Search Results for author: Jinsun Park

Found 12 papers, 9 papers with code

Deep Depth Estimation From Thermal Image

1 code implementation CVPR 2023 Ukcheol Shin, Jinsun Park, In So Kweon

Secondly, we conduct an exhaustive validation process of monocular and stereo depth estimation algorithms designed on visible spectrum bands to benchmark their performance in the thermal image domain.

Autonomous Driving Self-Driving Cars +1

Lightweight Alpha Matting Network Using Distillation-Based Channel Pruning

1 code implementation14 Oct 2022 Donggeun Yoon, Jinsun Park, Donghyeon Cho

Therefore, there has been a demand for a lightweight alpha matting model due to the limited computational resources of commercial portable devices.

Image Matting Semantic Segmentation

Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation

no code implementations30 Apr 2022 Daehan Kim, Minseok Seo, Jinsun Park, Dong-Geol Choi

In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation.

Domain Adaptation Semantic Segmentation +1

MC-Calib: A generic and robust calibration toolbox for multi-camera systems

1 code implementation Computer Vision and Image Understanding 2022 Francois Rameau, Jinsun Park, Oleksandr Bailo, In So Kweon

In this paper, we present MC-Calib, a novel and robust toolbox dedicated to the calibration of complex synchronized multi-camera systems using an arbitrary number of fiducial marker-based patterns.

Camera Calibration

SALT : Sharing Attention between Linear layer and Transformer for tabular dataset

1 code implementation29 Sep 2021 Juseong Kim, Jinsun Park, Giltae Song

The proposed SALT consists of two blocks: Transformers and linear layers blocks that take advantage of shared attention matrices.

Propose-and-Attend Single Shot Detector

no code implementations30 Jul 2019 Ho-Deok Jang, Sanghyun Woo, Philipp Benz, Jinsun Park, In So Kweon

We present a simple yet effective prediction module for a one-stage detector.

A Unified Approach of Multi-scale Deep and Hand-crafted Features for Defocus Estimation

1 code implementation CVPR 2017 Jinsun Park, Yu-Wing Tai, Donghyeon Cho, In So Kweon

In this paper, we introduce robust and synergetic hand-crafted features and a simple but efficient deep feature from a convolutional neural network (CNN) architecture for defocus estimation.

Defocus Estimation Image Generation

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