Min Shi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Min Shi has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Dengming Zhu
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and Taicang Zhongke Institute of Information Technology, Suzhou, China
12 shared publications - Zhaoxin Li
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing 100081, China
5 shared publications - Zhaoqi Wang
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
4 shared publications - Jia-Qi Zhang
School of Information Engineering, Chang'an University, Xian, China
2 shared publications - Lin Gao
Chinese Academy of Sciences
2 shared publications - Qi Wang
North China Electric Power University
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10577-10585
Noise-Resilient Robotic Facial Expression Generation with a Self-Supervised Embodied Expression Dataset
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 10577-10585
Open AccessNoise-Resilient Robotic Facial Expression Generation with a Self-Supervised Embodied Expression Dataset
- 13 September 2026
- Published by Springer Nature
- p. 613-629
IndoorSplat: Enhanced Indoor Scene Reconstruction with Structured 2D Gaussian Splatting
- 13 September 2026
- Published by Springer Nature
- p. 613-629
IndoorSplat: Enhanced Indoor Scene Reconstruction with Structured 2D Gaussian Splatting
- Open Access
Pose Compensation Method for Robotic Manipulators Based on Transformer
Industrial robots, particularly six-axis serial manipulators, have been widely deployed in manufacturing workflows including assembly, welding, material handling, inspection and precision machining. As the demand for higher end-effector positioning accuracy and trajectory tracking performance grows, end-position errors induced during manipulator operation—stemming from geometric deviations, joint friction, load fluctuations, current surges, as well as variations in velocity and acceleration—have emerged as a critical bottleneck limiting high-precision applications. Conventional error compensation approaches mostly rely on geometric calibration, empirical formulas or fixed regression algorithms, which struggle to adequately characterize error trends featuring strong temporal dependencies, nonlinearity and multi-factor coupling. To address the aforementioned limitations, this paper takes the UR5 industrial manipulator as the research object. Leveraging the NIST-released dataset for manipulator positional accuracy degradation monitoring, this study develops and implements a physics-aware Transformer-based compensation framework that integrates a physics-consistent constraint loss and a nonlinear exponential error amplification strategy with a standard Transformer encoder for end-effector positional accuracy degradation. Multiple variables including target joint position, velocity, acceleration, torque, motor current and control current are selected to construct time-window input vectors, which are used to train the Transformer regression model to capture the correlation between historical motion states and real-time end-effector positional accuracy degradation. Experimental results demonstrate that the proposed Transformer model can fully capture temporal contextual correlations and multi-feature fusion information embedded within manipulator kinematic data, delivering superior error compensation performance for the six-dimensional end-effector pose error prediction task. The self-attention-based time-series modeling framework is well-suited to the nonlinear, coupled and time-varying characteristics of manipulator operational errors. This work provides valuable references for accuracy enhancement of industrial robots and the design of intelligent error compensation schemes. This work provides valuable references for accuracy enhancement of industrial robots and the design of intelligent error compensation schemes, with the proposed physics-aware strategies being model-agnostic and potentially extensible to other regression architectures.
