semi-supervised LiDAR SOT by incorporating a pseudo-label-based motion augmentation and a self-supervised loss term. Under the fully-supervised setting, extensive experiments confirm that $M^{2}$ -Track significantly outperforms previous state-of-the-arts on three large-scale datasets while running at 57FPS ( $\sim$∼ 3% , $\sim$∼ 11% and $\sim$∼ 22% precision gains on KITTI, NuScenes, and Waymo Open Dataset respectively). While under the semi-supervised setting, our method performs on par with or even surpasses its fully-supervised counterpart using fewer than half labels from KITTI. Further analysis verifies each component's effectiveness and shows the motion-centric paradigm's promising potential for auto-labeling and unsupervised domain adaptation.

6 January 2023 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JGJiantao Gao
Jiantao Gao
XYXu Yan
Xu Yan
WZWeibing Zhao
Weibing Zhao
ZLZhen Lyu
Zhen Lyu
YLYinghong Liao
Yinghong Liao
CZChaoda Zheng
Chaoda Zheng
Single object tracking (SOT) is one of the most active research directions in the field of computer vision. Compared with the 2-D image-based SOT which has already been well-studied, SOT on 3-D point clouds is a relatively emerging research field. In this article, a novel approach, namely, the contextual-aware tracker (CAT), is investigated to achieve a superior 3-D SOT through spatially and temporally contextual learning from the LiDAR sequence. More precisely, in contrast to the previous 3-D SOT methods merely exploiting point clouds in the target bounding box as the template, CAT generates templates by adaptively including the surroundings outside the target box to use available ambient cues. This template generation strategy is more effective and rational than the previous area-fixed one, especially when the object has only a small number of points. Moreover, it is deduced that LiDAR point clouds in 3-D scenes are often incomplete and significantly vary from frame to another, which makes the learning process more difficult. To this end, a novel cross-frame aggregation (CFA) module is proposed to enhance the feature representation of the template by aggregating the features from a historical reference frame. Leveraging such schemes enables CAT to achieve a robust performance, even in the case of extremely sparse point clouds. The experiments confirm that the proposed CAT outperforms the state-of-the-art methods on both the KITTI and NuScenes benchmarks, achieving 3.9% and 5.6% improvements in terms of precision.

26 October 2023
Verified
Conference Paper
Open access
WZWeibing Zhao
Weibing Zhao
HZHaiming Zhang
Haiming Zhang
CZChaoda Zheng
Chaoda Zheng
XYXu Yan
Xu Yan
SCShuguang Cui
Shuguang Cui
ZLZhen Li
Zhen Li

12 August 2019 in IEEE Access
Verified
Journal Article
Open access
YXYong Xu
Yong Xu
CZChaoda Zheng
Chaoda Zheng
RXRuotao Xu
Ruotao Xu
YQYuhui Quan
Yuhui Quan
Recognition of 3D shapes is a fundamental task in computer vision. In recent years, view-based deep learning has emerged as an effective approach for 3D shape recognition. Most existing view-based methods treat the views of an object as an unordered set, which ignores the dynamic relations among the views, e.g. sequential semantic dependencies. In this paper, modeling the views of an object by a sequence, we aim at exploiting the long-term dependencies among different views for shape recognition, which is done by constructing a sequence-aware view aggregation module based on the bi-directional Long Short-Term Memory network. It is shown that our view aggregation module not only captures the bi-directional dependencies in view sequences, but also enjoys the robustness to circular shifts of input sequences. Incorporating the aggregation module into a standard convolutional network architecture, we develop an effective method for 3D shape classification and retrieval. Our method was evaluated on the ModelNet40/10 and ShapeNetCore55 datasets. The results show the encouraging performance gain from exploiting long-term dependencies in view sequences, as well as the superior performance of our method compared to the existing ones.

2 May 2025 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
HZHaiming Zhang
Haiming Zhang
ZYZhihao Yuan
Zhihao Yuan
CZChaoda Zheng
Chaoda Zheng
XYXu Yan
Xu Yan
BWBaoyuan Wang
Baoyuan Wang
ZLZhen Li
Zhen Li
Although existing speech-driven talking face generation methods achieve significant progress, they are far from real-world application due to the avatar-specific training demand and unstable lip movements. To address the above issues, we propose the GSmoothFace, a novel two-stage generalized talking face generation model guided by a fine-grained 3D face model, which can synthesize smooth lip dynamics while preserving the speaker’s identity. Our proposed GSmoothFace model mainly consists of the Audio to Expression Prediction (A2EP) module and the Target Adaptive Face Translation (TAFT) module. Specifically, we first develop the A2EP module to predict expression parameters synchronized with the driven speech. It uses a transformer to capture the long-term audio context and learns the parameters from the fine-grained 3D facial vertices, resulting in accurate and smooth lip-synchronization performance. Afterward, the well-designed TAFT module, empowered by Morphology Augmented Face Blending (MAFB), takes the predicted expression parameters and target video as inputs to modify the facial region of the target video without distorting the background content. The TAFT effectively exploits the identity appearance and background context in the target video, which makes it possible to generalize to different speakers without retraining. Both quantitative and qualitative experiments confirm the superiority of our method in terms of realism, lip-synchronization, and visual quality.