查看原文
其他

Talk预告 | 香港中文大学博士生徐英豪:从不规则的单目图片数据构建3D生成模型

让创新获得认可 将门创投
2024-08-23

本期为TechBeat人工智能社区498线上Talk

北京时间5月18(周四)20:00香港中文大学博士生 — 徐英豪的Talk将准时在TechBeat人工智能社区开播!他与大家分享的主题是: “3D Generation from Unstructured Single-view Data ”届时将介绍和探讨3d场景生成模型的标注与生成
Talk·信息
主题:3D Generation from Unstructured Single-view Data 
嘉宾:香港中文大学 博士生 —徐英豪
时间:北京时间 5月18日 (周四) 20:00
地点:TechBeat人工智能社区
http://www.techbeat.net/

 长按识别二维码,一键预约TALK!

Talk·介绍
Pixel-based content creation has made remarkable progress thanks to 2D generative models. However, a deeper understanding of the 3D world beyond image space is necessary for a wide range of real-world applications, such as AR and VR. Traditional 3D content creation authoring pipelines require professional expertise and significant financial investment to build large 3D datasets. In this talk, I will introduce our recent works in enabling 3D generative modeling from unstructured 2D images, especially in single-view data, by introducing powerful and effective 3D representations. It paves the way for generating high-quality 3D assets efficiently. Additionally, we also generalize the 3D generative model to in-the-wild objects and complex scenes, enabling 3D image generation on ImageNet and controllable 3D scene synthesis. These efforts are integral to our long-term vision of enabling high-quality, user-friendly 3D content creation for a broad audience

Talk大纲

1、如何让3d生成模型摆脱对相机标注的依赖
2、在大规模复杂数据集例如imagenet上构建高质量的3d生成模型
3、不规则场景数据集构建可控的3d场景生成模型


Talk·预习资料


paper链接:
https://nvlabs.github.io/eg3d/media/eg3d.pdf

paper链接:

https://arxiv.org/abs/2301.07702

paper链接:
https://arxiv.org/abs/2303.01416

paper链接:

https://arxiv.org/abs/2212.11984


Talk·提问交流

在Talk界面下的【交流区】参与互动!留下你的打call🤟和问题🙋,和更多小伙伴们共同讨论,被讲者直接翻牌解答!


你的每一次贡献,我们都会给予你相应的i豆积分,还会有惊喜奖励哦!


Talk·嘉宾介绍

徐英豪

香港中文大学 博士生

Yinghao Xu is a final-year Ph.D. student at Multimedia Lab (MMLab), Department of Information Engineering in The Chinese University of Hong Kong. His supervisor are Prof. Dahua Lin and Prof. Bolei Zhou. He is very interested in generative models and neural rendering, particularly in 3D generative models. During his Ph.D., he is fortunate to visit Stanford computational group, working with Prof. Gordon Wetzstein. Many of his papers have been awarded as oral representation and best paper candidate at CVPR, ECCV, NeurIPS and ICLR.

Github:

https://justimyhxu.github.io/


 长按识别二维码,一键预约TALK!


-The End-


如果你也想成为讲者

 自荐 / 推荐 
单人Talk | 团队专场 | 录播or直播 | 闭门交流多种方式任你选择!推荐讲者成功也有奖励哦~


关于TechBeat人工智能社区

TechBeat(www.techbeat.net)隶属于将门创投,是一个荟聚全球华人AI精英的成长社区。我们希望为AI人才打造更专业的服务和体验,加速并陪伴其学习成长。期待这里可以成为你学习AI前沿知识的高地,分享自己最新工作的沃土,在AI进阶之路上的升级打怪的根据地!

更多详细介绍>>TechBeat,一个荟聚全球华人AI精英的学习成长社区


点击“阅读原文”,⤵一键送你进入Talk页面
继续滑动看下一个
将门创投
向上滑动看下一个

您可能也对以下帖子感兴趣

文章有问题?点此查看未经处理的缓存