아이공의 AI 공부 도전기

최신 글

[논문 Summary] DreaMoving (2023.12 Arxiv) "DreaMoving: A Human Video Generation Framework based on Diffusion Models"

[논문 Summary] DreaMoving (2023.12 Arxiv) "DreaMoving: A Human Video Generation Framework based on Diffusion Models" 목차 논문 정보 Citation : 2024.03.12 화요일 기준 1회 저자 Mengyang Feng, Jinlin Liu, Kai Yu, Yuan Yao, Zheng Hui, Xiefan Guo, Xianhui Lin, Haolan Xue, Chen Shi, Xiaowen Li, Aojie Li, Xiaoyang Kang, Biwen Lei, Miaomiao Cui, Peiran Ren, Xuansong Xie - Alibaba Group 논문 & Github 링크 Official Arxiv htt..
Generative Model
2024.03.12

[논문 Summary] Animate Anyone (2023.11 Arxiv) "Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation"

[논문 Summary] Animate Anyone (2023.11 Arxiv) "Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation" 목차 논문 정보 Citation : 2024.03.11 월요일 기준 10회 저자 Li Hu, Xin Gao, Peng Zhang, Ke Sun, Bang Zhang, Liefeng Bo - Institute for Intelligent Computing, Alibaba Group 논문 & Github 링크 Official Not Yet Arxiv https://arxiv.org/abs/2311.17117 Animate Anyone: Consistent and ..
Generative Model
2024.03.11

[논문 Summary] SDXL-Turbo (ADD) (2023.11 Arxiv) "Adversarial Diffusion Distillation"

[논문 Summary] SDXL-Turbo (ADD) (2023.11 Arxiv) "Adversarial Diffusion Distillation" 목차 논문 정보 Citation : 2024.02.03 토요일 기준 3회 저자 Axel Sauer, Dominik Lorenz, Andreas Blattmann, Robin Rombach - Stability AI 논문 & Github 링크 Official https://stability.ai/news/stability-ai-sdxl-turbo Introducing SDXL Turbo: A Real-Time Text-to-Image Generation Model — Stability AI SDXL Turbo is a new text-to-image mode ..
Generative Model
2024.02.03

[논문 Summary] Nerfies (2021 ICCV) "Nerfies: Deformable Neural Radiance Fields"

[논문 Summary] Nerfies (2021 ICCV) "Nerfies: Deformable Neural Radiance Fields" 목차 논문 정보 Citation : 2024.01.27 토요일 기준 871회 저자 Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B Goldman, Steven M. Seitz, Ricardo Martin-Brualla - University of Washington, Google Research 논문 링크 Official https://openaccess.thecvf.com/content/ICCV2021/papers/Park_Nerfies_Deformable_Neural_Radiance_..
3D
2024.01.27

[논문 Summary] NeRF-W (2021 CVPR) "NeRF in the Wild : Neural Radiance Fields for Unconstrained Photo Collections"

[논문 Summary] NeRF-W (2021 CVPR) "NeRF in the Wild : Neural Radiance Fields for Unconstrained Photo Collections" 목차 논문 정보 Citation : 2024.01.14 일요일 기준 922회 저자 Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, Daniel Duckworth Google Research 논문 링크 Official https://openaccess.thecvf.com/content/CVPR2021/papers/Martin-Brualla_NeRF_in_the_Wild_Neural_R..
3D
2024.01.21

[논문 Summary] Score based generative model with SDE (2021 ICLR) "Score-Based Generative Modeling through Stochastic Differential Equations"

[논문 Summary] Score based generative model with SDE (2021 ICLR) "Score-Based Generative Modeling through Stochastic Differential Equations" 목차 논문 정보 Citation : 2023.12.03 토요일 기준 2072회 저자 Yang Song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole 논문 링크 Official https://openreview.net/forum?id=CzceR82CYc Score-Based Generative Modeling with Critically-Damped Lang..
카테고리 없음
2024.01.16

[논문 Summary] D-NeRF (2021 CVPR) "D-NeRF: Neural Radiance Fields for Dynamic Scenes"

[논문 Summary] D-NeRF (2021 CVPR) "D-NeRF: Neural Radiance Fields for Dynamic Scenes" 목차 논문 정보 Citation : 2024.01.07 일요일 기준 770회 저자 Albert Pumarola, Enric Corona, Gerard Pons-Moll, Francesc Moreno-Noguer 논문 링크 Official https://openaccess.thecvf.com/content/CVPR2021/papers/Pumarola_D-NeRF_Neural_Radiance_Fields_for_Dynamic_Scenes_CVPR_2021_paper.pdf Arxiv https://arxiv.org/abs/2011.13961 공식 Github ..
3D
2024.01.07

[논문 Summary] Tune-A-Video (2023 ICCV) "Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation"

