What's on the Other Side? A Single-View 3D Scene Reconstruction

Staszak, Rafał; Kulecki, Bartłomiej; Sempruch, Witold; Belter, Dominik

doi:10.1109/icarcv57592.2022.10004340

Cited by 4 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since the data obtained from a single perspective does not contain information about the complete threedimensional shape of the object, we perform a scanning procedure to collect and assemble multiple views of the scene. Another solution used in the system is a 3D reconstruction [25], which completes the object point cloud based on the predicted view from its opposite side.…”

Section: Scene Segmentationmentioning

confidence: 99%

Multimodal Robot Programming Interface Based On RGB-D Perception and Neural Scene Understanding Modules

Kulecki

2024

JAMRIS

View full text Add to dashboard Cite

In this paper, we propose a system for natural and intuitive interaction with the robot. Its purpose is to allow a person with no specialized knowledge and no training in robot programming to program a robotic arm.We utilize data from the RGB-D camera to segment the scene and detect objects. We also estimate the configuration of the operator's hand and the position of the visual marker to determine the intentions of the operator and the actions of the robot. To this end, we utilize trained neural networks and operations on the input point clouds. Also, voice commands are used to define or trigger the execution of the motion. Finally, we performed a set of experiments to show the properties of the proposed system.

show abstract

Section: Scene Segmentationmentioning

confidence: 99%

Multimodal Robot Programming Interface Based On RGB-D Perception and Neural Scene Understanding Modules

Kulecki

2024

JAMRIS

View full text Add to dashboard Cite

show abstract

“…The motivation for creating the dataset lies in improving the perceptual capabilities of robots, specifically in the context of single-view object reconstruction, with the aim of enhancing their ability to interact with and manipulate objects in various environments. By creating a dataset specifically tailored to the challenges posed by single-view object reconstruction, the goal is to enable robots equipped with RGB-D cameras to overcome the limitations associated with incomplete shape information [ 1 ] ( Fig. 1 ).…”

Section: Introductionmentioning

confidence: 99%