Homepage

Jia-Wang Bian, 边佳旺

POSTDOCTORAL RESEARCHER

DEPARTMENT OF COMPUTER VISION, MBZUAI

EMAIL: JIAWANG.BIAN(at)MBZUAI.AC.AE

Biography

Jiawang is currently a postdoctoral researcher at MBZUAI working with Prof. Ian Reid. Before that, he was a postdoctoral researcher at the University of Oxford working with Prof. ‪Philip Torr and Prof. Victor Adrian Prisacariu. Jiawang received his B.Eng degree from Nankai University, advised by Prof. Ming-Ming Cheng. After that, he did a research assistant job at the Singapore University of Technology and Design. He received his Ph.D. degree from the University of Adelaide, advised by Prof. Ian Reid and Prof. Chunhua Shen. Also, Jiawang did research intern jobs in research institutes/companies, including the Advanced Digital Sciences Center, Tusimple, Amazon, and Facebook. His research interests lie in 3D Computer Vision, involving scene/object reconstruction, generation, and pose estimation.

Selected Papers

• Feature Correspondence
  • GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature correspondence, IJCV 2020 (CVPR 2017)
  • An Evaluation of Feature Matchers for Fundamental Matrix Estimation, BMVC 2019
• Depth Estimation and Visual Odometry
  • Visual Odometry Revisited: What Should Be Learnt? ICRA 2020
  • [SC-Depth] Unsupervised Scale-consistent Depth Learning from Video, IJCV 2021 (NeurIPS 2019)
  • [SC-DepthV2] Auto-Rectify Network for Unsupervised Indoor Depth Estimation, TPAMI 2021
  • [SC-DepthV3] Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes, TPMAI 2023
• NeRF and 3D Reconstruction
  • NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior, CVPR 2023
  • MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices, CVPR 2023
  • PoRF: Pose Residual Field for Accurate Neural Surface Reconstruction, ICLR 2024
  • Neural Refinement for Absolute Pose Regression with Feature Synthesis, CVPR 2024
• 3D Generation and Editing
  • GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing, ArXiv 2024

Invited Presentations

• [12/2023] High-quality Neural Reconstruction in Real-world Scenes, presented at MBZUAI, Nanjing University, Shanghai Jiao Tong University, and Zhejiang University.
• [11/2023] Self-supervised Depth Estimation in Dynamic Scenes, an online presentation hosted by Jiangmen (将门).
• [07/2022] Unsupervised Indoor Depth Estimation, an online presentation hosted by Intelligent Things (智东西).
• [05/2022] An Overview of Unsupervised Monocular Depth Estimation, presented at the University of Electronic Science and Technology of China (UESTC) and Hefei University of Technology.
• [11/2019] Unsupervised Scale-Consistent Depth Estimation for Visual SLAM, an online presentation hosted by EXTREME VISION （极市）.
• [06/2017] Robust Feature Matching and Fast GMS Solution, online presented via both EXTREME VISION (极市) and VALSE.

Professional Activities

• Journal Reviewer: TPAMI, IJCV, TRO, TOG, TIP, ISPRS, TMM, KBS, PR, Neurocomputing, RA-L
• Conference Reviewer: NeurIPS, ICLR, CVPR, ICCV, ECCV,  SIGGRAPH, AAAI, ICRA, IROS, BMVC, ACCV, WACV, PRCV, CVM

News

• [03/2024] Join MBZUAI as a Postdoctoral Researcher.
• [02/2024] NeFeS was accepted to CVPR 2024 [arXiv | Project page | Github]
• [02/2024] PoRF was accepted to ICLR 2024. [arXiv | Project page | Github]
• [10/2023] SC-DepthV3 was accepted to TPAMI. [arXiv | Github]
• [03/2023] MobileBrick was accepted to CVPR2023. [arXiv | Project page | GitHub]
• [03/2023] NoPe-NeRF was accepted to CVPR 2023. [arXiv | Project page]
• [09/2022] Join the University of Oxford as a Postdoctoral Researcher.
• [12/2021] SC-DepthV2 (ARN) was accepted to TPAMI. [PDF | Github]
• [12/2021] MobileSal was accepted to TPAMI. [PDF | Github]
• [10/2021] One paper on Semantic Edge Detection was accepted to IJCV. [arXiv | Github]
• [10/2021] NVSS was accepted to 3DV 2021. [PDF | Project page]
• [05/2021] SC-Depth was accepted to IJCV. [PDF | GitHub]
• [02/2021] SAMNet was accepted to TIP. [PDF | Github]
• [12/2020] One paper on Person Search was accepted to AAAI 2021. [arXiv | GitHub]
• [02/2020] One paper on Video-based Person Re-ID was accepted to TPAMI. [arXiv | GitHub]
• [01/2020] DF-VO was accepted to ICRA 2020. [arXiv | GitHub]
• [12/2019] GMS has been published in IJCV. [PDF | GitHub] 
• [09/2019] DNCL was accepted to TPAMI. [PDF | GitHub]
• [09/2019] SC-SfMLearner was accepted to NeurIPS 2019. [PDF | GitHub]

Featured Projects