Search Results for author: Sunghoon Im

Found 23 papers, 9 papers with code

Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator

no code implementations6 Mar 2024 Wonhyeok Choi, Mingyu Shin, Hyukzae Lee, Jaehoon Cho, Jaehyeon Park, Sunghoon Im

Real-time processing is crucial in autonomous driving systems due to the imperative of instantaneous decision-making and rapid response.

Autonomous Driving Decision Making +5

Depth-discriminative Metric Learning for Monocular 3D Object Detection

no code implementations NeurIPS 2023 Wonhyeok Choi, Mingyu Shin, Sunghoon Im

Moreover, we introduce an auxiliary head for object-wise depth estimation, which enhances depth quality while maintaining the inference time.

Depth Estimation Metric Learning +3

Domain Generalization in LiDAR Semantic Segmentation Leveraged by Density Discriminative Feature Embedding

no code implementations19 Dec 2023 Jaeyeul Kim, Jungwan Woo, Jeonghoon Kim, Sunghoon Im

Understanding this, we view each LiDAR's point cloud at various distances as having distinct density distributions, which can be consistent across different LiDAR models.

Domain Generalization LIDAR Semantic Segmentation +1

Implicit Neural Image Stitching

1 code implementation4 Sep 2023 Minsu Kim, Jaewon Lee, Byeonghun Lee, Sunghoon Im, Kyong Hwan Jin

Existing frameworks for image stitching often provide visually reasonable stitchings.

Image Stitching Super-Resolution

Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies

no code implementations CVPR 2023 Wonhyeok Choi, Sunghoon Im

In this paper, we present a new MTL framework that searches for structures optimized for multiple tasks with diverse graph topologies and shares features among tasks.

Multi-Task Learning

Offline-to-Online Knowledge Distillation for Video Instance Segmentation

no code implementations15 Feb 2023 Hojin Kim, Seunghun Lee, Sunghoon Im

In this paper, we present offline-to-online knowledge distillation (OOKD) for video instance segmentation (VIS), which transfers a wealth of video knowledge from an offline model to an online model for consistent prediction.

Data Augmentation Instance Segmentation +3

A Study on the Generality of Neural Network Structures for Monocular Depth Estimation

1 code implementation9 Jan 2023 Jinwoo Bae, Kyumin Hwang, Sunghoon Im

In this paper, we deeply investigate the various backbone networks (e. g. CNN and Transformer models) toward the generalization of monocular depth estimation.

Monocular Depth Estimation

Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation

1 code implementation23 May 2022 Jinwoo Bae, Sungho Moon, Sunghoon Im

In this paper, we investigate the backbone networks (e. g. CNNs, Transformers, and CNN-Transformer hybrid models) toward the generalization of monocular depth estimation.

Monocular Depth Estimation

ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation

no code implementations CVPR 2022 Seunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, Sunghoon Im

In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretrained domain-specific models.

Attribute Domain Adaptation +2

Facial Depth and Normal Estimation using Single Dual-Pixel Camera

no code implementations25 Nov 2021 Minjun Kang, Jaesung Choe, Hyowon Ha, Hae-Gon Jeon, Sunghoon Im, In So Kweon, Kuk-Jin Yoon

Many mobile manufacturers recently have adopted Dual-Pixel (DP) sensors in their flagship models for faster auto-focus and aesthetic image captures.

ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack

1 code implementation1 Nov 2021 Dahoon Park, Kon-Woo Kwon, Sunghoon Im, Jaeha Kung

Many prior works on adversarial weight attack require not only the weight parameters, but also the training or test dataset in searching vulnerable bits to be attacked.

VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction

no code implementations ICCV 2021 Jaesung Choe, Sunghoon Im, Francois Rameau, Minjun Kang, In So Kweon

To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps fusion.

3D Reconstruction 3D Scene Reconstruction +1

DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation

1 code implementation CVPR 2021 Seunghun Lee, Sunghyun Cho, Sunghoon Im

Our model encodes individual representations of content (scene structure) and style (artistic appearance) from both source and target images.

Domain Adaptation

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency

1 code implementation4 Feb 2021 Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision.

Instance Segmentation Monocular Depth Estimation +5

Instance-wise Depth and Motion Learning from Monocular Videos

1 code implementation19 Dec 2019 Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon

We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision.

Instance Segmentation Monocular Depth Estimation +3

Learning Residual Flow as Dynamic Motion from Stereo Videos

no code implementations16 Sep 2019 Seokju Lee, Sunghoon Im, Stephen Lin, In So Kweon

Based on rigid projective geometry, the estimated stereo depth is used to guide the camera motion estimation, and the depth and camera motion are used to guide the residual flow estimation.

Depth And Camera Motion Motion Estimation +4

DPSNet: End-to-end Deep Plane Sweep Stereo

1 code implementation ICLR 2019 Sunghoon Im, Hae-Gon Jeon, Stephen Lin, In So Kweon

The cost volume is constructed using a differentiable warping process that allows for end-to-end training of the network.

Optical Flow Estimation

Robust Depth Estimation from Auto Bracketed Images

no code implementations CVPR 2018 Sunghoon Im, Hae-Gon Jeon, In So Kweon

As demand for advanced photographic applications on hand-held devices grows, these electronics require the capture of high quality depth.

Depth Estimation Stereo Matching +1

Noise Robust Depth From Focus Using a Ring Difference Filter

no code implementations CVPR 2017 Jaeheung Surh, Hae-Gon Jeon, Yunwon Park, Sunghoon Im, Hyowon Ha, In So Kweon

With the result from the FM, the role of a DfF pipeline is to determine and recalculate unreliable measurements while enhancing those that are reliable.

High-Quality Depth From Uncalibrated Small Motion Clip

1 code implementation CVPR 2016 Hyowon Ha, Sunghoon Im, Jaesik Park, Hae-Gon Jeon, In So Kweon

We propose a novel approach that generates a high-quality depth map from a set of images captured with a small viewpoint variation, namely small motion clip.

Camera Calibration Vocal Bursts Intensity Prediction

High Quality Structure From Small Motion for Rolling Shutter Cameras

no code implementations ICCV 2015 Sunghoon Im, Hyowon Ha, Gyeongmin Choe, Hae-Gon Jeon, Kyungdon Joo, In So Kweon

To address these problems, we introduce a novel 3D reconstruction method from narrow-baseline image sequences that effectively handles the effects of a rolling shutter that occur from most of commercial digital cameras.

3D Reconstruction Depth Estimation +1

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