[논문 Summary] Tune-A-Video (2023 ICCV) "Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation" 목차 논문 정보 Citation : 2024.01.14 일요일 기준 192회 저자 Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Weixian Lei, Yuchao Gu, Yufei Shi, Wynne Hsu, Ying Shan, Xiaohu Qie, Mike Zheng Shou 1) Show Lab, National University of Singapore 2) ARC Lab 3) Tencent PCG 4) School of Computing, Natio..
Generative Model
2023.11.10

[논문 Summary] AnimateDiff (2023.07 Arxiv) "AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Modelswithout Specific Tuning"

[논문 Summary] AnimateDiff (2023.07 Arxiv) "AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning" 목차 논문 정보 Citation : 2023.10.28 토요일 기준 4회 저자 Yuwei Guo, Ceyuan Yang, Anyi Rao, Yaohui Wang, Yu Qiao, Dahua Lin, Bo Dai Shanghai AI Laboratory, The Chinese University of Hong Kong, Stanford University 논문 링크 Official https://arxiv.org/abs/2307.04725 Arxiv 공식 Githu..
Generative Model
2023.10.28

[Pytorch] 새로운 축 만들기 방법 (torch.unsqueeze, input[:, None])

torch tensor에서 새로운 축을 만들고자 할 때 사용할 수 있는 방법 1. torch.unsqueeze (input, dim) ex) torch.unsqueeze(input, dim=0) https://pytorch.org/docs/stable/generated/torch.unsqueeze.html torch.unsqueeze — PyTorch 2.1 documentation Shortcuts pytorch.org 2. input[:, None] numpy 에서도 비슷하게 사용가능 input[None, :] input[:, None] input[:, None, None] https://stackoverflow.com/questions/37867354/in-numpy-what-does-selecti..
Pytorch
2023.10.21

[논문 Summary] MAE(Masked AutoEncoder) (2022 CVPR) "Masked Autoencoders Are Scalable Vision Learners"

[논문 Summary] MAE(Masked AutoEncoder) (2022 CVPR) "Masked Autoencoders Are Scalable Vision Learners" 목차 논문 정보 Citation : 2023.10.02 월요일 기준 2950회 저자 Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollár, Ross Girshick Meta (FAIR) 논문 링크 Official https://openaccess.thecvf.com/content/CVPR2022/papers/He_Masked_Autoencoders_Are_Scalable_Vision_Learners_CVPR_2022_paper.pdf Arxiv https://arxiv...
Self-Supervised Learning
2023.10.08

[해결] ImportError: cannot import name 'Literal' from 'typing'

ImportError: cannot import name 'Literal' from 'typing' 문제가 생기면 Python Version 확인 먼저 해야함. typing에서 Literal은 3.8 이상에서 사용가능한 package이므로 Python version 3.7 이하의 경우 실행 불가 에러가 뜸 고로, terminal에 'python --version'을 통해 확인 혹은 import sys sys.version 으로 Python 버전을 확인 먼저 진행 만약 Python version이 3.7이하라면 1) kernel 재설치 만약 terminal env로 재설치가 가능하다면 python = 3.8 이상 환경 구축 후 활용 2) typing_extensions package 활용 pip insta..
Python Bug Solution
2023.10.06

[논문 Summary] PerSAM (2023.05 arxiv) "Personalize Segment Anything Model with One Shot"

[논문 Summary] PerSAM (2023.05 arxiv) "Personalize Segment Anything Model with One Shot" 목차 논문 정보 Citation : 2023.06.30 금요일 기준 4회 저자 Renrui Zhang, Zhengkai Jiang, Ziyu Guo, Shilin Yan, Junting Pan, Hao Dong, Peng Gao, Hongsheng Li 논문 링크 Official Arxiv https://arxiv.org/abs/2305.03048 Personalize Segment Anything Model with One Shot Driven by large-data pre-training, Segment Anything Model (SAM) ha..
Generative Model
2023.08.31

[논문 Summary] Animated Drawings (2023 SIGGRAPH) "A Method for Animating Children's Drawings of the human Figure"

[논문 Summary] Animated Drawings (2023 SIGGRAPH) "A Method for Animating Children's Drawings of the human Figure" 목차 논문 정보 Citation : 저자 Harrison Jesse Smith, Qingyuan Zheng, Yifei Li, Somya Jain, Jessica K. Hodgins Meta, Tencent, MIT CSAIL, Carnegie Mellon University 논문 링크 Official https://dl.acm.org/doi/10.1145/3592788 Arxiv https://arxiv.org/abs/2303.12741 A Method for Animating Children's Draw..
Deep Learning
2023.08.30

[논문 Summary] DreamPose (2023.04 arxiv) "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

[논문 Summary] DreamPose (2023.04 arxiv) "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion" 목차 논문 정보 Citation : 2023.08.30 수요일 기준 4회 저자 Johanna Karras, Aleksander Holynski, Ting-Chun Wang, Ira Kemelmacher-Shlizerman 논문 링크 Official https://grail.cs.washington.edu/projects/dreampose/ DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion Given an image of a person and a seq..
Generative Model
2023.08.30
loading

티스토리툴바