Open AccessPose Compensation Method for Robotic Manipulators Based on Transformer
Industrial robots, particularly six-axis serial manipulators, have been widely deployed in manufacturing workflows including assembly, welding, material handling, inspection and precision machining. As the demand for higher end-effector positioning accuracy and trajectory tracking performance grows, end-position errors induced during manipulator operation—stemming from geometric deviations, joint friction, load fluctuations, current surges, as well as variations in velocity and acceleration—have emerged as a critical bottleneck limiting high-precision applications. Conventional error compensation approaches mostly rely on geometric calibration, empirical formulas or fixed regression algorithms, which struggle to adequately characterize error trends featuring strong temporal dependencies, nonlinearity and multi-factor coupling. To address the aforementioned limitations, this paper takes the UR5 industrial manipulator as the research object. Leveraging the NIST-released dataset for manipulator positional accuracy degradation monitoring, this study develops and implements a physics-aware Transformer-based compensation framework that integrates a physics-consistent constraint loss and a nonlinear exponential error amplification strategy with a standard Transformer encoder for end-effector positional accuracy degradation. Multiple variables including target joint position, velocity, acceleration, torque, motor current and control current are selected to construct time-window input vectors, which are used to train the Transformer regression model to capture the correlation between historical motion states and real-time end-effector positional accuracy degradation. Experimental results demonstrate that the proposed Transformer model can fully capture temporal contextual correlations and multi-feature fusion information embedded within manipulator kinematic data, delivering superior error compensation performance for the six-dimensional end-effector pose error prediction task. The self-attention-based time-series modeling framework is well-suited to the nonlinear, coupled and time-varying characteristics of manipulator operational errors. This work provides valuable references for accuracy enhancement of industrial robots and the design of intelligent error compensation schemes. This work provides valuable references for accuracy enhancement of industrial robots and the design of intelligent error compensation schemes, with the proposed physics-aware strategies being model-agnostic and potentially extensible to other regression architectures.
- Open Access
An Optimized Particle Swarm Algorithm for High-Precision Camera Calibration with Enhanced Wide-Angle Distortion Correction
Camera calibration is crucial to accurate vision tasks for its establishment of the mapping between 3D space and 2D image space. Traditional calibration methods often suffer from limited accuracy and time-consuming processes. In this study, we propose an automatic guidance system leveraging an improved particle swarm optimization algorithm to achieve fast and high-precision camera calibration. Our system dynamically recommends optimal camera poses for the next calibration image, effectively reducing calibration uncertainty and enhancing accuracy. Furthermore, for wide-angle cameras, we introduce a pre-estimation of distortion coefficients to guide the calibration process, significantly improving the calibration of distortion parameters. Experimental results demonstrate that our method outperforms existing guidance systems, achieving higher calibration accuracy with fewer images and shorter calculation time. The results of camera parameters calibrated by the system are applied to the reconstruction based on point clouds, and can achieve desirable reconstruction effect. The proposed system holds promise for applications in film and television shooting, promoting the development of the industry by reducing calibration errors and equipment debugging time.
Open AccessAn Optimized Particle Swarm Algorithm for High-Precision Camera Calibration with Enhanced Wide-Angle Distortion Correction
Camera calibration is crucial to accurate vision tasks for its establishment of the mapping between 3D space and 2D image space. Traditional calibration methods often suffer from limited accuracy and time-consuming processes. In this study, we propose an automatic guidance system leveraging an improved particle swarm optimization algorithm to achieve fast and high-precision camera calibration. Our system dynamically recommends optimal camera poses for the next calibration image, effectively reducing calibration uncertainty and enhancing accuracy. Furthermore, for wide-angle cameras, we introduce a pre-estimation of distortion coefficients to guide the calibration process, significantly improving the calibration of distortion parameters. Experimental results demonstrate that our method outperforms existing guidance systems, achieving higher calibration accuracy with fewer images and shorter calculation time. The results of camera parameters calibrated by the system are applied to the reconstruction based on point clouds, and can achieve desirable reconstruction effect. The proposed system holds promise for applications in film and television shooting, promoting the development of the industry by reducing calibration errors and equipment debugging time.
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
WaterGS: Physically‐Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction
Reconstructing underwater object geometry from multi‐view images is a long‐standing challenge in computer graphics, primarily due to image degradation caused by underwater scattering, blur, and color shift. These degradations severely impair feature extraction and multi‐view consistency. Existing methods typically rely on pre‐trained image enhancement models as a preprocessing step, but often struggle with robustness under varying water conditions. To overcome these limitations, we propose WaterGS, a novel framework for underwater surface reconstruction that jointly recovers accurate 3D geometry and restores true object colors. The core of our approach lies in introducing a Physically‐Based imaging model into the rendering process of 2D Gaussian Splatting. This enables accurate separation of true object colors from water‐induced distortions, thereby facilitating more robust photometric alignment and denser geometric reconstruction across views. Building upon this improved photometric consistency, we further introduce a Gaussian bundle adjustment scheme guided by our physical model to jointly optimize camera poses and geometry, enhancing reconstruction accuracy. Extensive experiments on synthetic and real‐world datasets show that WaterGS achieves robust, high‐fidelity reconstruction directly from raw underwater images, outperforming prior approaches in both geometric accuracy and visual consistency.
