Search Results for author: Sing Bing Kang

Found 33 papers, 4 papers with code

Visual Attribute Transfer through Deep Image Analogy

5 code implementations2 May 2017 Jing Liao, Yuan YAO, Lu Yuan, Gang Hua, Sing Bing Kang

We propose a new technique for visual attribute transfer across images that may have very different appearance but have perceptually similar semantic structure.

Attribute

LASER: LAtent SpacE Rendering for 2D Visual Localization

1 code implementation CVPR 2022 Zhixiang Min, Naji Khosravan, Zachary Bessinger, Manjunath Narayana, Sing Bing Kang, Enrique Dunn, Ivaylo Boyadzhiev

LASER introduces the concept of latent space rendering, where 2D pose hypotheses on the floor map are directly rendered into a geometrically-structured latent space by aggregating viewing ray features.

Indoor Localization Metric Learning +1

Memory-augmented Attention Modelling for Videos

1 code implementation7 Nov 2016 Rasool Fakoor, Abdel-rahman Mohamed, Margaret Mitchell, Sing Bing Kang, Pushmeet Kohli

We present a method to improve video description generation by modeling higher-order interactions between video frames and described concepts.

Video Description

Semantic-driven Generation of Hyperlapse from $360^\circ$ Video

no code implementations31 Mar 2017 Wei-Sheng Lai, Yujia Huang, Neel Joshi, Chris Buehler, Ming-Hsuan Yang, Sing Bing Kang

We present a system for converting a fully panoramic ($360^\circ$) video into a normal field-of-view (NFOV) hyperlapse for an optimal viewing experience.

Video Stabilization

Automatic Layer Separation using Light Field Imaging

no code implementations15 Jun 2015 Qiaosong Wang, Haiting Lin, Yi Ma, Sing Bing Kang, Jingyi Yu

We propose a novel approach that jointly removes reflection or translucent layer from a scene and estimates scene depth.

Resolving Scale Ambiguity Via XSlit Aspect Ratio Analysis

no code implementations ICCV 2015 Wei Yang, Haiting Lin, Sing Bing Kang, Jingyi Yu

We first conduct a comprehensive analysis to characterize DDAR, infer object depth from its AR, and model recoverable depth range, sensitivity, and error.

3D Reconstruction

A Light Transport Model for Mitigating Multipath Interference in TOF Sensors

no code implementations CVPR 2015 Nikhil Naik, Achuta Kadambi, Christoph Rhemann, Shahram Izadi, Ramesh Raskar, Sing Bing Kang

Continuous-wave Time-of-flight (TOF) range imaging has become a commercially viable technology with many applications in computer vision and graphics.

Automatic 3D Indoor Scene Modeling From Single Panorama

no code implementations CVPR 2018 Yang Yang, Shi Jin, Ruiyang Liu, Sing Bing Kang, Jingyi Yu

The recovered layout is then used to guide shape estimation of the remaining objects using their normal information.

object-detection Object Detection +1

Fast Patch-Based Denoising Using Approximated Patch Geodesic Paths

no code implementations CVPR 2013 Xiaogang Chen, Sing Bing Kang, Jie Yang, Jingyi Yu

PatchGPs treat image patches as nodes and patch differences as edge weights for computing the shortest (geodesic) paths.

Image Denoising

Recovering Stereo Pairs from Anaglyphs

no code implementations CVPR 2013 Armand Joulin, Sing Bing Kang

An anaglyph is a single image created by selecting complementary colors from a stereo color pair; the user can perceive depth by viewing it through color-filtered glasses.

A Learning-to-Rank Approach for Image Color Enhancement

no code implementations CVPR 2014 Jianzhou Yan, Stephen Lin, Sing Bing Kang, Xiaoou Tang

We present a machine-learned ranking approach for automatically enhancing the color of a photograph.

Learning-To-Rank

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

Time-Mapping Using Space-Time Saliency

no code implementations CVPR 2014 Feng Zhou, Sing Bing Kang, Michael F. Cohen

We describe a new approach for generating regular-speed, low-frame-rate (LFR) video from a high-frame-rate (HFR) input while preserving the important moments in the original.

