Search Results for author: Dongbo Min

Found 33 papers, 10 papers with code

Guided Semantic Flow

no code implementations ECCV 2020 Sangryul Jeon, Dongbo Min, Seungryong Kim, Jihwan Choe, Kwanghoon Sohn

Establishing dense semantic correspondences requires dealing with large geometric variations caused by the unconstrained setting of images.

Semantic correspondence

Environment Agnostic Representation for Visual Reinforcement Learning

1 code implementation ICCV 2023 Hyesong Choi, Hunsang Lee, Seongwon Jeong, Dongbo Min

Generalization capability of vision-based deep reinforcement learning (RL) is indispensable to deal with dynamic environment changes that exist in visual observations.

Domain Generalization reinforcement-learning +1

Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning

no code implementations CVPR 2023 Hyesong Choi, Hunsang Lee, Wonil Song, Sangryul Jeon, Kwanghoon Sohn, Dongbo Min

Recent vision-based reinforcement learning (RL) methods have found extracting high-level features from raw pixels with self-supervised learning to be effective in learning policies.

Atari Games reinforcement-learning +3

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

1 code implementation6 Oct 2022 Sunghwan Hong, Jisu Nam, Seokju Cho, Susung Hong, Sangryul Jeon, Dongbo Min, Seungryong Kim

Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters.

Semantic correspondence

Contour-Aware Equipotential Learning for Semantic Segmentation

1 code implementation1 Oct 2022 Xu Yin, Dongbo Min, Yuchi Huo, Sung-Eui Yoon

This novel module transfers the predicted/ground-truth semantic labels to a self-defined potential domain to learn and infer decision boundaries along customized directions.

regression Segmentation +1

Sequential Cross Attention Based Multi-task Learning

1 code implementation6 Sep 2022 Sunkyung Kim, Hyesong Choi, Dongbo Min

The cross-task attention module (CTAM) is first applied to facilitate the exchange of relevant information between the multiple task features of the same scale.

Multi-Task Learning Scene Understanding

PointFix: Learning to Fix Domain Bias for Robust Online Stereo Adaptation

no code implementations27 Jul 2022 Kwonyoung Kim, Jungin Park, Jiyoung Lee, Dongbo Min, Kwanghoon Sohn

To mitigate this issue, we propose to incorporate an auxiliary point-selective network into a meta-learning framework, called PointFix, to provide a robust initialization of stereo models for online stereo adaptation.

Autonomous Driving Meta-Learning

KNN Local Attention for Image Restoration

no code implementations CVPR 2022 Hunsang Lee, Hyesong Choi, Kwanghoon Sohn, Dongbo Min

In this way, the pair-wise operation establishes non-local connectivity while maintaining the desired properties of the local attention, i. e., inductive bias of locality and linear complexity to input resolution.

Deblurring Image Denoising +3

DIML/CVL RGB-D Dataset: 2M RGB-D Images of Natural Indoor and Outdoor Scenes

no code implementations22 Oct 2021 Jaehoon Cho, Dongbo Min, Youngjung Kim, Kwanghoon Sohn

This manual is intended to provide a detailed description of the DIML/CVL RGB-D dataset.

Self-Supervised Structured Representations for Deep Reinforcement Learning

no code implementations29 Sep 2021 Hyesong Choi, Hunsang Lee, Wonil Song, Sangryul Jeon, Kwanghoon Sohn, Dongbo Min

The proposed method imposes similarity constraints on the three latent volumes; warped query representations by estimated flows, predicted target representations from the transition model, and target representations of future state.

Atari Games Image Reconstruction +3

Weakly-Supervised Learning of Disentangled and Interpretable Skills for Hierarchical Reinforcement Learning

no code implementations29 Sep 2021 Wonil Song, Sangryul Jeon, Hyesong Choi, Kwanghoon Sohn, Dongbo Min

Given the latent representations as skills, a skill-based policy network is trained to generate similar trajectories to the learned decoder of the trajectory VAE.

