14 citations · 35 across the 15 of their papers we have counts for
10 papers · 1 filter
Recursive Video Lane Detection
Dongkwon Jin, Dahyun Kim, Chang-Su Kim
A novel algorithm to detect road lanes in videos, called recursive video lane detector (RVLD), is proposed in this paper, which propagates the state of a current frame recursively…
BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation
Junheum Park, Jintae Kim, Chang-Su Kim
A novel 4K video frame interpolator based on bilateral transformer (BiFormer) is proposed in this paper, which performs three steps: global motion estimation, local motion refineme…
Versatile Depth Estimator Based on Common Relative Depth Estimation and Camera-Specific Relative-to-Metric Depth Conversion
Jinyoung Jun, Jae-Han Lee, Chang-Su Kim
A typical monocular depth estimator is trained for a single camera, so its performance drops severely on images taken with different cameras. To address this issue, we propose a ve…
Applying Eigencontours to PolarMask-Based Instance Segmentation
Wonhui Park, Dongkwon Jin, Chang-Su Kim
Eigencontours are the first data-driven contour descriptors based on singular value decomposition. Based on the implementation of ESE-Seg, eigencontours were applied to the instanc…
Depth Map Decomposition for Monocular Depth Estimation
Jinyoung Jun, Jae-Han Lee, Chul Lee +1
We propose a novel algorithm for monocular depth estimation that decomposes a metric depth map into a normalized depth map and scale features. The proposed network is composed of a…
Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes
Dongkwon Jin, Wonhui Park, Seong-Gyun Jeong +2
A novel algorithm to detect road lanes in the eigenlane space is proposed in this paper. First, we introduce the notion of eigenlanes, which are data-driven descriptors for structu…
Semantic Line Detection Using Mirror Attention and Comparative Ranking and Matching
Dongkwon Jin, Jun-Tae Lee, Chang-Su Kim
A novel algorithm to detect semantic lines is proposed in this paper. We develop three networks: detection network with mirror attention (D-Net) and comparative ranking and matchin…
Eigencontours: Novel Contour Descriptors Based on Low-Rank Approximation
Wonhui Park, Dongkwon Jin, Chang-Su Kim
Novel contour descriptors, called eigencontours, based on low-rank approximation are proposed in this paper. First, we construct a contour matrix containing all object boundaries i…
BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation
Junheum Park, Keunsoo Ko, Chul Lee +1
Video interpolation increases the temporal resolution of a video sequence by synthesizing intermediate frames between two consecutive frames. We propose a novel deep-learning-based…
Interactive Video Object Segmentation Using Global and Local Transfer Modules
Yuk Heo, Yeong Jun Koh, Chang-Su Kim
An interactive video object segmentation algorithm, which takes scribble annotations on query objects as input, is proposed in this paper. We develop a deep neural network, which c…