Ran Zhang
Research Subjects
Ran Zhang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Alan Zhao
Tencent Video AI Center, Beijing, China
2 shared publications - Bernd Bickel
ETH Zurich, Zurich, Switzerland
2 shared publications - Changxi Zheng
Columbia University, New York, USA
2 shared publications - Jinxu Xiang
Tencent Video AI Center, New York City, USA
2 shared publications - Yanni Zhang
Tencent Video AI Center, Beijing, China
2 shared publications - Bowen Zhao
Department of Physics Boston University 590 Commonwealth Avenue 02215 Boston Massachusetts USA
1 shared publication
Latest Publications
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Let There Be Light: Learning Lights from In-The-Wild Character Images
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessLet There Be Light: Learning Lights from In-The-Wild Character Images
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
RELATE3D: REfocusing Latent Adapter for Targeted local Enhancement and Editing in 3D Generation
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessRELATE3D: REfocusing Latent Adapter for Targeted local Enhancement and Editing in 3D Generation
- Open Access
- 25 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Gabor Splatting for High-Quality Gigapixel Image Representations
- 25 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessGabor Splatting for High-Quality Gigapixel Image Representations
- 1 October 2023
- Published by Wiley in Computer Graphics Forum
- Vol. 42 (7)
Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation
Neural Radiance Fields (NeRF) have significantly advanced the generation of highly realistic and expressive 3D scenes. However, the task of editing NeRF, particularly in terms of geometry modification, poses a significant challenge. This issue has obstructed NeRF's wider adoption across various applications. To tackle the problem of efficiently editing neural implicit fields, we introduceNeural Impostor, a hybrid representation incorporating an explicit tetrahedral mesh alongside a multigrid implicit field designated for each tetrahedron within the explicit mesh. Our framework bridges the explicit shape manipulation and the geometric editing of implicit fields by utilizing multigrid barycentric coordinate encoding, thus offering a pragmatic solution to deform, composite, and generate neural implicit fields while maintaining a complex volumetric appearance. Furthermore, we propose a comprehensive pipeline for editing neural implicit fields based on a set of explicit geometric editing operations. We show the robustness and adaptability of our system through diverse examples and experiments, including the editing of both synthetic objects and real captured data. Finally, we demonstrate the authoring process of a hybrid synthetic‐captured object utilizing a variety of editing operations, underlining the transformative potential ofNeural Impostorin the field of 3D content creation and manipulation.
- 1 October 2023
- Published by Wiley in Computer Graphics Forum
- Vol. 42 (7)
Neural Impostor: Editing Neural Radiance Fields with Explicit Shape Manipulation
Neural Radiance Fields (NeRF) have significantly advanced the generation of highly realistic and expressive 3D scenes. However, the task of editing NeRF, particularly in terms of geometry modification, poses a significant challenge. This issue has obstructed NeRF's wider adoption across various applications. To tackle the problem of efficiently editing neural implicit fields, we introduceNeural Impostor, a hybrid representation incorporating an explicit tetrahedral mesh alongside a multigrid implicit field designated for each tetrahedron within the explicit mesh. Our framework bridges the explicit shape manipulation and the geometric editing of implicit fields by utilizing multigrid barycentric coordinate encoding, thus offering a pragmatic solution to deform, composite, and generate neural implicit fields while maintaining a complex volumetric appearance. Furthermore, we propose a comprehensive pipeline for editing neural implicit fields based on a set of explicit geometric editing operations. We show the robustness and adaptability of our system through diverse examples and experiments, including the editing of both synthetic objects and real captured data. Finally, we demonstrate the authoring process of a hybrid synthetic‐captured object utilizing a variety of editing operations, underlining the transformative potential ofNeural Impostorin the field of 3D content creation and manipulation.
