3d vsg: Long-term semantic scene change prediction through 3d variable scene graphs

S Looper, J Rodriguez-Puigvert… - … on Robotics and …, 2023 - ieeexplore.ieee.org
Numerous applications require robots to operate in environments shared with other agents,
such as humans or other robots. However, such shared scenes are typically subject to …

DiffAssemble: A Unified Graph-Diffusion Model for 2D and 3D Reassembly

G Scarpellini, S Fiorini, F Giuliari… - Proceedings of the …, 2024 - openaccess.thecvf.com
Reassembly tasks play a fundamental role in many fields and multiple approaches exist to
solve specific reassembly problems. In this context we posit that a general unified model can …

Commonsense Knowledge-Driven Joint Reasoning Approach for Object Retrieval in Virtual Reality

H Jiang, D Weng, X Dongye, L Luo… - ACM Transactions on …, 2023 - dl.acm.org
National Key Laboratory of General Artificial Intelligence, Bei**g Institute for General
Artificial Intelligence (BIGAI), China Retrieving out-of-reach objects is a crucial task in virtual …

ZInD-Tell: Towards Translating Indoor Panoramas into Descriptions

T Deb, L Wang, Z Bessinger… - Proceedings of the …, 2024 - openaccess.thecvf.com
This paper focuses on bridging the gap between natural language descriptions 360-degree
panoramas room shapes and layouts/floorplans of indoor spaces. To enable new multi …

Model-based inexact graph matching on top of DNNs for semantic scene understanding

J Chopin, JB Fasquel, H Mouchère, R Dahyot… - Computer Vision and …, 2023 - Elsevier
Deep learning based pipelines for semantic segmentation often ignore structural information
available on annotated images used for training. We propose a novel post-processing …

Think holistically, act down-to-earth: A semantic navigation strategy with continuous environmental representation and multi-step forward planning

B Chen, J Kang, P Zhong, Y Cui, S Lu… - … on Circuits and …, 2023 - ieeexplore.ieee.org
The Object goal Navigation (ObjectNav) task requires an agent to navigate through a
previously unknown domestic scenario using spatial and semantic contextual information …

RP-SG: Relation Prediction in 3D Scene Graphs for Unobserved Objects Localization

Z Ying, X Yuan, B Yang, Y Song, Q Xu… - IEEE Robotics and …, 2023 - ieeexplore.ieee.org
The ability to search for objects is a fundamental prerequisite for mobile robots when
addressing a wide range of automation tasks. However, how to effectively estimate the …

Unsupervised active visual search with monte carlo planning under uncertain detections

F Taioli, F Giuliari, Y Wang, R Berra… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
We propose a solution for Active Visual Search of objects in an environment, whose 2D floor
map is the only known information. Our solution has three key features that make it more …

[PDF][PDF] Exploring the impact of knowledge graphs on zero-shot visual object state classification

F Gouidis, K Papoutsakis, T Patkos, A Argyros… - Proceedings …, 2024 - scitepress.org
In this work, we explore the potential of Knowledge Graphs (KGs) towards an effective Zero-
Shot Learning (ZSL) approach for Object State Classification (OSC) in images. For this …

A survey on 3d scene graphs: Definition, generation and application

J Bae, D Shin, K Ko, J Lee, UH Kim - International Conference on Robot …, 2022 - Springer
With the advancement of intelligent agents, 3D scene understanding has become one of key
tasks of computer vision. 3D scene understanding is challenging to represent effectively …