Xingyu Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xingyu Chen has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Xinyu Zhang
University of California San Diego, La Jolla, CA, USA
10 shared publications - Ju Ren
Tsinghua University
2 shared publications - Kai Zheng
University of California San Diego, La Jolla, CA, USA
2 shared publications - Ke Sun
University of Michigan, Ann Arbor, MI, USA
2 shared publications - Tzu-Mao Li
UC San Diego, La Jolla, USA
2 shared publications - Wuqiong Zhao
UC San Diego, San Diego, USA
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-19
Dirichlet Splatting: Differentiable Rendering for Wave-Based Inverse Problems
We present Dirichlet Splatting , a physically grounded differentiable rendering method for inverse problems with wave-based coherent sensors. Unlike optical cameras, these sensors observe a scene in a band-limited Fourier space whose continuous point response is complex-valued and oscillatory. Our key observation is that the point spread function of a reflector in this Fourier space is the Dirichlet kernel , not a Gaussian. We instantiate each splat as a Dirichlet kernel in closed form, model each primitive as a planar surfel rendered through a surfel-aware Dirichlet splat whose complex amplitude is set by wave propagation physics, and introduce a sliding Frank-Wolfe adaptation tailored to the rugged, non-convex landscape that the Dirichlet oscillation induces. On terahertz tomography, Dirichlet Splatting recovers reflector geometry with an order of magnitude fewer parameters, faster convergence, and higher accuracy than 3D Gaussian Splatting.
- 9 November 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-19
Open AccessDirichlet Splatting: Differentiable Rendering for Wave-Based Inverse Problems
We present Dirichlet Splatting , a physically grounded differentiable rendering method for inverse problems with wave-based coherent sensors. Unlike optical cameras, these sensors observe a scene in a band-limited Fourier space whose continuous point response is complex-valued and oscillatory. Our key observation is that the point spread function of a reflector in this Fourier space is the Dirichlet kernel , not a Gaussian. We instantiate each splat as a Dirichlet kernel in closed form, model each primitive as a planar surfel rendered through a surfel-aware Dirichlet splat whose complex amplitude is set by wave propagation physics, and introduce a sliding Frank-Wolfe adaptation tailored to the rugged, non-convex landscape that the Dirichlet oscillation induces. On terahertz tomography, Dirichlet Splatting recovers reflector geometry with an order of magnitude fewer parameters, faster convergence, and higher accuracy than 3D Gaussian Splatting.
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 227-249
Physically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 227-249
Open AccessPhysically Accurate Differentiable Inverse Rendering for Radio Frequency Digital Twin
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1891-1893
Demo: Differentiable Radio Frequency Digital Twin
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1891-1893
Open AccessDemo: Differentiable Radio Frequency Digital Twin
- Open Access
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 564-581
FlowForm: Scalable Passive Metasurface Network for mmWave Coverage Expansion
- 11 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 564-581
Open AccessFlowForm: Scalable Passive Metasurface Network for mmWave Coverage Expansion
- Open Access
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-15
UltraPoser: Pushing the Limits of IMU-based Full-Body Pose Estimation with Ultrasound Sensing on Consumer Wearables
- 27 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-15
Open AccessUltraPoser: Pushing the Limits of IMU-based Full-Body Pose Estimation with Ultrasound Sensing on Consumer Wearables
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 263-276
You Only Render Once: Enhancing Energy and Computation Efficiency of Mobile Virtual Reality
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 263-276
Open AccessYou Only Render Once: Enhancing Energy and Computation Efficiency of Mobile Virtual Reality
- Open Access
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1998-2003
Hybrid Data-Driven and Simulation-Driven Prediction of mmWave Network Performance
Millimeter wave (mmWave) links offer high-bandwidth connectivity for next-generation wireless networks but face challenges in interference management and performance prediction. This paper introduces DDS, a novel hybrid data-driven simulator that accurately predicts link throughput distribution in mmWave networks. DDS leverages readily available physical (PHY) layer measurements and employs a deep reinforcement learning (DRL) framework to interpret the PHY environment and determine appropriate parameters for subsequent simulations. The system integrates a DRL-based parameter tuner with a PHY and MAC layer simulator, bridging the gap between simulation and real-world performance. We conduct comprehensive evaluations of DDS, demonstrating its superior accuracy compared to its baselines. Our experiments validate DDS's effectiveness in enhancing network controller training and deriving optimal network configuration policies in dense mmWave deployments.
- 4 December 2024
- Published by Association for Computing Machinery (ACM)
- p. 1998-2003
Open AccessHybrid Data-Driven and Simulation-Driven Prediction of mmWave Network Performance
Millimeter wave (mmWave) links offer high-bandwidth connectivity for next-generation wireless networks but face challenges in interference management and performance prediction. This paper introduces DDS, a novel hybrid data-driven simulator that accurately predicts link throughput distribution in mmWave networks. DDS leverages readily available physical (PHY) layer measurements and employs a deep reinforcement learning (DRL) framework to interpret the PHY environment and determine appropriate parameters for subsequent simulations. The system integrates a DRL-based parameter tuner with a PHY and MAC layer simulator, bridging the gap between simulation and real-world performance. We conduct comprehensive evaluations of DDS, demonstrating its superior accuracy compared to its baselines. Our experiments validate DDS's effectiveness in enhancing network controller training and deriving optimal network configuration policies in dense mmWave deployments.
