CubeComposer: Spatio-Temporal Autoregressive 4K 360deg Video Generation from Perspective Video
Lingen Li, Guangzhi Wang, Xiaoyu Li, Zhaoyang Zhang, Qi Dou, Jinwei Gu, Tianfan Xue, Ying Shan
2026年份
10被引次数
摘要
Frame 1 Frame 25 Frame 1 Frame 25 Frame 1 Frame 25 Frame 1 Frame 25 Frame 20 Frame 15 Frame 10 Frame 5 Frame 1 Frame 25 Frame 20 Frame 15 Frame 10 Frame 5 Project Argus Generated 360¡ Video (1024×512) Argus + VEnhancer Super-resolved (SR) 360¡ Video (2048×1024) CubeComposer (Ours) Generated 360¡ Video (3840×1920, native 4K w/o SR) Frame 1 Frame 25 Frame 20 Frame 15
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式，引用它的顶会 Paper 也一样。你提问，回答直接引用原文。
它引用的顶会 Paper33
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 被引用 5,568 次
- Elucidating the Design Space of Diffusion-Based Generative ModelsTero Karras, Miika Aittala, Timo Aila, Samuli LaineNeurIPS 2022 · 被引用 3,959 次
相关 Paper
- UltraGen: High-Resolution Video Generation with Hierarchical AttentionTeng Hu, Jiangning Zhang, Zihan Su, Ran YiAAAI 2026 · 被引用 7 次
- Argus: Bandwidth-Efficient Live Multiview Video Streaming via Sparse-View Gaussian ReconstructionYizong Wang, Hongbo Ning, Haohua Wang, Yutao Yuan 等INFOCOM 2026
- Beyond Perspective: Neural 360-Degree Video CompressionAndy Regensky, Marc Windsheimer, Fabian Brand, André KaupICCV 2025 · 被引用 2 次
- Argus: Real-Time HQ Video Decoding with CPU Coordinating on Consumer DevicesQiang Chen, Changlong LiRTSS 2024 · 被引用 1 次
- VR Viewport Pose Model for Quantifying and Exploiting Frame CorrelationsYing Chen, Hojung Kwon, Hazer Inaltekin, Maria GorlatovaINFOCOM 2022 · 被引用 10 次
