Junfeng Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junfeng Yao has a total of 205 co-authors. Here are the top co-authors by number of shared publications:
- Jinsong Su
Xiamen University, China
7 shared publications - Qingqi Hong
Xiamen University
6 shared publications - Xiaohu Guo
University of Texas at Dallas, Richardson, USA
6 shared publications - Qingqiang Wu
Xiamen University
5 shared publications - Chunyan Li
Yunnan Normal University
4 shared publications - Kunhong Liu
School of Film, Xiamen University, Xiamen, China
4 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12146-12155
LDSG: Learning Decoupled Structured Gaussians for Improved Dynamic Rendering and Reconstruction
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 12146-12155
Open AccessLDSG: Learning Decoupled Structured Gaussians for Improved Dynamic Rendering and Reconstruction
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-19
S4R: Scaling for Rigid-Body Interpenetration Resolution
Rigid-body interpenetration frequently occurs in procedurally assembled and generated scenes and must be removed before downstream applications such as physical simulation. We present S4R ( S caling for Rigid-Body Interpenetration R esolution), a scale-continuation method for static interpenetration repair. S4R first uniformly shrinks each body about a fixed reference center to a small initial scale, at which the layout is penetration-free, and then restores full scale through a sequence of minimum-norm convex contact quadratic programs (QPs) that target the linearized separation margin during continuation. Resolution thereby replaces one deep correction with a sequence of shallow-contact subproblems. A conservative scale-event bound and frozen-witness gap predictions cut the number of exact mesh queries; the continuation then ends with a full-scale evaluator check and bounded tail refinement. We evaluate S4R on Kubric [Greff et al. 2022], HY3D-Bench [Team Hunyuan3D et al. 2026], and Thingi10K [Zhou and Jacobson 2016] using a shared mesh-level evaluator and a unified per-scene timing protocol. In the main comparisons on all three benchmarks, up to N =5000 bodies, S4R reaches zero reported penetration with displacement that stays small and nearly independent of scene size, and at the lowest wall time within each hardware tier among the compared methods. A GPU implementation extends these results to large-scale scenes. Our code and data can be found on our project page: https://frank-zy-dou.github.io/projects/S4R/index.html.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-19
Open AccessS4R: Scaling for Rigid-Body Interpenetration Resolution
Rigid-body interpenetration frequently occurs in procedurally assembled and generated scenes and must be removed before downstream applications such as physical simulation. We present S4R ( S caling for Rigid-Body Interpenetration R esolution), a scale-continuation method for static interpenetration repair. S4R first uniformly shrinks each body about a fixed reference center to a small initial scale, at which the layout is penetration-free, and then restores full scale through a sequence of minimum-norm convex contact quadratic programs (QPs) that target the linearized separation margin during continuation. Resolution thereby replaces one deep correction with a sequence of shallow-contact subproblems. A conservative scale-event bound and frozen-witness gap predictions cut the number of exact mesh queries; the continuation then ends with a full-scale evaluator check and bounded tail refinement. We evaluate S4R on Kubric [Greff et al. 2022], HY3D-Bench [Team Hunyuan3D et al. 2026], and Thingi10K [Zhou and Jacobson 2016] using a shared mesh-level evaluator and a unified per-scene timing protocol. In the main comparisons on all three benchmarks, up to N =5000 bodies, S4R reaches zero reported penetration with displacement that stays small and nearly independent of scene size, and at the lowest wall time within each hardware tier among the compared methods. A GPU implementation extends these results to large-scale scenes. Our code and data can be found on our project page: https://frank-zy-dou.github.io/projects/S4R/index.html.
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13600-13609
Skel4D: Reconstructing 4D Objects from Casual Videos with Skeleton-Driven Structured Gaussians and Diffusion Priors
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 13600-13609
Open AccessSkel4D: Reconstructing 4D Objects from Casual Videos with Skeleton-Driven Structured Gaussians and Diffusion Priors
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3132-3140
Disentangling Camera Motion and Scene Deformation in Pose-Free Dynamic 3D Gaussian Splatting
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 3132-3140
Open AccessDisentangling Camera Motion and Scene Deformation in Pose-Free Dynamic 3D Gaussian Splatting
- 1 June 2026
- Published by Springer Nature
- p. 18-38
Integrating Multi-modal Interaction with AR Garment Design for Educational Applications
- 1 June 2026
- Published by Springer Nature
- p. 18-38
Integrating Multi-modal Interaction with AR Garment Design for Educational Applications
- Open Access
- 20 March 2026
- Published by Springer Nature in Visual Computing for Industry, Biomedicine, and Art
- Vol. 9 (1)
Review of electroencephalography and electromyography research in robotics: opportunities and challenges
In the evolving nexus of neuroscience and robotics, the symbiotic fusion of electroencephalography (EEG) and electromyography (EMG) is emerging as a paradigm-shifting avenue for enhancing human-machine interfaces. While EEG, which captures the subtle electrical nuances of the brain, offers a potent channel for nuanced brain-machine communication, EMG serves as a bridge, converting neuromuscular intentions into actionable directives for robotic apparatuses. This review highlights the current methodologies in which EEG and EMG not only function in silos but also converge harmoniously to dictate robotic control. By delving deeper into this, the intricate synergy between cognitive processes, muscular responses, and machine actions can be unraveled. Subsequently, the discourse also navigates through the myriad challenges encountered in realizing real-time, seamless integration of these bio-signals with robotics and the innovative solutions poised to address them. The aim is to provide a comprehensive understanding of the interplay between neuroscience and robotics. This insight will help drive breakthroughs in adaptive human-machine collaboration.
