Vision-based holistic scene understanding towards proactive human–robot collaboration
Recently human–robot collaboration (HRC) has emerged as a promising paradigm for mass
personalization in manufacturing owing to the potential to fully exploit the strength of human …
personalization in manufacturing owing to the potential to fully exploit the strength of human …
Sensors, systems and algorithms of 3D reconstruction for smart agriculture and precision farming: A review
S Yu, X Liu, Q Tan, Z Wang, B Zhang - Computers and Electronics in …, 2024 - Elsevier
Perceiving the shape and structure of the real three-dimensional world through sensors and
cameras is indispensable across various domains. The 3D reconstruction technology is …
cameras is indispensable across various domains. The 3D reconstruction technology is …
Slicenet: deep dense depth estimation from a single indoor panorama using a slice-based representation
We introduce a novel deep neural network to estimate a depth map from a single monocular
indoor panorama. The network directly works on the equirectangular projection, exploiting …
indoor panorama. The network directly works on the equirectangular projection, exploiting …
[HTML][HTML] Automated joint 3D reconstruction and visual inspection for buildings using computer vision and transfer learning
T Wang, VJL Gan - Automation in Construction, 2023 - Elsevier
Regular building inspection and maintenance has been deemed as a necessary preventive
measure to maintain the functionality, integrity and aesthetics of buildings. 2D computer …
measure to maintain the functionality, integrity and aesthetics of buildings. 2D computer …
3D semantic scene completion: A survey
Semantic scene completion (SSC) aims to jointly estimate the complete geometry and
semantics of a scene, assuming partial sparse input. In the last years following the …
semantics of a scene, assuming partial sparse input. In the last years following the …
Automatic floor plan analysis and recognition
Due to recent advances in machine learning, there has been an explosive development of
multiple methodologies that automatically extract information from architectural floor plans …
multiple methodologies that automatically extract information from architectural floor plans …
Zillow indoor dataset: Annotated floor plans with 360deg panoramas and 3d room layouts
Abstract We present Zillow Indoor Dataset (ZInD): A large indoor dataset with 71,474
panoramas from 1,524 real unfurnished homes. ZInD provides annotations of 3D room …
panoramas from 1,524 real unfurnished homes. ZInD provides annotations of 3D room …
AtlantaNet: Inferring the 3D Indoor Layout from a Single Image Beyond the Manhattan World Assumption
We introduce a novel end-to-end approach to predict a 3D room layout from a single
panoramic image. Compared to recent state-of-the-art works, our method is not limited to …
panoramic image. Compared to recent state-of-the-art works, our method is not limited to …
Construction and maintenance of building geometric digital twins: state of the art review
Most of the buildings that exist today were built based on 2D drawings. Building information
models that represent design-stage product information have become prevalent in the …
models that represent design-stage product information have become prevalent in the …
Procedural point cloud modelling in scan-to-BIM and scan-vs-BIM applications: a review
Point cloud processing is an essential task in many applications in the AEC domain, such as
automated progress assessment, quality control and 3D reconstruction. As much of the …
automated progress assessment, quality control and 3D reconstruction. As much of the …