C
Chen Liu
Researcher at Washington University in St. Louis
Publications - 15
Citations - 949
Chen Liu is an academic researcher from Washington University in St. Louis. The author has contributed to research in topics: Floorplan & Segmentation. The author has an hindex of 9, co-authored 15 publications receiving 620 citations. Previous affiliations of Chen Liu include University of Science and Technology of China.
Papers
More filters
Proceedings ArticleDOI
PlaneNet: Piece-Wise Planar Reconstruction from a Single RGB Image
TL;DR: This paper presents the first end-to-end neural architecture for piece-wise planar reconstruction from a single RGB image, and outperforms baseline methods in terms of both plane segmentation and depth estimation accuracy.
Proceedings ArticleDOI
PlaneRCNN: 3D Plane Detection and Reconstruction From a Single Image
TL;DR: In this article, a deep neural architecture, PlaneRCNN, is proposed to detect and reconstruct piecewise planar regions from a single RGB image, which employs a variant of Mask R-CNN to detect planes with their plane parameters and segmentation masks.
Proceedings ArticleDOI
Raster-to-Vector: Revisiting Floorplan Transformation
TL;DR: This paper addresses the problem of converting a rasterized floorplan image into a vector-graphics representation by adopting a learning-based approach and significantly outperforms existing methods and achieves around 90% precision and recall.
Book ChapterDOI
FloorNet: A Unified Framework for Floorplan Reconstruction from 3D Scans
TL;DR: Wang et al. as mentioned in this paper proposed a novel deep neural architecture that automatically reconstructs a floorplan by walking through a house with a smartphone, which is the ultimate goal of indoor mapping research.
Posted Content
PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image
TL;DR: A deep neural architecture that detects and reconstructs piecewise planar regions from a single RGB image using a variant of Mask R-CNN and refines an arbitrary number of segmentation masks with a novel loss enforcing the consistency with a nearby view during training.