A5101566592- Adsorption and biosorption for pollutant removal
- Advanced Cellulose Research Studies
- Lignin and Wood Chemistry
- Advanced Photocatalysis Techniques
- Advanced oxidation water treatment
- Nanomaterials for catalytic reactions
- Flame retardant materials and properties
- Water Quality Monitoring and Analysis
- Extraction and Separation Processes
- Electrospun Nanofibers in Biomedical Applications
- biodegradable polymer synthesis and properties
- Advanced Polymer Synthesis and Characterization
- MXene and MAX Phase Materials
- Surface Modification and Superhydrophobicity
- Environmental Quality and Pollution
- Environmental remediation with nanomaterials
- Nanocomposite Films for Food Packaging
- Arsenic contamination and mitigation
- Analytical chemistry methods development
- Graphene and Nanomaterials Applications
- 3D Shape Modeling and Analysis
- Enzyme-mediated dye degradation
- Coal Combustion and Slurry Processing
- Minerals Flotation and Separation Techniques
- Aerogels and thermal insulation
Fuzhou University
2015-2024
Putian University
2022-2024
Powerchina Huadong Engineering Corporation (China)
2024
UC San Diego Health System
2020-2024
University of California, San Diego
2019-2023
Chongqing University
2023
Xinyang Normal University
2007-2023
Qingdao University of Science and Technology
2009-2023
Chengdu University of Information Technology
2023
Northeast Agricultural University
2022
3D point cloud completion, the task of inferring complete geometric shape from a partial cloud, has been attracting attention in community. For acquiring high-fidelity dense clouds and avoiding uneven distribution, blurred details, or structural loss existing methods' results, we propose novel approach to two stages. Specifically, first stage, predicts but coarse-grained with collection parametric surface elements. Then, second it merges prediction input by sampling algorithm. Our method...
Single image 3D reconstruction is an important but challenging task that requires extensive knowledge of our natural world. Many existing methods solve this problem by optimizing a neural radiance field under the guidance 2D diffusion models suffer from lengthy optimization time, inconsistency results, and poor geometry. In work, we propose novel method takes single any object as input generates full 360-degree textured mesh in feed-forward pass. Given image, first use view-conditioned...