Yifan Peng
YOU?
Author Swipe
View article: A CLIP-Based Cross-Modal Matching Model for Image-Text Retrieval
A CLIP-Based Cross-Modal Matching Model for Image-Text Retrieval Open
In recent years, the demand for multimodal data retrieval has been growing rapidly. As two major modalities for information transmission, images and texts exhibit significant differences in feature distribution. To address challenges in im…
View article: Learning RGBD imaging via asymmetrically focused stereo cameras
Learning RGBD imaging via asymmetrically focused stereo cameras Open
RGBD imaging can enable a wide range of applications in computer vision, such as 3D reconstruction, object detection, and scene understanding. While depth estimation through stereo matching has been widely studied, real-world scenarios int…
View article: Propagation-adaptive 4K computer-generated holography using physics-constrained spatial and Fourier neural operator
Propagation-adaptive 4K computer-generated holography using physics-constrained spatial and Fourier neural operator Open
Computer-generated holography (CGH) offers a promising method to create true-to-life reconstructions of objects. While recent advances in deep learning-based CGH algorithms have significantly improved the tradeoff between algorithm runtime…
View article: Enhanced Velocity Field Modeling for Gaussian Video Reconstruction
Enhanced Velocity Field Modeling for Gaussian Video Reconstruction Open
High-fidelity 3D video reconstruction is essential for enabling real-time rendering of dynamic scenes with realistic motion in virtual and augmented reality (VR/AR). The deformation field paradigm of 3D Gaussian splatting has achieved near…
View article: Retained imaging quality with reduced manufacturing precision: leveraging computational optics
Retained imaging quality with reduced manufacturing precision: leveraging computational optics Open
View article: Regulation-aware freeform headlamp reflector design with differentiable ray tracing
Regulation-aware freeform headlamp reflector design with differentiable ray tracing Open
Headlamp design is an essential aspect of the automotive industry, often relying on reflector systems composed of freeform surfaces. Traditional methods depend on manually adjusting surfaces to ensure reflected rays meet regulation require…
View article: Optimization-Free Diffusion Model -- A Perturbation Theory Approach
Optimization-Free Diffusion Model -- A Perturbation Theory Approach Open
Diffusion models have emerged as a powerful framework in generative modeling, typically relying on optimizing neural networks to estimate the score function via forward SDE simulations. In this work, we propose an alternative method that i…
View article: In situ fully vectorial tomography and pupil function retrieval of tightly focused fields
In situ fully vectorial tomography and pupil function retrieval of tightly focused fields Open
Tightly focused optical fields are essential in nano-optics, but their applications have been limited by the challenges of accurate yet efficient characterization. In this article, we develop an in situ method for reconstructing the fully …
View article: Development and Validation of Natural Language Processing Algorithms in the ENACT National Electronic Health Record Research Network
Development and Validation of Natural Language Processing Algorithms in the ENACT National Electronic Health Record Research Network Open
Electronic health record (EHR) data are a rich and invaluable source of real-world clinical information, enabling detailed insights into patient populations, treatment outcomes, and healthcare practices. The availability of large volumes o…
View article: Polarized image feature fusion in power inspection
Polarized image feature fusion in power inspection Open
View article: Learned off-aperture Encoding for Wide Field-of-view RGBD Imaging
Learned off-aperture Encoding for Wide Field-of-view RGBD Imaging Open
End-to-end (E2E) designed imaging systems integrate coded optical designs with decoding algorithms to enhance imaging fidelity for diverse visual tasks. However, existing E2E designs encounter significant challenges in maintaining high ima…
View article: Development and validation of natural language processing algorithms in the national ENACT network
Development and validation of natural language processing algorithms in the national ENACT network Open
Objective: Electronic Health Record (EHR) data are critical for advancing translational research and AI technologies. The ENACT network offers access to structured EHR data across 57 CTSA hubs. However, substantial information is contained…
View article: Embodied neuromorphic synergy for lighting-robust machine vision to see in extreme bright
Embodied neuromorphic synergy for lighting-robust machine vision to see in extreme bright Open
Proper exposure settings are crucial for modern machine vision cameras to accurately convert light into clear images. However, traditional auto-exposure solutions are vulnerable to illumination changes, splitting the continuous acquisition…
View article: Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering
Local Gaussian Density Mixtures for Unstructured Lumigraph Rendering Open
View article: Learned Multi-aperture Color-coded Optics for Snapshot Hyperspectral Imaging
Learned Multi-aperture Color-coded Optics for Snapshot Hyperspectral Imaging Open
Learned optics, which incorporate lightweight diffractive optics, coded-aperture modulation, and specialized image-processing neural networks, have recently garnered attention in the field of snapshot hyperspectral imaging (HSI). While con…
