DGIST Library Repository

2. Conference Papers22

  Department of Electrical Engineering and Computer Science Computer Vision Lab.

Related Keyword

Showing results 1 to 20 of 22

Conference
Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining
  • Choi, Wonhyeok ; 
  • Hwang, Kyumin ; 
  • Peng, Wei ; 
  • Choi, Minwoo ; 
  • Im, Sunghoon
  • 2025-04-26
  • Choi, Wonhyeok. (2025-04-26). Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining. International Conference on Learning Representations, 95218–95236.
  • International Conference on Learning Representations (ICLR)
  • View : 212
  • Download : 0
Conference
Style-Editor: Text-driven Object-centric Style Editing
  • Park, Jihun ; 
  • Gim, Jongmin ; 
  • Lee, Kyoungmin ; 
  • Lee, Seunghun ; 
  • Im, Sunghoon
  • 2025-06-14
  • Park, Jihun. (2025-06-14). Style-Editor: Text-driven Object-centric Style Editing. Conference on Computer Vision and Pattern Recognition (spotlight), 18281–18291.
  • IEEE Computer Society
  • View : 242
  • Download : 0
Conference
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
  • Choi, Wonhyeok ; 
  • Hwang, Kyumin ; 
  • Choi, Minwoo ; 
  • Han, Kiljoon ; 
  • Choi, Wonjoon ; 
  • Shin, Mingyu ; 
  • Im, Sunghoon
  • 2025-02-28
  • Choi, Wonhyeok. (2025-02-28). Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces. AAAI Conference on Artificial Intelligence, 2555–2563. doi: 10.1609/aaai.v39i3.32258
  • Association for the Advancement of Artificial Intelligence
  • View : 30
  • Download : 0
Conference
Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders
  • Gim, Jongmin ; 
  • Park, Jihun ; 
  • Lee, Kyoungmin ; 
  • Im, Sunghoon
  • 2024-12-10
  • Gim, Jongmin. (2024-12-10). Content-Adaptive Style Transfer: A Training-Free Approach with VQ Autoencoders. Asian Conference on Computer Vision, 187–204. doi: 10.1007/978-981-96-0917-8_11
  • Asian Federation of Computer Vision
  • View : 86
  • Download : 0
Conference
JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
  • Han, Woo Kyoung ; 
  • Im, Sunghoon ; 
  • Kim, Jaedeok ; 
  • Jin, Kyong Hwan
  • 2024-06-18
  • Han, Woo Kyoung. (2024-06-18). JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients. Conference on Computer Vision and Pattern Recognition (poster), 2784–2793. doi: 10.1109/CVPR52733.2024.00269
  • IEEE Computer Society
  • View : 72
  • Download : 0
Conference
Density-aware Domain Generalization for LiDAR Semantic Segmentation
  • Kim, Jae-Yeul ; 
  • Woo, Jungwan ; 
  • Shin, Ukcheol ; 
  • Oh, Jean ; 
  • Im, Sunghoon
  • 2024-10-16
  • Kim, Jae-Yeul. (2024-10-16). Density-aware Domain Generalization for LiDAR Semantic Segmentation. IEEE/RSJ International Conference on Intelligent Robots and Systems, 9573–9580. doi: 10.1109/IROS58592.2024.10801829
  • IEEE Robotics and Automation Society
  • View : 74
  • Download : 0
Conference
Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator
  • Choi, Wonhyeok ; 
  • Shin, Mingyu ; 
  • Lee, Hyukzae ; 
  • Cho, Jaehoon ; 
  • Park, Jaehyeon ; 
  • Im, Sunghoon
  • 2024-05-15
  • Choi, Wonhyeok. (2024-05-15). Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator. IEEE International Conference on Robotics and Automation, 14732–14739. doi: 10.1109/ICRA57147.2024.10610716
  • IEEE Robotics and Automation Society
  • View : 84
  • Download : 0
Conference
향상된 연속 코사인 계수 추출을 통한 국소적 함축 신경망 표현 방식의 앤드-투-앤드 JPEG 복호기
  • 한우경 ; 
  • 임성훈 ; 
  • 김재덕 ; 
  • 진경환
  • 2023-11-24
  • 한우경. (2023-11-24). 향상된 연속 코사인 계수 추출을 통한 국소적 함축 신경망 표현 방식의 앤드-투-앤드 JPEG 복호기. 대한전자공학회 2023년도 추계학술대회, 352–355.
  • 대한전자공학회
  • View : 51
  • Download : 0
Conference
BurstM: Deep Burst Multi-scale SR Using Fourier Space with Optical Flow
  • Kang, EungGu ; 
  • Lee, Byeonghun ; 
  • Im, Sunghoon ; 
  • Jin, Kyong Hwan
  • 2024-10-03
  • Kang, EungGu. (2024-10-03). BurstM: Deep Burst Multi-scale SR Using Fourier Space with Optical Flow. European Conference on Computer Vision (poster), 459–477. doi: 10.1007/978-3-031-72946-1_26
  • European Computer Vision Association (ECVA)
  • View : 70
  • Download : 0
Conference
Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains
  • Kim, Jae-Yeul ; 
  • Woo, Jungwan ; 
  • Kim, Jeonghoon ; 
  • Im, Sunghoon
  • 2024-10-03
  • Kim, Jae-Yeul. (2024-10-03). Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains. European Conference on Computer Vision (poster), 310–327. doi: 10.1007/978-3-031-72661-3_18