- 20 March 2026
- Published by Springer Nature in Visual Computing for Industry, Biomedicine, and Art
- Vol. 9 (1)
Open AccessReview of electroencephalography and electromyography research in robotics: opportunities and challenges
In the evolving nexus of neuroscience and robotics, the symbiotic fusion of electroencephalography (EEG) and electromyography (EMG) is emerging as a paradigm-shifting avenue for enhancing human-machine interfaces. While EEG, which captures the subtle electrical nuances of the brain, offers a potent channel for nuanced brain-machine communication, EMG serves as a bridge, converting neuromuscular intentions into actionable directives for robotic apparatuses. This review highlights the current methodologies in which EEG and EMG not only function in silos but also converge harmoniously to dictate robotic control. By delving deeper into this, the intricate synergy between cognitive processes, muscular responses, and machine actions can be unraveled. Subsequently, the discourse also navigates through the myriad challenges encountered in realizing real-time, seamless integration of these bio-signals with robotics and the innovative solutions poised to address them. The aim is to provide a comprehensive understanding of the interplay between neuroscience and robotics. This insight will help drive breakthroughs in adaptive human-machine collaboration.
- Open Access
- 12 January 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (2) , 278
AGSM–CPA: Reliability-Aware Robustness for Rotation-Invariant Point Cloud Learning
Rotation-invariant (RI) point cloud models aim to reduce sensitivity to viewpoint changes, but their performance still drops noticeably in real-world settings when local geometry is degraded by noise, occlusion, and uneven sampling. Once these disturbances propagate through deeper layers, they can lead to significant robustness degradation, especially for high-capacity RI backbones. To address this problem, we propose AGSM-CPA (Adaptive Geometric Signal Modulation with Cross-Perturbation Alignment), a lightweight and plug-and-play framework that enhances the robustness of RI models without altering their core convolutional operators. It integrates two complementary modules: the Geometric Signal-to-Noise Ratio (G-SNR) modulation mechanism, which adaptively suppresses unreliable neighborhoods based on local coordinate variance, and the Cross-Perturbation Semantic Consistency Alignment (CP-SCL) module, which enforces prediction consistency between weakly augmented inputs and strongly corrupted ones. We evaluate AGSM-CPA on ModelNet40, ScanObjectNN, and ShapeNetPart. Across standard corruption protocols, AGSM-CPA consistently improves robustness while maintaining competitive clean accuracy with negligible computational overhead. These results indicate that AGSM-CPA offers a practical, reliability-aware adapter for robust rotation-invariant point cloud learning.
- 12 January 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (2) , 278
Open AccessAGSM–CPA: Reliability-Aware Robustness for Rotation-Invariant Point Cloud Learning
Rotation-invariant (RI) point cloud models aim to reduce sensitivity to viewpoint changes, but their performance still drops noticeably in real-world settings when local geometry is degraded by noise, occlusion, and uneven sampling. Once these disturbances propagate through deeper layers, they can lead to significant robustness degradation, especially for high-capacity RI backbones. To address this problem, we propose AGSM-CPA (Adaptive Geometric Signal Modulation with Cross-Perturbation Alignment), a lightweight and plug-and-play framework that enhances the robustness of RI models without altering their core convolutional operators. It integrates two complementary modules: the Geometric Signal-to-Noise Ratio (G-SNR) modulation mechanism, which adaptively suppresses unreliable neighborhoods based on local coordinate variance, and the Cross-Perturbation Semantic Consistency Alignment (CP-SCL) module, which enforces prediction consistency between weakly augmented inputs and strongly corrupted ones. We evaluate AGSM-CPA on ModelNet40, ScanObjectNN, and ShapeNetPart. Across standard corruption protocols, AGSM-CPA consistently improves robustness while maintaining competitive clean accuracy with negligible computational overhead. These results indicate that AGSM-CPA offers a practical, reliability-aware adapter for robust rotation-invariant point cloud learning.
- 22 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
Endo-HDR: Dynamic endoscopic reconstruction with deformable 3D Gaussians and hierarchical depth regularization
- 22 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
Endo-HDR: Dynamic endoscopic reconstruction with deformable 3D Gaussians and hierarchical depth regularization
- Open Access
- 21 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
"Glory Comes from the Hands": Exploring Glove Puppetry Performance with Dexterous Robotic Hands
- 21 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open Access"Glory Comes from the Hands": Exploring Glove Puppetry Performance with Dexterous Robotic Hands
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5509-5518
Sera: Separated Coarse-to-fine Representation Alignment for Cross-subject EEG-based Emotion Recognition
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5509-5518
Open AccessSera: Separated Coarse-to-fine Representation Alignment for Cross-subject EEG-based Emotion Recognition