April 2025
Intermediate to advanced
690 pages
19h 37m
Portuguese (Portugal, Brazil)
Content preview from Ciência de dados 3D com Python
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
Capítulo 16. PointNet para classificação de objectos 3D
Este trabalho foi traduzido com recurso a IA. Agradecemos o teu feedback e comentários: translation-feedback@oreilly.com
3D A compreensão de cenas, um aspeto crucial dos sistemas de IA espacial, depende muito da extração semântica eficaz de dados 3D. Os Capítulos 12 a 14 permitiram-nos tirar partido da aprendizagem automática 3D supervisionada e não supervisionada para este objetivo, quando temos conjuntos de dados rotulados limitados. No entanto, quando se beneficia de repositórios de dados em grande escala, a aprendizagem profunda 3D mostra-se promissora, o que destacámos no Capítulo 15 com as CNNs 3D.
No entanto, as CNNs 3D são inadequadas para lidar com as complexidades das nuvens de pontos, que são conjuntos de dados não estruturados sem uma grelha fixa ou representação baseada em pixels. Esta limitação realça a necessidade crítica de abordagens inovadoras para processar e interpretar diretamente dados de nuvens de pontos.
De facto, existem vários métodos para representar e processar dados 3D, tais como voxels, malhas e imagens multivistas (ver Capítulo 4). No entanto, cada uma destas representações tem os seus inconvenientes. Embora adequados para CNNs 3D, os voxels podem ser computacionalmente intensivos e exigir muita memória, especialmente para entradas de alta resolução. As malhas ou B-reps, processadas utilizando GNNs, apresentam desafios na construção de gráficos e custos computacionais. As CNNs multivistas, que ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.