Realistic 3D indoor scene datasets have enabled significant recent progress in computer vision, scene understanding, autonomous navigation, and 3D reconstruction. But the scale, diversity, and customizability of existing datasets is limited, and it is time‐consuming and expensive to scan and annotate more. Fortunately, combinatorics is on our side: there are enough individual
Kit-Net: Self-Supervised Learning to Kit Novel 3D Objects into Novel 3D Cavities
- Award ID(s):
- 1734633
- NSF-PAR ID:
- 10314372
- Date Published:
- Journal Name:
- Conference on Automation Science and Engineering (CASE) 2021
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
Abstract rooms in existing 3D scene datasets, if there was but a way to recombine them into new layouts. In this paper, we propose the task of generating novel 3D floor plans from existing 3D rooms. We identify three sub‐tasks of this problem: generation of 2D layout, retrieval of compatible 3D rooms, and deformation of 3D rooms to fit the layout. We then discuss different strategies for solving the problem, and design two representative pipelines: one uses available 2D floor plans to guide selection and deformation of 3D rooms; the other learns to retrieve a set of compatible 3D rooms and combine them into novel layouts. We design a set of metrics that evaluate the generated results with respect to each of the three subtasks and show that different methods trade off performance on these subtasks. Finally, we survey downstream tasks that benefit from generated 3D scenes and discuss strategies in selecting the methods most appropriate for the demands of these tasks. -
Functional magnetic resonance imaging (fMRI) offers a rich source of data for studying the neural basis of cognition. Here, we describe the Brain Imaging Analysis Kit (BrainIAK), an open-source, free Python package that provides computationally optimized solutions to key problems in advanced fMRI analysis. A variety of techniques are presently included in BrainIAK: intersubject correlation (ISC) and intersubject functional connectivity (ISFC), functional alignment via the shared response model (SRM), full correlation matrix analysis (FCMA), a Bayesian version of representational similarity analysis (BRSA), event segmentation using hidden Markov models, topographic factor analysis (TFA), inverted encoding models (IEMs), an fMRI data simulator that uses noise characteristics from real data (fmrisim), and some emerging methods. These techniques have been optimized to leverage the efficiencies of high-performance compute (HPC) clusters, and the same code can be seamlessly transferred from a laptop to a cluster. For each of the aforementioned techniques, we describe the data analysis problem that the technique is meant to solve and how it solves that problem; we also include an example Jupyter notebook for each technique and an annotated bibliography of papers that have used and/or described that technique. In addition to the sections describing various analysis techniques in BrainIAK, we have included sections describing the future applications of BrainIAK to real-time fMRI, tutorials that we have developed and shared online to facilitate learning the techniques in BrainIAK, computational innovations in BrainIAK, and how to contribute to BrainIAK. We hope that this manuscript helps readers to understand how BrainIAK might be useful in their research.more » « less
-
Como a matemática pode melhor contribuir para a justiça social e a sustentabilidade? A justiça distributiva aborda a pobreza e os problemas relacionados de cima para baixo: movendo o valor extraído da propriedade privada para a propriedade estatal. Mas, a história do socialismo burocrático, da poluição na URSS à escassez de alimentos na Venezuela, mostra tantos problemas quanto o capitalismo. A justiça generativa, ao contrário, funciona de baixo para cima: substitui a extração de valor e a alienação pela circulação de valores. Esses ciclos geradores incluem os trabalhos não alienados, como, por exemplo, os espaços de produção e os códigos abertos; valores ecológicos não alienados como a agricultura orgânica e valores expressivos não alienados como a diversidade sexual, as artes liberadas e outras liberdades polissêmicas. Este ensaio revisará 3 aspectos das etnociências (etnomatemática, etnocomputação e disciplinas relacionadas) em relação à justiça generativa. No caso dos sistemas de conhecimento indígena, há um perigo de alienação do valor à medida que os conceitos são traduzidos em modelos e, posteriormente, abstraídos em currículos de sala de aula. No caso dos sistemas de conhecimentos vernaculares, a colonização por interesses comerciais já ocorreu, e o desafio é desenvolver uma alternativa descolonizada. Finalmente, no caso das relações entre a escola e a comunidade, um ciclo generativo completo pode incorporar fluxos de valores econômico, de saúde e ambientais, alavancando essas abordagens generativas CTEM (Ciências, Tecnologias, Engenharia e Matemáticas). Este ensaio fornecerá, ambos, a teoria e alguns resultados iniciais dessa abordagem generativa CTEM para um mundo mais justo e sustentável.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/CASE49439.2021.9551395