- Open Access
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Demonstrating Trusscillator: a System for Fabricating Human-Scale Human-Powered Oscillating Devices
- 19 April 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessDemonstrating Trusscillator: a System for Fabricating Human-Scale Human-Powered Oscillating Devices
- 24 May 2022
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (2) , 507-519
Worst‐Case Rigidity Analysis and Optimization for Assemblies with Mechanical Joints
We study structural rigidity for assemblies with mechanical joints. Existing methods identify whether an assembly is structurally rigid by assuming parts are perfectly rigid. Yet, an assembly identified as rigid may not be that “rigid” in practice, and existing methods cannot quantify how rigid an assembly is. We address this limitation by developing a new measure, worst‐case rigidity, to quantify the rigidity of an assembly as the largest possible deformation that the assembly undergoes for arbitrary external loads of fixed magnitude. Computing worst‐case rigidity is non‐trivial due to non‐rigid parts and different joint types. We thus formulate a new computational approach by encoding parts and their connections into a stiffness matrix, in which parts are modeled as deformable objects and joints as soft constraints. Based on this, we formulate worst‐case rigidity analysis as an optimization that seeks the worst‐case deformation of an assembly for arbitrary external loads, and solve the optimization problem via an eigenanalysis. Furthermore, we present methods to optimize the geometry and topology of various assemblies to enhance their rigidity, as guided by our rigidity measure. In the end, we validate our method on a variety of assembly structures with physical experiments and demonstrate its effectiveness by designing and fabricating several structurally rigid assemblies.
- 24 May 2022
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (2) , 507-519
Worst‐Case Rigidity Analysis and Optimization for Assemblies with Mechanical Joints
We study structural rigidity for assemblies with mechanical joints. Existing methods identify whether an assembly is structurally rigid by assuming parts are perfectly rigid. Yet, an assembly identified as rigid may not be that “rigid” in practice, and existing methods cannot quantify how rigid an assembly is. We address this limitation by developing a new measure, worst‐case rigidity, to quantify the rigidity of an assembly as the largest possible deformation that the assembly undergoes for arbitrary external loads of fixed magnitude. Computing worst‐case rigidity is non‐trivial due to non‐rigid parts and different joint types. We thus formulate a new computational approach by encoding parts and their connections into a stiffness matrix, in which parts are modeled as deformable objects and joints as soft constraints. Based on this, we formulate worst‐case rigidity analysis as an optimization that seeks the worst‐case deformation of an assembly for arbitrary external loads, and solve the optimization problem via an eigenanalysis. Furthermore, we present methods to optimize the geometry and topology of various assemblies to enhance their rigidity, as guided by our rigidity measure. In the end, we validate our method on a variety of assembly structures with physical experiments and demonstrate its effectiveness by designing and fabricating several structurally rigid assemblies.
- Open Access
- 8 October 2021
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 40 (5) , 1-16
Computational Design of Planar Multistable Compliant Structures
This article presents a method for designing planar multistable compliant structures. Given a sequence of desired stable states and the corresponding poses of the structure, we identify the topology and geometric realization of a mechanism—consisting of bars and joints—that is able to physically reproduce the desired multistable behavior. In order to solve this problem efficiently, we build on insights from minimally rigid graph theory to identify simple but effective topologies for the mechanism. We then optimize its geometric parameters, such as joint positions and bar lengths, to obtain correct transitions between the given poses. Simultaneously, we ensure adequate stability of each pose based on an effective approximate error metric related to the elastic energy Hessian of the bars in the mechanism. As demonstrated by our results, we obtain functional multistable mechanisms of manageable complexity that can be fabricated using 3D printing. Further, we evaluated the effectiveness of our method on a large number of examples in the simulation and fabricated several physical prototypes.