Hierarchical Reinforcement Learning Inductive Bias +3

Self-balanced Learning For Domain Generalization

no code implementations31 Aug 2021 Jin Kim, Jiyoung Lee, Jungin Park, Dongbo Min, Kwanghoon Sohn

Domain generalization aims to learn a prediction model on multi-domain source data such that the model can generalize to a target domain with unknown statistics.

Domain Generalization

On the confidence of stereo matching in a deep-learning era: a quantitative evaluation

1 code implementation2 Jan 2021 Matteo Poggi, Seungryong Kim, Fabio Tosi, Sunok Kim, Filippo Aleotti, Dongbo Min, Kwanghoon Sohn, Stefano Mattoccia

Stereo matching is one of the most popular techniques to estimate dense depth maps by finding the disparity between matching pixels on two, synchronized and rectified images.

Stereo Matching

Pseudo Label-Guided Multi Task Learning for Scene Understanding

no code implementations1 Jan 2021 Sunkyung Kim, Hyesong Choi, Dongbo Min

More importantly, the pseudo depth labels serve to impose a cross-view consistency on the estimated monocular depth and segmentation maps of two views.

Monocular Depth Estimation Multi-Task Learning +5

Adaptive confidence thresholding for monocular depth estimation

1 code implementation ICCV 2021 Hyesong Choi, Hunsang Lee, Sunkyung Kim, Sunok Kim, Seungryong Kim, Kwanghoon Sohn, Dongbo Min

To cope with the prediction error of the confidence map itself, we also leverage the threshold network that learns the threshold dynamically conditioned on the pseudo depth maps.

Monocular Depth Estimation Stereo Matching

Joint Learning of Semantic Alignment and Object Landmark Detection

no code implementations ICCV 2019 Sangryul Jeon, Dongbo Min, Seungryong Kim, Kwanghoon Sohn

Based on the key insight that the two tasks can mutually provide supervisions to each other, our networks accomplish this through a joint loss function that alternatively imposes a consistency constraint between the two tasks, thereby boosting the performance and addressing the lack of training data in a principled manner.


A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation

no code implementations23 Apr 2019 Jaehoon Cho, Dongbo Min, Youngjung Kim, Kwanghoon Sohn

In this paper, we present a simple yet effective approach for monocular depth estimation using stereo image pairs.

Monocular Depth Estimation Semantic Segmentation

Semantic Attribute Matching Networks

no code implementations CVPR 2019 Seungryong Kim, Dongbo Min, Somi Jeong, Sunok Kim, Sangryul Jeon, Kwanghoon Sohn

SAM-Net accomplishes this through an iterative process of establishing reliable correspondences by reducing the attribute discrepancy between the images and synthesizing attribute transferred images using the learned correspondences.


Recurrent Transformer Networks for Semantic Correspondence

1 code implementation NeurIPS 2018 Seungryong Kim, Stephen Lin, Sangryul Jeon, Dongbo Min, Kwanghoon Sohn

Our networks accomplish this through an iterative process of estimating spatial transformations between the input images and using these transformations to generate aligned convolutional activations.

General Classification Semantic correspondence

PARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence

no code implementations ECCV 2018 Sangryul Jeon, Seungryong Kim, Dongbo Min, Kwanghoon Sohn

To the best of our knowledge, it is the first work that attempts to estimate dense affine transformation fields in a coarse-to-fine manner within deep networks.

regression Semantic correspondence

DCTM: Discrete-Continuous Transformation Matching for Semantic Flow

no code implementations ICCV 2017 Seungryong Kim, Dongbo Min, Stephen Lin, Kwanghoon Sohn

In this way, our approach draws solutions from the continuous space of affine transformations in a manner that can be computed efficiently through constant-time edge-aware filtering and a proposed affine-varying CNN-based descriptor.