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 464-477
RFCanvas: Modeling RF Channel by Fusing Visual Priors and Few-shot RF Measurements
Accurate and responsive simulation of radio frequency (RF) signal propagation is crucial for designing wireless systems operating in dynamic environments. Conventional ray tracing approaches struggle to accurately model the intricate geometries and material properties of objects that impact propagation. Recently proposed neural scene representations can learn such intricacies from RF data, but they treat the entire scene as implicit neural networks, necessitating retraining with a massive amount of RF data upon any environmental changes. In this paper, we propose RFCanvas, which fuses visual priors and RF measurements to achieve high accuracy for realistic scenes and be responsive to environmental changes. To ensure compatibility between visual priors and RF measurements, we introduce RFCanvas scene representations that model shapes and materials of substantial objects with tensorial fields and signed distance fields. We further extract motion information from visual priors to adapt RFCanvas scene representations to scene dynamics. RFCanvas is built upon an end-to-end optimization framework with differentiable RF simulation. Extensive evaluations across real-world wireless communication and sensing environments demonstrate RFCanvas's superiority over both existing methods.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 464-477
Open AccessRFCanvas: Modeling RF Channel by Fusing Visual Priors and Few-shot RF Measurements
Accurate and responsive simulation of radio frequency (RF) signal propagation is crucial for designing wireless systems operating in dynamic environments. Conventional ray tracing approaches struggle to accurately model the intricate geometries and material properties of objects that impact propagation. Recently proposed neural scene representations can learn such intricacies from RF data, but they treat the entire scene as implicit neural networks, necessitating retraining with a massive amount of RF data upon any environmental changes. In this paper, we propose RFCanvas, which fuses visual priors and RF measurements to achieve high accuracy for realistic scenes and be responsive to environmental changes. To ensure compatibility between visual priors and RF measurements, we introduce RFCanvas scene representations that model shapes and materials of substantial objects with tensorial fields and signed distance fields. We further extract motion information from visual priors to adapt RFCanvas scene representations to scene dynamics. RFCanvas is built upon an end-to-end optimization framework with differentiable RF simulation. Extensive evaluations across real-world wireless communication and sensing environments demonstrate RFCanvas's superiority over both existing methods.
- Open Access
- 29 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 62-76
AutoMS: Automated Service for mmWave Coverage Optimization using Low-cost Metasurfaces
MmWave networks offer wide bandwidth for high-speed wireless communication but suffer from limited range and susceptibility to blockage. Existing coverage provisioning solutions not only incur high costs but also require significant expert knowledge and manual efforts. In this paper, we present AutoMS, an automated service framework to optimize mmWave coverage by strategically designing and placing low-cost passive metasurfaces. Our approach consists of three key components: (1) joint optimization of metasurface phase configurations and placement as well as access point beamforming codebooks. (2) a fast 3D ray-tracing simulator for accelerated large-scale metasurface channel modeling. (3) a metasurface design amenable to ultra-low-cost hot stamping fabrication, featuring high reflectivity, near 2π phase control, and wideband support. Simulation and testbed experiments show that AutoMS can increase the median received signal strength by 11 dB in target rooms and over 20 dB at previous blind spots, and improve the median throughput by over 3× in real-world scenarios.
- 29 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 62-76
Open AccessAutoMS: Automated Service for mmWave Coverage Optimization using Low-cost Metasurfaces
MmWave networks offer wide bandwidth for high-speed wireless communication but suffer from limited range and susceptibility to blockage. Existing coverage provisioning solutions not only incur high costs but also require significant expert knowledge and manual efforts. In this paper, we present AutoMS, an automated service framework to optimize mmWave coverage by strategically designing and placing low-cost passive metasurfaces. Our approach consists of three key components: (1) joint optimization of metasurface phase configurations and placement as well as access point beamforming codebooks. (2) a fast 3D ray-tracing simulator for accelerated large-scale metasurface channel modeling. (3) a metasurface design amenable to ultra-low-cost hot stamping fabrication, featuring high reflectivity, near 2π phase control, and wideband support. Simulation and testbed experiments show that AutoMS can increase the median received signal strength by 11 dB in target rooms and over 20 dB at previous blind spots, and improve the median throughput by over 3× in real-world scenarios.
- Open Access
- 28 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 136
Poster: Generalizing mmWave Sensing with Simulation Synthesis and Generative Models
- 28 February 2024
- Published by Association for Computing Machinery (ACM)
- p. 136
Open AccessPoster: Generalizing mmWave Sensing with Simulation Synthesis and Generative Models