Kunming Luo
Scholar

Kunming Luo

Google Scholar ID: liaSLT8AAAAJ
HKUST
computer vision
Citations & Impact
All-time
Citations
641
 
H-index
15
 
i10-index
16
 
Publications
20
 
Co-authors
13
list available
Resume (English only)
Academic Achievements
  • - 2024:
  • - GenN2N: Generative NeRF2NeRF Translation, CVPR 2024
  • - GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning, IJCV 2024
  • - 2023:
  • - Ctrl-Room: Controllable Text-to-3D Room Meshes Generation with Layout Constraints, arxiv, 2023
  • - Iterative Reconstruction Based on Latent Diffusion Model for Sparse Data Reconstruction, arxiv, 2023
  • - AccFlow: Backward Accumulation for Long-Range Optical Flow, ICCV 2023
  • - Learning Optical Flow from Event Camera with Rendered Dataset, ICCV 2023
  • - The Elliptic Energy Loss for Rotated Object Detection in Aerial Images, ICIP 2023
  • - 2022:
  • - RealFlow: EM-based Realistic Optical Flow Datasets Generation from Videos, ECCV 2022
  • - Content-Aware Unsupervised Deep Homography Estimation and Its Extensions, TPAMI 2022
  • - Learning Optical Flow with Adaptive Graph Reasoning, AAAI 2022
  • - 2021:
  • - GyroFlow: Gyroscope-Guided Unsupervised Optical Flow Learning, ICCV 2021
  • - ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling, TCSVT 2021
  • - OIFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning, TIP 2021
  • - Semi-supervised Pixel-level Scene Text Segmentation by Mutually Guided Network, TIP 2021
  • - UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning, CVPR 2021
Research Experience
  • - Research assistant at Megvii Technology Chengdu from 2019 to 2023, supervised by Prof. Shuaicheng Liu.
Education
  • - B.E. degree from the University of Electronic Science and Technology of China (UESTC) in 2016, supervised by Prof. Fanman Meng.
  • - M.S. degree from the University of Electronic Science and Technology of China (UESTC) in 2019, supervised by Prof. Fanman Meng.
  • - PhD student at the Hong Kong University of Science and Technology (HKUST) since 2023, supervised by Prof. Ping Tan.
Background
  • Research interests include computer vision and computer graphics.