肖俊，現任中國科學院大學人工智慧學院黨委書記，中國科學院大學教授。
基本介紹
- 中文名：肖俊
- 國籍：中國
- 任職單位：中國科學院大學
- 職稱：教授
人物履歷,研究領域,科研成果,主要科研項目,代表性論文,所獲榮譽,
人物履歷
2008年4月至2010年3月，中國科學院研究生院師資博士後。
2010年3月至2010年5月，中國科學院研究生院講師。
2010年5月至2016年11月，中國科學院大學副教授。
2016年11月至今，中國科學院大學教授。
研究領域
計算機視覺，AI+。
科研成果
主要科研項目
（1）面向室內場景的全向視覺重建與可視渲染關鍵技術研究
（2）基於多目圖像的室內場景重建與編輯關鍵技術研究
（3）元宇宙中三維場景感知與理解關鍵技術
（4）道路交通場景的環境目標三維狀態感知與驗證
（5）基於多模態數據的銀屑病和特應性皮炎智慧型辨別方法研究
（6）基於序列化高清圖像的大規模場景實時三維重建與智慧型解析方法
（7）深度學習驅動的弱監督三維場景理解及實例重建
（8）面向BIM的參數化模型重建與分析
（9）三維數位化機房重建算法研究
（10）山地致災風險評估平台的軟體研發
（11）面向月球場景的高精度三維重建與語義分割技術研究
（12） 三維非連續性工程計算軟體研發及示範套用
（13） 面向大規模岩體點雲的自適應濾波方法研究
（14） 任意臨空麵條件下的關鍵塊體識別理論研究
（15） 面向工程計算的岩體三維重建理論與方法研究
（16） 面向岩體結構面提取的大規模點雲分析方法研究
代表性論文
(1) Efficient Single Correspondence Voting for Point Cloud Registration [J]. IEEE Transactions on Image Processing, 2024
(2) Multi-view Human Pose and Shape Estimation via Mesh-aligned Voxel Interpolation [J], Information Fusion, 2024
(3) FC-4DFS: Frequency-controlled Flexible 4D Facial Expression Synthesizing [C]. ACM MM 2024
(4) World to Code: Multi-modal Data Generation via Self-Instructed Compositional Captioning and Filtering. EMNLP 2024
(5)T2DyVec: Leveraging Sparse Images and Controllable Text for Dynamic SVG. SIGGRAPH Poster 2024
(6) SPDET: Edge-Aware Self-Supervised Panoramic Depth Estimation Transformer With Spherical Geometry [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023
(7) PartCom: Part Composition Learning for 3D Open-Set Recognition [J]. International Journal of Computer Vision, 2023
(8)NR-MVSNet: Learning Multi-view Stereo based on Normal Consistency and Depth Refinement [J]. IEEE Transactions on Image Processing, 2023
(9) Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery [C]. NeurIPS, 2023
(10) VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation[C], CVPR 2023 (HIGHLIGHT paper)
(11) SSF: Accelerating Training of Spiking Neural Networks with Stabilized Spiking Flow [C]. ICCV 2023
(12) Progressive Graph Matching Network for Correspondences[C]. Pacific Graphics, 2023
(13) Landmark Guided 4D Facial Expression Generation[C]. SIGGRAPH Asia Poster, 2023
(14) DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis[C], ACM Multimedia, 2022
(15) ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation[C], AAAI, 2022
(16) Context-Aware 3D Point Cloud Semantic Segmentation With Plane Guidance[J], IEEE Transactions on Multimedia, 2022
(17) MEMformer: Transformer-based 3D Human Motion Estimation from MoCap Markers[C], SIGGRAPH Asia, 2022
(18) Registration Method for Point Clouds of Complex Rock-mass Based on Dual Structure Information[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022
(19) Joint Specular Highlight Detection and Removal in Single Images via Unet-Transformer[J], Computational Visual Media, 2022
(20) Single-Image Specular Highlight Removal via Real-World Dataset Construction[J]. IEEE Transactions on Multimedia, 2021
(21) A Novel Rock-Mass Point Cloud Registration Method Based on Feature Line Extraction and Feature Point Matching [J]. IEEE Transactions on Geoscience and Remote Sensing, 2021
(22) Efficient Pairwise 3D Registration of Urban Scenes Via Hybrid Structural Descriptors [J]. IEEE Transactions on Geoscience and Remote Sensing, 2021
(23) Data-driven Floor Plan Understanding in Rural Residential Buildings via Deep Recognition [J], Information Sciences, 2021
(24) Unsupervised Learning of Disentangled 3D Representation from a Single Image [C], Eurographics, 2021
(25) End-to-end 3D Point Cloud Instance Segmentation without Detection[C]. CVPR 2020
(26) Blending Surface Segmentation and Editing for 3D Models [J], IEEE Transactions on Visualization and Computer Graphics, 2020
(27) Deep Specular Highlight Removal for Single Real-world Image [C], SIGGRAPH Asia Poster, 2020
(28) Extracting Cycle-Aware Feature Curve Networks from 3D Models [J], Computer-Aided Design, 2020
(29) Accurate Rock-mass Extraction from Terrestrial Laser Point Clouds via Multi-scale and Multi-view Convolutional Feature Representation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020
(30) Efficient Rock-Mass Point Cloud Registration Using n-Point Complete Graphs [J]. IEEE Transactions on Geoscience and Remote Sensing, 2020
(31) CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentation [C]，AAAI, 2020
所獲榮譽
2023年，榮獲“北京高校優秀黨務工作者”稱號。
