Runze Zhang

ORCID: 0000-0001-9698-0178
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Vision and Imaging
  • Robotics and Sensor-Based Localization
  • 3D Surveying and Cultural Heritage
  • Advanced Image and Video Retrieval Techniques
  • Computational Drug Discovery Methods
  • Optical measurement and interference techniques
  • Bioinformatics and Genomic Networks
  • Protein Structure and Dynamics
  • Antenna Design and Analysis
  • Remote Sensing and LiDAR Applications
  • 3D Shape Modeling and Analysis
  • Microwave Engineering and Waveguides
  • Machine Learning in Materials Science
  • COVID-19 diagnosis using AI
  • Semantic Web and Ontologies
  • Biomedical Text Mining and Ontologies
  • Mathematical Dynamics and Fractals
  • Antenna Design and Optimization
  • Metamaterials and Metasurfaces Applications
  • Manufacturing Process and Optimization
  • Cancer, Stress, Anesthesia, and Immune Response
  • Mathematics and Applications
  • Advanced Neural Network Applications
  • Meromorphic and Entire Functions
  • Advanced Combinatorial Mathematics

Beijing Institute of Technology
2020-2025

University of Chinese Academy of Sciences
2021-2024

Shanghai Institute of Materia Medica
2023-2024

Chinese Academy of Sciences
2021-2024

Stony Brook University
2024

North China University of Science and Technology
2024

Nanjing University
2023-2024

Tencent (China)
2019-2024

Southern University of Science and Technology
2024

Tianjin Medical University General Hospital
2024

Global Structure-from-Motion (SfM) techniques have demonstrated superior efficiency and accuracy than the conventional incremental approach in many recent studies. This work proposes a divide-and-conquer framework to solve very large global SfM at scale of millions images. Specifically, we first divide all images into multiple partitions that preserve strong data association for well-posed parallel local motion averaging. Then, averaging determines cameras partition boundaries similarity...

10.1109/cvpr.2018.00480 article EN 2018-06-01

Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study explored power fine-tuned large models (LLMs) on five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data...

10.1039/d4sc00924j article EN cc-by-nc Chemical Science 2024-01-01

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization mapping (SLAM). Recently, self-supervised learning framework that jointly optimizes target image depth has attracted attention community. Previous works rely on photometric error generated from depths poses between adjacent frames, which contains large systematic under realistic scenes due to reflective surfaces occlusions. In this paper, we bridge gap geometric loss by introducing...

10.1109/icra.2019.8793479 preprint EN 2022 International Conference on Robotics and Automation (ICRA) 2019-05-01

The increasing scale of Structure-from-Motion is fundamentally limited by the conventional optimization framework for all-in-one global bundle adjustment. In this paper, we propose a distributed approach to coping with adjustment very large computation. First, derive formulation from classical algorithm ADMM, Alternating Direction Method Multipliers, based on camera consensus. Then, analyze conditions under which convergence would be guaranteed. particular, adopt over-relaxation and...

10.1109/iccv.2017.13 article EN 2017-10-01

In recent years, sparse voxel-based methods have be-come the state-of-the-arts for 3D semantic segmentation of indoor scenes, thanks to powerful CNNs. Nevertheless, being oblivious underlying geometry, suffer from ambiguous features on spatially close objects and struggle with handling complex irregular geometries due lack geodesic information. view this, we present Voxel-Mesh Network (VMNet), a novel deep architecture that operates voxel mesh representations leveraging both Euclidean...

10.1109/iccv48922.2021.01520 article EN 2021 IEEE/CVF International Conference on Computer Vision (ICCV) 2021-10-01

Lipophilicity is a fundamental physical property that significantly affects various aspects of drug behavior, including solubility, permeability, metabolism, distribution, protein binding, and toxicity. Accurate prediction lipophilicity, measured by the logD7.4 value (the distribution coefficient between n-octanol buffer at physiological pH 7.4), crucial for successful discovery design. However, limited availability data logD modeling poses significant challenge to achieving satisfactory...

10.1186/s13321-023-00754-4 article EN cc-by Journal of Cheminformatics 2023-09-05

Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study explored power fine-tuned large models (LLMs) on five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data...

10.26434/chemrxiv-2023-k7ct5-v2 preprint EN cc-by-nc-nd 2024-02-01

In this paper, we tackle the accurate and consistent Structure from Motion (SfM) problem, in particular camera registration, far exceeding memory of a single computer parallel. Different previous methods which drastically simplify parameters SfM sacrifice accuracy final reconstruction, try to preserve connectivities among cameras by proposing clustering algorithm divide large problem into smaller sub-problems terms clusters with overlapping. We then exploit hybrid formulation that applies...

10.48550/arxiv.1702.08601 preprint EN other-oa arXiv (Cornell University) 2017-01-01

Image Inpainting has recently become an important research problem due to the rise of generative image synthesis models. While many solutions have been proposed for this problem, it is challenging establish a testbed different possible types inpainting masks e.g., completion mask, expand thick brushes etc. Most shine on object removal or texture synthesis, while semantic generation still difficult achieve. To address these issues, we introduce first general Challenge. The target develop that...

10.1109/cvprw56347.2022.00124 article EN 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2022-06-01

Recent advancements in 2D diffusion models allow appearance generation on untextured raw meshes. These methods create RGB textures by distilling a model, which often contains unwanted baked-in shading effects and results unrealistic rendering the downstream applications. Generating Physically Based Rendering (PBR) materials instead of just would be promising solution. However, directly PBR material parameters from still suffers incorrect decomposition, such as albedo. We introduce DreamMat ,...

10.1145/3658170 article EN ACM Transactions on Graphics 2024-07-19

Abstract In the field of optical communications and quantum informatics, polarization orbital angular momentum (OAM) offer a promising way to expand dimension information. However, detecting state topological charge OAM beam on‐chip can be challenging. To address this, an ultracompact metasurface is proposed demonstrated. The composed six polarization‐sensitive metalenses that occupy 60°annular sectors each are capable simultaneous detection. focuses coaxial polarized vortex into locations,...

10.1002/lpor.202301012 article EN Laser & Photonics Review 2023-12-22
Coming Soon ...