  • European Computer Vision Association (ECVA)
  • View : 54
  • Download : 0
Conference
ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack
  • 2021-11-22
  • Park, Dahoon. (2021-11-22). ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack. British Machine Vision Conference, 1–14.
  • British Machine Vision Association (BMVA)
  • View : 131
  • Download : 50
Conference
Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction
  • Kim, Minsu ; 
  • Lee, Jaewon ; 
  • Lee, Byeonghun ; 
  • Im, Sunghoon ; 
  • Jin, Kyong Hwan
  • 2024-01-05
  • Kim, Minsu. (2024-01-05). Implicit Neural Image Stitching With Enhanced and Blended Feature Reconstruction. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024), 4087–4096. doi: 10.1109/WACV57701.2024.00404
  • IEEE Computer Society, The Computer Vision Foundation
  • View : 212
  • Download : 0
Conference
Offline-to-Online Knowledge Distillation for Video Instance Segmentation
  • Kim, Hojin ; 
  • Lee, Seunghun ; 
  • Kang, Hyeon ; 
  • Im, Sunghoon
  • 2024-01-07
  • Kim, Hojin. (2024-01-07). Offline-to-Online Knowledge Distillation for Video Instance Segmentation. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024), 159–168. doi: 10.1109/WACV57701.2024.00023
  • IEEE Computer Society, The Computer Vision Foundation
  • View : 139
  • Download : 0
Conference
Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation
  • 2023-11-22
  • Kim, Changjae. (2023-11-22). Multi-Target Domain Adaptation with Class-Wise Attribute Transfer in Semantic Segmentation. British Machine Vision Conference, 1–13.
  • The British Machine Vision Association and Society for Pattern Recognition
  • View : 128
  • Download : 59
Conference
Depth-discriminative Metric Learning for Monocular 3D Object Detection
  • 2023-12-13
  • Choi, Wonhyeok. (2023-12-13). Depth-discriminative Metric Learning for Monocular 3D Object Detection. Conference on Neural Information Processing Systems (poster), 1–13.
  • Neural Information Processing Systems Foundation (NeurIPS Foundation)
  • View : 91
  • Download : 0
Conference
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
  • Lee, Seokju ; 
  • Im, Sunghoon ; 
  • Lin, Stephen ; 
  • Kweon, In So
  • 2021-02-05
  • Lee, Seokju. (2021-02-05). Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency. AAAI Conference on Artificial Intelligence, 1863–1872. doi: 10.1609/aaai.v35i3.16281
  • Association for the Advancement of Artificial Intelligence(AAAI)
  • View : 61
  • Download : 0
Conference
DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
  • 2021-06-24
  • Lee, Seunghun. (2021-06-24). DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation. Conference on Computer Vision and Pattern Recognition (poster), 15247–15256. doi: 10.1109/CVPR46437.2021.01500
  • IEEE Computer Society, The Computer Vision Foundation
  • View : 73
  • Download : 0
Conference
VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction
  • Choe, Jaesung ; 
  • Im, Sunghoon ; 
  • Rameau, Francois ; 
  • Kang, Minjun ; 
  • Kweon, In So
  • 2021-10-13
  • Choe, Jaesung. (2021-10-13). VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction. IEEE International Conference on Computer Vision, 16066–16075. doi: 10.1109/ICCV48922.2021.01578
  • IEEE Computer Society and the Computer Vision Foundation (CVF)
  • View : 161
  • Download : 0
Conference
ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
  • Lee, Seunghun ; 
  • Choi, Wonhyeok ; 
  • Kim, Changjae ; 
  • Choi, Minwoo ; 
  • Im, Sunghoon
  • 2022-06-24
  • Lee, Seunghun. (2022-06-24). ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation. Conference on Computer Vision and Pattern Recognition (poster), 19174–19184. doi: 10.1109/CVPR52688.2022.01860
  • IEEE Computer Society, The Computer Vision Foundation
  • View : 141
  • Download : 0
Conference
Facial Depth and Normal Estimation using Single Dual-Pixel Camera
  • Kang, Minjun ; 
  • Choe, Jaesung ; 
  • Ha, Hyowon ; 
  • Jeon, Hae-Gon ; 
  • Im, Sunghoon ; 
  • Kweon, In So ; 
  • Yoon, Kuk-Jin
  • 2022-10-26
  • Kang, Minjun. (2022-10-26). Facial Depth and Normal Estimation using Single Dual-Pixel Camera. European Conference on Computer Vision (poster), 181–200. doi: 10.1007/978-3-031-20074-8_11
  • European Conference on Computer Vision
  • View : 89
  • Download : 0
1 2 >>

Recent Submissions