paper-with-me

홈 › Papers

MAGVIT: Masked Generative Video Transformer

2022-12-10 · CVPR 2023 1 · Lijun Yu, Yong Cheng, Kihyuk Sohn, José Lezama, Han Zhang, Huiwen Chang, Alexander G. Hauptmann, Ming-Hsuan Yang, Yuan Hao, Irfan Essa, Lu Jiang

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.

📄 PDF Abstract BibTeX arXiv:2212.05199

Code (1)

google-research/magvit 공식 구현 jax

Tasks

Multi-Task LearningText-to-Video GenerationVideo GenerationVideo Prediction

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

RefTok: Reference-Based Tokenization for Video Generation

2025-07-03 · Xiang Fan, Xiaohang Sun, Kushan Thakkar, Zhu Liu 외 arxiv

Effectively handling temporal redundancy remains a key challenge in learning video models. Prevailing approaches often treat each set of frames independently, failing to effectively capture the temporal dependencies and …

Video Generation

Extending Video Masked Autoencoders to 128 frames

2024-11-20 · Neural Information Processing Systems 2024 9 · Nitesh Bharadwaj Gundavarapu, Luke Friedman, Raghav Goyal, Chaitra Hegde 외

Video understanding has witnessed significant progress with recent video foundation models demonstrating strong performance owing to self-supervised pre-training objectives; Masked Autoencoders (MAE) being the design of …

DecoderVideo Understanding

MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

2023-12-19 · CVPR 2024 1 · Haoyu Ma, Shahin Mahdizadehaghdam, Bichen Wu, Zhipeng Fan 외

Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish t…

Video Editing

Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation

2023-10-09 · Lijun Yu, José Lezama, Nitesh B. Gundavarapu, Luca Versari 외

While Large Language Models (LLMs) are the dominant models for generative tasks in language, they do not perform as well as diffusion models on image and video generation. To effectively use LLMs for visual generation, o…

Action RecognitionImage GenerationLanguage ModelingLanguage Modelling+3

Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation

2024-09-06 · Zhuoyan Luo, Fengyuan Shi, Yixiao Ge, Yujiu Yang 외

We present Open-MAGVIT2, a family of auto-regressive image generation models ranging from 300M to 1.5B. The Open-MAGVIT2 project produces an open-source replication of Google's MAGVIT-v2 tokenizer, a tokenizer with a sup…

Image GenerationImage Reconstruction