View article: In situ fully vectorial tomography and pupil function retrieval of tightly focused fields
In situ fully vectorial tomography and pupil function retrieval of tightly focused fields Open
Tightly focused optical fields are essential in nano-optics, but their applications have been limited by the challenges of accurate yet efficient characterization. In this article, we develop an in situ method for reconstructing the fully …
View article: Physics-aware cross-domain fusion aids learning-driven computer-generated holography
Physics-aware cross-domain fusion aids learning-driven computer-generated holography Open
The rapid advancement of computer-generated holography has bridged deep learning with traditional optical principles in recent years. However, a critical challenge in this evolution is the efficient and accurate conversion from the amplitu…
View article: Some remarks on the argument appealing to nature against synthetic biology
Some remarks on the argument appealing to nature against synthetic biology Open
This paper will focus on analyzing the argument with appealing to nature against synthetic biology and provide a counter-argument against it through demonstrating the ambiguity of the concept of nature, denying the existence of a morally s…
View article: Hybrid design scheme for enabling large-aperture diffractive achromat imaging
Hybrid design scheme for enabling large-aperture diffractive achromat imaging Open
Diffractive achromats (DAs) combined with image processing algorithms offer a promising lens solution for high-performance ultra-thin imagers. However, the design of large-aperture DAs that align seamlessly with image processing algorithms…
View article: Full-colour 3D holographic augmented-reality displays with metasurface waveguides
Full-colour 3D holographic augmented-reality displays with metasurface waveguides Open
View article: Learned Scanpaths Aid Blind Panoramic Video Quality Assessment
Learned Scanpaths Aid Blind Panoramic Video Quality Assessment Open
Panoramic videos have the advantage of providing an immersive and interactive viewing experience. Nevertheless, their spherical nature gives rise to various and uncertain user viewing behaviors, which poses significant challenges for panor…
View article: High-fidelity models for the online control of power ramps in fuel displacement systems – Revisiting the ISABELLE experiment in the OSIRIS Material Testing Reactor
High-fidelity models for the online control of power ramps in fuel displacement systems – Revisiting the ISABELLE experiment in the OSIRIS Material Testing Reactor Open
The Jules Horowitz Reactor (JHR) is an MTR under construction at the CEA Cadarache, France. Its design and future operation build upon the lessons learned from the OSIRIS MTR. The CEA intends to transfer the knowledge accumulated with the …
View article: Exploring angular-steering illumination-based eyebox expansion for holographic displays
Exploring angular-steering illumination-based eyebox expansion for holographic displays Open
Holography represents an enabling technology for next-generation virtual and augmented reality systems. However, it remains challenging to achieve both wide field of view and large eyebox at the same time for holographic near-eye displays,…
View article: Modeling off-axis diffraction with the least-sampling angular spectrum method
Modeling off-axis diffraction with the least-sampling angular spectrum method Open
Accurately yet efficiently simulating off-axis diffraction is vital to design large-scale computational optics, but existing rigid sampling and modeling schemes fail to address this. Herein, we establish a universal least-sampling angular …
View article: Optical neural network via loose neuron array and functional learning
Optical neural network via loose neuron array and functional learning Open
View article: Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation
Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation Open
Implicit neural rendering, which uses signed distance function (SDF) representation with geometric priors (such as depth or surface normal), has led to impressive progress in the surface reconstruction of large-scale scenes. However, apply…
View article: Off-Axis Layered Displays: Hybrid Direct-View/Near-Eye Mixed Reality with Focus Cues
Off-Axis Layered Displays: Hybrid Direct-View/Near-Eye Mixed Reality with Focus Cues Open
This work introduces off-axis layered displays, the first approach to stereoscopic direct-view displays with support for focus cues. Off-axis layered displays combine a head-mounted display with a traditional direct-view display for encodi…
View article: Efficient long-range convolutions for point clouds
Efficient long-range convolutions for point clouds Open
View article: Temperature‐Robust Learned Image Recovery for Shallow‐Designed Imaging Systems
Temperature‐Robust Learned Image Recovery for Shallow‐Designed Imaging Systems Open
Imaging systems are widely applied in harsh environments where the performance of shallow‐designed systems may deviate from expectation. As a representative scenario, environmental temperature variation may degrade image quality due to the…
View article: Investigating deep optics model representation in affecting resolved all-in-focus image quality and depth estimation fidelity
Investigating deep optics model representation in affecting resolved all-in-focus image quality and depth estimation fidelity Open
The end-to-end (E2E) optimization of optics and image processing, dubbed deep optics, has renewed the state-of-the-art in various computer vision tasks. However, specifying the proper model representation or parameterization of the optical…