本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This document summarizes recent research on applying self-attention mechanisms from Transformers to domains other than language, such as computer vision. It discusses models that use self-attention for images, including ViT, DeiT, and T2T, which apply Transformers to divided image patches. It also covers more general attention modules like the Perceiver that aims to be domain-agnostic. Finally, it discusses work on transferring pretrained language Transformers to other modalities through frozen weights, showing they can function as universal computation engines.
【DL輪読会】NeRF-VAE: A Geometry Aware 3D Scene Generative ModelDeep Learning JP
?
NeRF-VAE is a 3D scene generative model that combines Neural Radiance Fields (NeRF) and Generative Query Networks (GQN) with a variational autoencoder (VAE). It uses a NeRF decoder to generate novel views conditioned on a latent code. An encoder extracts latent codes from input views. During training, it maximizes the evidence lower bound to learn the latent space of scenes and allow for novel view synthesis. NeRF-VAE aims to generate photorealistic novel views of scenes by leveraging NeRF's view synthesis abilities within a generative model framework.
[DL輪読会]Neural Radiance Flow for 4D View Synthesis and Video Processing (NeRF...Deep Learning JP
?
Neural Radiance Flow (NeRFlow) is a method that extends Neural Radiance Fields (NeRF) to model dynamic scenes from video data. NeRFlow simultaneously learns two fields - a radiance field to reconstruct images like NeRF, and a flow field to model how points in space move over time using optical flow. This allows it to generate novel views from a new time point. The model is trained end-to-end by minimizing losses for color reconstruction from volume rendering and optical flow reconstruction. However, the method requires training separate models for each scene and does not generalize to unknown scenes.
【DL輪読会】NeRF-VAE: A Geometry Aware 3D Scene Generative ModelDeep Learning JP
?
NeRF-VAE is a 3D scene generative model that combines Neural Radiance Fields (NeRF) and Generative Query Networks (GQN) with a variational autoencoder (VAE). It uses a NeRF decoder to generate novel views conditioned on a latent code. An encoder extracts latent codes from input views. During training, it maximizes the evidence lower bound to learn the latent space of scenes and allow for novel view synthesis. NeRF-VAE aims to generate photorealistic novel views of scenes by leveraging NeRF's view synthesis abilities within a generative model framework.
[DL輪読会]Neural Radiance Flow for 4D View Synthesis and Video Processing (NeRF...Deep Learning JP
?
Neural Radiance Flow (NeRFlow) is a method that extends Neural Radiance Fields (NeRF) to model dynamic scenes from video data. NeRFlow simultaneously learns two fields - a radiance field to reconstruct images like NeRF, and a flow field to model how points in space move over time using optical flow. This allows it to generate novel views from a new time point. The model is trained end-to-end by minimizing losses for color reconstruction from volume rendering and optical flow reconstruction. However, the method requires training separate models for each scene and does not generalize to unknown scenes.