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
WaterGS: Physically‐Based Imaging in Gaussian Splatting for Underwater Scene Reconstruction
Reconstructing underwater object geometry from multi‐view images is a long‐standing challenge in computer graphics, primarily due to image degradation caused by underwater scattering, blur, and color shift. These degradations severely impair feature extraction and multi‐view consistency. Existing methods typically rely on pre‐trained image enhancement models as a preprocessing step, but often struggle with robustness under varying water conditions. To overcome these limitations, we propose WaterGS, a novel framework for underwater surface reconstruction that jointly recovers accurate 3D geometry and restores true object colors. The core of our approach lies in introducing a Physically‐Based imaging model into the rendering process of 2D Gaussian Splatting. This enables accurate separation of true object colors from water‐induced distortions, thereby facilitating more robust photometric alignment and denser geometric reconstruction across views. Building upon this improved photometric consistency, we further introduce a Gaussian bundle adjustment scheme guided by our physical model to jointly optimize camera poses and geometry, enhancing reconstruction accuracy. Extensive experiments on synthetic and real‐world datasets show that WaterGS achieves robust, high‐fidelity reconstruction directly from raw underwater images, outperforming prior approaches in both geometric accuracy and visual consistency.
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
Self‐Supervised Humidity‐Controllable Garment Simulation via Capillary Bridge Modeling
Simulating wet clothing remains a significant challenge due to the complex physical interactions between moist fabric and the human body, compounded by the lack of dedicated datasets for training data‐driven models. Existing self‐supervised approaches struggle to capture moisture‐induced dynamics such as skin adhesion, anisotropic surface resistance, and non‐linear wrinkling, leading to limited accuracy and efficiency. To address this, we present SHGS, a novel self‐supervised framework for humidity‐controllable clothing simulation grounded in the physical modeling of capillary bridges that form between fabric and skin. We abstract the forces induced by wetness into two physically motivated components: a normal adhesive force derived from Laplace pressure and a tangential shear‐resistance force that opposes relative motion along the fabric surface. By formulating these forces as potential energy for conservative effects and as mechanical work for non‐conservative effects, we construct a physics‐consistent wetness loss. This enables self‐supervised training without requiring labeled data of wet clothing. Our humidity‐sensitive dynamics are driven by a multi‐layer graph neural network, which facilitates a smooth and physically realistic transition between different moisture levels. This architecture decouples the garment's dynamics in wet and dry states through a local weight interpolation mechanism, adjusting the fabric's behavior in response to varying humidity conditions. Experiments demonstrate that SHGS outperforms existing methods in both visual fidelity and computational efficiency, marking a significant advancement in realistic wet‐cloth simulation.
- 11 October 2025
- Published by Wiley in Computer Graphics Forum
- Vol. 44 (7)
Self‐Supervised Humidity‐Controllable Garment Simulation via Capillary Bridge Modeling
Simulating wet clothing remains a significant challenge due to the complex physical interactions between moist fabric and the human body, compounded by the lack of dedicated datasets for training data‐driven models. Existing self‐supervised approaches struggle to capture moisture‐induced dynamics such as skin adhesion, anisotropic surface resistance, and non‐linear wrinkling, leading to limited accuracy and efficiency. To address this, we present SHGS, a novel self‐supervised framework for humidity‐controllable clothing simulation grounded in the physical modeling of capillary bridges that form between fabric and skin. We abstract the forces induced by wetness into two physically motivated components: a normal adhesive force derived from Laplace pressure and a tangential shear‐resistance force that opposes relative motion along the fabric surface. By formulating these forces as potential energy for conservative effects and as mechanical work for non‐conservative effects, we construct a physics‐consistent wetness loss. This enables self‐supervised training without requiring labeled data of wet clothing. Our humidity‐sensitive dynamics are driven by a multi‐layer graph neural network, which facilitates a smooth and physically realistic transition between different moisture levels. This architecture decouples the garment's dynamics in wet and dry states through a local weight interpolation mechanism, adjusting the fabric's behavior in response to varying humidity conditions. Experiments demonstrate that SHGS outperforms existing methods in both visual fidelity and computational efficiency, marking a significant advancement in realistic wet‐cloth simulation.