- 8 October 2021
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 40 (5) , 1-16
Open AccessComputational Design of Planar Multistable Compliant Structures
This article presents a method for designing planar multistable compliant structures. Given a sequence of desired stable states and the corresponding poses of the structure, we identify the topology and geometric realization of a mechanism—consisting of bars and joints—that is able to physically reproduce the desired multistable behavior. In order to solve this problem efficiently, we build on insights from minimally rigid graph theory to identify simple but effective topologies for the mechanism. We then optimize its geometric parameters, such as joint positions and bar lengths, to obtain correct transitions between the given poses. Simultaneously, we ensure adequate stability of each pose based on an effective approximate error metric related to the elastic energy Hessian of the bars in the mechanism. As demonstrated by our results, we obtain functional multistable mechanisms of manageable complexity that can be fabricated using 3D printing. Further, we evaluated the effectiveness of our method on a large number of examples in the simulation and fabricated several physical prototypes.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 286-289
Chaos Chicken Swarm-based Blind Equalization Algorithm for Multipath Mitigation of UAVs
Constant modulus blind equalization algorithm (CMA) has the disadvantages of large steady-state errors, slow convergence speed and easy to fall into local precocity in solving the multipath mitigation problem of UAVs. To solve these problems, a chaos chicken swarm-based constant modulus blind equalization algorithm (C-CSO-CMA) is proposed in this paper. On the basis of CMA, the proposed algorithm introduces the chicken learning coefficient into the chicken swarm optimization algorithm (CSO). Furthermore chaotic mutation is used for each chicken subgroup to achieve the global optimum. Finally, the experimental results show that the proposed algorithm not only has small steady-state error, fast convergence speed, but also has strong global convergence ability.
- 1 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 286-289
Chaos Chicken Swarm-based Blind Equalization Algorithm for Multipath Mitigation of UAVs
Constant modulus blind equalization algorithm (CMA) has the disadvantages of large steady-state errors, slow convergence speed and easy to fall into local precocity in solving the multipath mitigation problem of UAVs. To solve these problems, a chaos chicken swarm-based constant modulus blind equalization algorithm (C-CSO-CMA) is proposed in this paper. On the basis of CMA, the proposed algorithm introduces the chicken learning coefficient into the chicken swarm optimization algorithm (CSO). Furthermore chaotic mutation is used for each chicken subgroup to achieve the global optimum. Finally, the experimental results show that the proposed algorithm not only has small steady-state error, fast convergence speed, but also has strong global convergence ability.
- Open Access
- 1 January 2021
- Published by Taylor & Francis in Cogent Education
- Vol. 8 (1)
Metaphor Enriched Medical English Supplement for First-year Students in an Selected Chinese Medical University
Based on the conceptual metaphor theory, this paper focuses on applying the metaphor-enriched medical English supplement to the College English class to facilitate the metaphoric competence of students and the learning of Medical English, aiming to facilitate college students to migrate smoothly from English for General Purposes to English for Specific Purposes (Medical English). One unit in the textbook was selected to be analyzed from the prospective of metaphor and the related medical knowledge was supplemented. A test was conducted before and after the implementation as the pre-test and the post-test. The collected data were analyzed via NVivo 11 and SPSS 22.0. The result shows that metaphor-enriched medical English supplement did improve students’ metaphoric competence and enlarge their medical knowledge. On one hand, the metaphorical cognitive mechanism is consistent with the process of English learning which is an interaction between the old language knowledge and the new one. On the other hand, it is an effective method to understand medical words by metaphoric thinking, that is, to perceive as many morphemes as possible from the existing Medical English terms and remember these terms in relation to their forms.
- 1 January 2021
- Published by Taylor & Francis in Cogent Education
- Vol. 8 (1)
Open AccessMetaphor Enriched Medical English Supplement for First-year Students in an Selected Chinese Medical University
Based on the conceptual metaphor theory, this paper focuses on applying the metaphor-enriched medical English supplement to the College English class to facilitate the metaphoric competence of students and the learning of Medical English, aiming to facilitate college students to migrate smoothly from English for General Purposes to English for Specific Purposes (Medical English). One unit in the textbook was selected to be analyzed from the prospective of metaphor and the related medical knowledge was supplemented. A test was conducted before and after the implementation as the pre-test and the post-test. The collected data were analyzed via NVivo 11 and SPSS 22.0. The result shows that metaphor-enriched medical English supplement did improve students’ metaphoric competence and enlarge their medical knowledge. On one hand, the metaphorical cognitive mechanism is consistent with the process of English learning which is an interaction between the old language knowledge and the new one. On the other hand, it is an effective method to understand medical words by metaphoric thinking, that is, to perceive as many morphemes as possible from the existing Medical English terms and remember these terms in relation to their forms.