Semantic correspondence

Fast 2-D Complex Gabor Filter with Kernel Decomposition

no code implementations18 Apr 2017 Suhyuk Um, Jaeyoon Kim, Dongbo Min

To obtain the 2-D complex Gabor filter bank output, existing methods are repeatedly applied with respect to multiple orientations and frequencies.

FCSS: Fully Convolutional Self-Similarity for Dense Semantic Correspondence

1 code implementation CVPR 2017 Seungryong Kim, Dongbo Min, Bumsub Ham, Sangryul Jeon, Stephen Lin, Kwanghoon Sohn

The sampling patterns of local structure and the self-similarity measure are jointly learned within the proposed network in an end-to-end and multi-scale manner.

Object Semantic correspondence +1

Deeply Aggregated Alternating Minimization for Image Restoration

no code implementations CVPR 2017 Youngjung Kim, Hyungjoo Jung, Dongbo Min, Kwanghoon Sohn

The proposed framework enables the convolutional neural networks (CNNs) to operate as a prior or regularizer in the AM algorithm.

Image Denoising Image Restoration +1

DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation

no code implementations27 Apr 2016 Seungryong Kim, Dongbo Min, Bumsub Ham, Minh N. Do, Kwanghoon Sohn

In this paper, we propose a novel dense descriptor, called dense adaptive self-correlation (DASC), to estimate multi-modal and multi-spectral dense correspondences.

Efficient Splitting-based Method for Global Image Smoothing

no code implementations26 Apr 2016 Youngjung Kim, Dongbo Min, Bumsub Ham, Kwanghoon Sohn

In this paper, we introduce a highly efficient splitting-based method for global EPS that minimizes the objective function of ${l_2}$ data and prior terms (possibly non-smooth and non-convex) in linear time.

image smoothing

Deep Self-Convolutional Activations Descriptor for Dense Cross-Modal Correspondence

no code implementations21 Mar 2016 Seungryong Kim, Dongbo Min, Stephen Lin, Kwanghoon Sohn

We present a novel descriptor, called deep self-convolutional activations (DeSCA), designed for establishing dense correspondences between images taken under different imaging modalities, such as different spectral ranges or lighting conditions.

SPM-BP: Sped-up PatchMatch Belief Propagation for Continuous MRFs

no code implementations ICCV 2015 Yu Li, Dongbo Min, Michael S. Brown, Minh N. Do, Jiangbo Lu

However, the quality of the PMBP solution is tightly coupled with the local window size, over which the raw data cost is aggregated to mitigate ambiguity in the data constraint.

Optical Flow Estimation

DASC: Dense Adaptive Self-Correlation Descriptor for Multi-Modal and Multi-Spectral Correspondence

no code implementations CVPR 2015 Seungryong Kim, Dongbo Min, Bumsub Ham, Seungchul Ryu, Minh N. Do, Kwanghoon Sohn

To further improve the matching quality and runtime efficiency, we propose a patch-wise receptive field pooling, in which a sampling pattern is optimized with a discriminative learning.

Optical Flow Estimation

Cross-Scale Cost Aggregation for Stereo Matching

1 code implementation CVPR 2014 Kang Zhang, Yuqiang Fang, Dongbo Min, Lifeng Sun, Shiqiang Yang. Shuicheng Yan, Qi Tian

We firstly reformulate cost aggregation from a unified optimization perspective and show that different cost aggregation methods essentially differ in the choices of similarity kernels.

Stereo Matching Stereo Matching Hand

Patch Match Filter: Efficient Edge-Aware Filtering Meets Randomized Search for Fast Correspondence Field Estimation

no code implementations CVPR 2013 Jiangbo Lu, Hongsheng Yang, Dongbo Min, Minh N. Do

Recent studies on fast cost volume filtering based on efficient edge-aware filters have provided a fast alternative to solve discrete labeling problems, with the complexity independent of the support window size.

Computational Efficiency Optical Flow Estimation +1

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