- 1 March 2025
- Published by Springer Nature
- p. 270-282
Unsupervised Real-Time Garment Deformation Prediction Driven by Human Body Pose and Shape
- 1 March 2025
- Published by Springer Nature
- p. 270-282
Unsupervised Real-Time Garment Deformation Prediction Driven by Human Body Pose and Shape
- Open Access
- 1 April 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 261-277
Generating diverse clothed 3D human animations via a generative model
Data-driven garment animation is a current topic of interest in the computer graphics industry. Existing approaches generally establish the mapping between a single human pose or a temporal pose sequence, and garment deformation, but it is difficult to quickly generate diverse clothed human animations. We address this problem with a method to automatically synthesize dressed human animations with temporal consistency from a specified human motion label. At the heart of our method is a two-stage strategy. Specifically, we first learn a latent space encoding the sequence-level distribution of human motions utilizing a transformer-based conditional variational autoencoder (Transformer-CVAE). Then a garment simulator synthesizes dynamic garment shapes using a transformer encoder–decoder architecture. Since the learned latent space comes from varied human motions, our method can generate a variety of styles of motions given a specific motion label. By means of a novel beginning of sequence (BOS) learning strategy and a self-supervised refinement procedure, our garment simulator is capable of efficiently synthesizing garment deformation sequences corresponding to the generated human motions while maintaining temporal and spatial consistency. We verify our ideas experimentally. This is the first generative model that directly dresses human animation.
- 1 April 2024
- Published by Tsinghua University Press in Computational Visual Media
- Vol. 10 (2) , 261-277
Open AccessGenerating diverse clothed 3D human animations via a generative model
Data-driven garment animation is a current topic of interest in the computer graphics industry. Existing approaches generally establish the mapping between a single human pose or a temporal pose sequence, and garment deformation, but it is difficult to quickly generate diverse clothed human animations. We address this problem with a method to automatically synthesize dressed human animations with temporal consistency from a specified human motion label. At the heart of our method is a two-stage strategy. Specifically, we first learn a latent space encoding the sequence-level distribution of human motions utilizing a transformer-based conditional variational autoencoder (Transformer-CVAE). Then a garment simulator synthesizes dynamic garment shapes using a transformer encoder–decoder architecture. Since the learned latent space comes from varied human motions, our method can generate a variety of styles of motions given a specific motion label. By means of a novel beginning of sequence (BOS) learning strategy and a self-supervised refinement procedure, our garment simulator is capable of efficiently synthesizing garment deformation sequences corresponding to the generated human motions while maintaining temporal and spatial consistency. We verify our ideas experimentally. This is the first generative model that directly dresses human animation.
- 7 February 2024
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 36 (2) , 1477-1490
NG-Net: No-Grasp annotation grasp detection network for stacked scenes
- 7 February 2024
- Published by Springer Nature in Journal of Intelligent Manufacturing
- Vol. 36 (2) , 1477-1490
NG-Net: No-Grasp annotation grasp detection network for stacked scenes
- 30 November 2023
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 38 (6) , 1356-1368
Motion-Inspired Real-Time Garment Synthesis with Temporal-Consistency
- 30 November 2023
- Published by Springer Nature in Journal of Computer Science and Technology
- Vol. 38 (6) , 1356-1368
Motion-Inspired Real-Time Garment Synthesis with Temporal-Consistency