- Open Access
- 1 January 2019
- Published by Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences in Acta Physica Sinica
- Vol. 68 (12) , 124702-124702-11
Surface effects on Couette gas flows in nanochannels
A three-dimensional non-equilibrium molecular dynamics method is adopted to investigate the influence of wall force field on the nanoscale gas flow in the transition regime. For the gas flow under nanoscale condition, the dominant effect of the wall force field on the flow field is more obvious, and the flow physical quantity is more sensitive to the change of the wall condition and system temperature. The motion of the wall atoms is governed by the Einstein theory, with using an elastic coefficient k to model the surface stiffness. The results indicate that the surface stiffness has little effect on the physical quantity distribution of the bulk flow region, but a certain influence on that of the near wall region. Increasing the value of the stiffness changes the velocity peak of the gas in the near-wall region and the tangential momentum adaptation coefficient (TMAC) towards lower values, thus demoting the momentum adaptability of the gas molecules to the surface. The wall roughness is simulated by a typical pyramidal model. It is found that the influence of wall roughness on the flow is very obvious, whether it is in the bulk flow region or in the near wall region. For the former case, the increase of roughness leads gas velocity and shear stress to increase, with density and normal stress remaining constant. The linear distribution of physical quantities is also affected to some extent. While for the latter case, as the roughness increases, the velocity of the fluid increases rapidly and approaches to the wall velocity. The peak of density increases, and the adsorption of gas molecules at the surface is obvious. The TMAC approaches to 1, suggesting that the gas and the surface achieve a complete momentum adaptation. Besides, the influence of system temperature on the gas flow in the nanochannel is also studied. The system temperature is controlled by the Nose-Hoover thermostat, making the flow field maintained at the target temperature through the damping coefficient. The results show that the effect of temperature is global in the whole flow region. The increase of temperature causes the flow velocity of the whole flow field to decrease, while the normal stress and shear stress to increase. A higher temperature leads to more frequent collisions between gas molecules, thus increasing the effective viscosity of the gas. At the same time, the degree of gas molecule adsorption in the near-wall region is reduced, contributing to a smaller TMAC value, and consequently a weaker gas-surface interaction.
- 1 January 2019
- Published by Acta Physica Sinica, Chinese Physical Society and Institute of Physics, Chinese Academy of Sciences in Acta Physica Sinica
- Vol. 68 (12) , 124702-124702-11
Open AccessSurface effects on Couette gas flows in nanochannels
A three-dimensional non-equilibrium molecular dynamics method is adopted to investigate the influence of wall force field on the nanoscale gas flow in the transition regime. For the gas flow under nanoscale condition, the dominant effect of the wall force field on the flow field is more obvious, and the flow physical quantity is more sensitive to the change of the wall condition and system temperature. The motion of the wall atoms is governed by the Einstein theory, with using an elastic coefficient k to model the surface stiffness. The results indicate that the surface stiffness has little effect on the physical quantity distribution of the bulk flow region, but a certain influence on that of the near wall region. Increasing the value of the stiffness changes the velocity peak of the gas in the near-wall region and the tangential momentum adaptation coefficient (TMAC) towards lower values, thus demoting the momentum adaptability of the gas molecules to the surface. The wall roughness is simulated by a typical pyramidal model. It is found that the influence of wall roughness on the flow is very obvious, whether it is in the bulk flow region or in the near wall region. For the former case, the increase of roughness leads gas velocity and shear stress to increase, with density and normal stress remaining constant. The linear distribution of physical quantities is also affected to some extent. While for the latter case, as the roughness increases, the velocity of the fluid increases rapidly and approaches to the wall velocity. The peak of density increases, and the adsorption of gas molecules at the surface is obvious. The TMAC approaches to 1, suggesting that the gas and the surface achieve a complete momentum adaptation. Besides, the influence of system temperature on the gas flow in the nanochannel is also studied. The system temperature is controlled by the Nose-Hoover thermostat, making the flow field maintained at the target temperature through the damping coefficient. The results show that the effect of temperature is global in the whole flow region. The increase of temperature causes the flow velocity of the whole flow field to decrease, while the normal stress and shear stress to increase. A higher temperature leads to more frequent collisions between gas molecules, thus increasing the effective viscosity of the gas. At the same time, the degree of gas molecule adsorption in the near-wall region is reduced, contributing to a smaller TMAC value, and consequently a weaker gas-surface interaction.