Image de couverture de livre

From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wallingford, Matthew, Bhattad, Anand, Kusupati, Aditya, Ramanujan, Vivek, Deitke, Matt, Kakade, Sham, Kembhavi, Aniruddha, Mottaghi, Roozbeh, Ma, Wei-Chiu, Farhadi, Ali
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Matryoshka Representation Learning
par: Kusupati, Aditya, et autres
Publié: (2022)

Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videos
par: Luo, Rundong, et autres
Publié: (2025)

Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
par: Shen, Ethan, et autres
Publié: (2024)

ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos
par: Soraki, Rustin, et autres
Publié: (2026)

Posterior Augmented Flow Matching
par: Stoica, George, et autres
Publié: (2026)

MatFormer: Nested Transformer for Elastic Inference
par: Devvrit, et autres
Publié: (2023)

Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
par: Gao, Ziqi, et autres
Publié: (2024)

Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation
par: Bharadhwaj, Homanga, et autres
Publié: (2024)

When Worse is Better: Navigating the compression-generation tradeoff in visual tokenization
par: Ramanujan, Vivek, et autres
Publié: (2024)

Polaris: A Gödel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair
par: Kakade, Aditya, et autres
Publié: (2026)

Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion
par: Fan, Xiang, et autres
Publié: (2024)

Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
par: Yang, Yue, et autres
Publié: (2025)

CodeNav: Beyond tool-use to using real-world codebases with LLM agents
par: Gupta, Tanmay, et autres
Publié: (2024)

The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
par: Geng, Scott, et autres
Publié: (2024)

MIMIC: Masked Image Modeling with Image Correspondences
par: Marathe, Kalyani, et autres
Publié: (2023)

ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition
par: Salehi, Mohammadreza, et autres
Publié: (2024)

Imagine360: Immersive 360 Video Generation from Perspective Anchor
par: Tan, Jing, et autres
Publié: (2024)

Contrastive Flow Matching
par: Stoica, George, et autres
Publié: (2025)

Loss-to-Loss Prediction: Scaling Laws for All Datasets
par: Brandfonbrener, David, et autres
Publié: (2024)

Characterization and Mitigation of Training Instabilities in Microscaling Formats
par: Su, Huangyuan, et autres
Publié: (2025)

Seeing Fast and Slow: Learning the Flow of Time in Videos
par: Wu, Yen-Siang, et autres
Publié: (2026)

Task Me Anything
par: Zhang, Jieyu, et autres
Publié: (2024)

LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting
par: Xing, Xiaoyan, et autres
Publié: (2024)

Iterated Learning Improves Compositionality in Large Vision-Language Models
par: Zheng, Chenhao, et autres
Publié: (2024)

Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation
par: Duggal, Shivam, et autres
Publié: (2025)

VideoNet: A Large-Scale Dataset for Domain-Specific Action Recognition
par: Yadav, Tanush, et autres
Publié: (2026)

Grounding Multimodal LLMs to Embodied Agents that Ask for Help with Reinforcement Learning
par: Ramrakhya, Ram, et autres
Publié: (2025)

UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video
par: Lin, Chih-Hao, et autres
Publié: (2023)

Preserving Identity with Variational Score for General-purpose 3D Editing
par: Le, Duong H., et autres
Publié: (2024)

Generative Blocks World: Moving Things Around in Pictures
par: Vavilala, Vaibhav, et autres
Publié: (2025)

FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuning
par: Hu, Jiaheng, et autres
Publié: (2024)

Algebraic generators of the skein algebra of a surface
par: Santharoubane, Ramanujan
Publié: (2018)

LOTION: Smoothing the Optimization Landscape for Quantized Training
par: Kwun, Mujin, et autres
Publié: (2025)

Connections between Schedule-Free Optimizers, AdEMAMix, and Accelerated SGD Variants
par: Morwani, Depen, et autres
Publié: (2025)

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities
par: Zhang, Hanlin, et autres
Publié: (2026)

GQ-VAE: A gated quantized VAE for learning variable length tokens
par: Datta, Theo, et autres
Publié: (2025)

The Potential of Second-Order Optimization for LLMs: A Study with Full Gauss-Newton
par: Abreu, Natalie, et autres
Publié: (2025)

Discovering Hierarchical Latent Capabilities of Language Models via Causal Representation Learning
par: Jin, Jikai, et autres
Publié: (2025)

Neuro-Parametric Spectral Classification of Black Hole and Neutron Star X-ray Binary Systems
par: Garg, Akash, et autres
Publié: (2026)

Objects in Generated Videos Are Slower Than They Appear: Models Suffer Sub-Earth Gravity and Don't Know Galileo's Principle...for now
par: Thozhiyoor, Varun Varma, et autres
Publié: (2025)