Ranked #6 on Video Salient Object Detection on DAVSOD-Difficult20 (using extra training data)

Tone Mapping Video Salient Object Detection

A Light Transport Model for Mitigating Multipath Interference in Time-of-Flight Sensors

no code implementations CVPR 2015 Nikhil Naik, Achuta Kadambi, Christoph Rhemann, Shahram Izadi, Ramesh Raskar, Sing Bing Kang

Continuous-wave Time-of-flight (TOF) range imaging has become a commercially viable technology with many applications in computer vision and graphics.

Ambient Occlusion via Compressive Visibility Estimation

no code implementations CVPR 2015 Wei Yang, Yu Ji, Haiting Lin, Yang Yang, Sing Bing Kang, Jingyi Yu

This enables a sparsity-prior based solution for iteratively recovering the surface normal, the surface albedo, and the visibility function from a small number of images.

Compressive Sensing

Depth Recovery From Light Field Using Focal Stack Symmetry

no code implementations ICCV 2015 Haiting Lin, Can Chen, Sing Bing Kang, Jingyi Yu

The other is a data consistency measure based on analysis-by-synthesis, i. e., the difference between the synthesized focal stack given the hypothesized depth map and that from the LF.

Privacy Preserving Image-Based Localization

no code implementations CVPR 2019 Pablo Speciale, Johannes L. Schönberger, Sing Bing Kang, Sudipta N. Sinha, Marc Pollefeys

Current localization systems rely on the persistent storage of 3D point clouds of the scene to enable camera pose estimation, but such data reveals potentially sensitive scene information.

Image-Based Localization Mixed Reality +2

3D Face Reconstruction Using Color Photometric Stereo with Uncalibrated Near Point Lights

no code implementations4 Apr 2019 Zhang Chen, Yu Ji, Mingyuan Zhou, Sing Bing Kang, Jingyi Yu

We avoid the need for spatial constancy of albedo; instead, we use a new measure for albedo similarity that is based on the albedo norm profile.

3D Face Reconstruction Semantic Segmentation

DepthTransfer: Depth Extraction from Video Using Non-parametric Sampling

no code implementations24 Dec 2019 Kevin Karsch, Ce Liu, Sing Bing Kang

We describe a technique that automatically generates plausible depth maps from videos using non-parametric depth sampling.

Depth Estimation Optical Flow Estimation

Depth Extraction from Video Using Non-parametric Sampling

no code implementations24 Dec 2019 Kevin Karsch, Ce Liu, Sing Bing Kang

We describe a technique that automatically generates plausible depth maps from videos using non-parametric depth sampling.

Depth Estimation Optical Flow Estimation

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

U2RLE: Uncertainty-Guided 2-Stage Room Layout Estimation

no code implementations17 Apr 2023 Pooya Fayyazsanavi, Zhiqiang Wan, Will Hutchcroft, Ivaylo Boyadzhiev, Yuguang Li, Jana Kosecka, Sing Bing Kang

While the existing deep learning-based room layout estimation techniques demonstrate good overall accuracy, they are less effective for distant floor-wall boundary.

Room Layout Estimation

Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation

no code implementations26 Apr 2023 Negar Nejatishahidin, Will Hutchcroft, Manjunath Narayana, Ivaylo Boyadzhiev, Yuguang Li, Naji Khosravan, Jana Kosecka, Sing Bing Kang

In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360$^\circ$ panoramas under upright-camera assumption.

Pose Estimation

iBARLE: imBalance-Aware Room Layout Estimation

no code implementations29 Aug 2023 Taotao Jing, Lichen Wang, Naji Khosravan, Zhiqiang Wan, Zachary Bessinger, Zhengming Ding, Sing Bing Kang

iBARLE consists of (1) Appearance Variation Generation (AVG) module, which promotes visual appearance domain generalization, (2) Complex Structure Mix-up (CSMix) module, which enhances generalizability w. r. t.

Avg Domain Generalization +1

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