Search Results for author: Jinwei Ye

Found 16 papers, 1 papers with code

3D Fluid Flow Reconstruction Using Compact Light Field PIV

no code implementations ECCV 2020 Zhong Li, Yu Ji, Jingyi Yu, Jinwei Ye

In this paper, we present a PIV solution that uses a compact lenslet-based light field camera to track dense particles floating in the fluid and reconstruct the 3D fluid flow.

Optical Flow Estimation

Unsupervised Region-Growing Network for Object Segmentation in Atmospheric Turbulence

no code implementations6 Nov 2023 Dehao Qin, Ripon Saha, Suren Jayasuriya, Jinwei Ye, Nianyi Li

In this paper, we present a two-stage unsupervised foreground object segmentation network tailored for dynamic scenes affected by atmospheric turbulence.

Object Optical Flow Estimation +2

Textureless Deformable Surface Reconstruction with Invisible Markers

no code implementations25 Aug 2023 Xinyuan Li, Yu Ji, Yanchen Liu, Xiaochen Hu, Jinwei Ye, Changxi Zheng

Leveraging the markers, we design a multi-camera system that captures surface deformation under the UV light and the visible light in a time multiplexing fashion.

3D Reconstruction 3D Shape Reconstruction +1

Light Field-Based Underwater 3D Reconstruction Via Angular Resampling

no code implementations5 Sep 2021 Yuqi Ding, Zhang Chen, Yu Ji, Jingyi Yu, Jinwei Ye

Recovering 3D geometry of underwater scenes is challenging because of non-linear refraction of light at the water-air interface caused by the camera housing.

3D Reconstruction Depth Estimation

Next-generation perception system for automated defects detection in composite laminates via polarized computational imaging

no code implementations24 Aug 2021 Yuqi Ding, Jinwei Ye, Corina Barbalata, James Oubre, Chandler Lemoine, Jacob Agostinho, Genevieve Palardy

Finishing operations on large-scale composite components like wind turbine blades, including trimming and sanding, often require multiple workers and part repositioning.

Learning To Remove Refractive Distortions From Underwater Images

no code implementations ICCV 2021 Simron Thapa, Nianyi Li, Jinwei Ye

The fluctuation of the water surface causes refractive distortions that severely downgrade the image of an underwater scene.

Generative Adversarial Network

Polarimetric Helmholtz Stereopsis

no code implementations ICCV 2021 Yuqi Ding, Yu Ji, Mingyuan Zhou, Sing Bing Kang, Jinwei Ye

Helmholtz stereopsis (HS) exploits the reciprocity principle of light propagation (i. e., the Helmholtz reciprocity) for 3D reconstruction of surfaces with arbitrary reflectance.

3D Reconstruction

PIV-Based 3D Fluid Flow Reconstruction Using Light Field Camera

no code implementations15 Apr 2019 Zhong Li, Jinwei Ye, Yu Ji, Hao Sheng, Jingyi Yu

Particle Imaging Velocimetry (PIV) estimates the flow of fluid by analyzing the motion of injected particles.

Depth Estimation Optical Flow Estimation

Non-Lambertian Surface Shape and Reflectance Reconstruction Using Concentric Multi-Spectral Light Field

no code implementations9 Apr 2019 Mingyuan Zhou, Yu Ji, Yuqi Ding, Jinwei Ye, S. Susan Young, Jingyi Yu

In this paper, we introduce a novel concentric multi-spectral light field (CMSLF) design that is able to recover the shape and reflectance of surfaces with arbitrary material in one shot.

Depth Estimation

Learning to Dodge A Bullet: Concyclic View Morphing via Deep Learning

no code implementations ECCV 2018 Shi Jin, Ruiynag Liu, Yu Ji, Jinwei Ye, Jingyi Yu

The bullet-time effect, presented in feature film ``The Matrix", has been widely adopted in feature films and TV commercials to create an amazing stopping-time illusion.

Robust 3D Human Motion Reconstruction Via Dynamic Template Construction

no code implementations31 Jan 2018 Zhong Li, Yu Ji, Wei Yang, Jinwei Ye, Jingyi Yu

In multi-view human body capture systems, the recovered 3D geometry or even the acquired imagery data can be heavily corrupted due to occlusions, noise, limited field of- view, etc.

Image Pre-compensation: Balancing Contrast and Ringing

no code implementations CVPR 2014 Yu Ji, Jinwei Ye, Sing Bing Kang, Jingyi Yu

In particular, we show that linear tone mapping eliminates ringing but incurs severe contrast loss, while non-linear tone mapping functions such as Gamma curves slightly enhances contrast but introduces ringing.

Tone Mapping

Saliency Detection on Light Field

no code implementations CVPR 2014 Nianyi Li, Jinwei Ye, Yu Ji, Haibin Ling, Jingyi Yu

Existing saliency detection approaches use images as inputs and are sensitive to foreground/background similarities, complex background textures, and occlusions.

Saliency Detection

Reconstructing Gas Flows Using Light-Path Approximation

no code implementations CVPR 2013 Yu Ji, Jinwei Ye, Jingyi Yu

By observing the LF-probe through the gas flow, we acquire a dense set of ray-ray correspondences and then reconstruct their light paths.

Manhattan Scene Understanding via XSlit Imaging

no code implementations CVPR 2013 Jinwei Ye, Yu Ji, Jingyi Yu

Specifically, we prove that parallel 3D lines map to 2D curves in an XSlit image and they converge at an XSlit Vanishing Point (XVP).

Scene Understanding

Cannot find the paper you are looking for? You can Submit a new open access paper.