paper-with-me

Papers

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

2025-06-23 · Ziqiao Ma, Xuweiyi Chen, Shoubin Yu, Sai Bi, Kai Zhang, Chen Ziwen, Sihan Xu, Jianing Yang, Zexiang Xu, Kalyan Sunkavalli, Mohit Bansal, Joyce Chai, Hao Tan

Can we scale 4D pretraining to learn general space-time representations that reconstruct an object from a few views at some times to any view at any time? We provide an affirmative answer with 4D-LRM, the first large-scale 4D reconstruction model that takes input from unconstrained views and timestamps and renders arbitrary novel view-time combinations. Unlike prior 4D approaches, e.g., optimization-based, geometry-based, or generative, that struggle with efficiency, generalization, or faithfulness, 4D-LRM learns a unified space-time representation and directly predicts per-pixel 4D Gaussian primitives from posed image tokens across time, enabling fast, high-quality rendering at, in principle, infinite frame rate. Our results demonstrate that scaling spatiotemporal pretraining enables accurate and efficient 4D reconstruction. We show that 4D-LRM generalizes to novel objects, interpolates across time, and handles diverse camera setups. It reconstructs 24-frame sequences in one forward pass with less than 1.5 seconds on a single A100 GPU.

📄 PDF Abstract BibTeX arXiv:2506.18890

Code (0)

등록된 구현이 없습니다.

Tasks

4D reconstructionGPU

Similar Papers 제목 키워드 기반

LiDAR4D: Dynamic Neural Fields for Novel Space-time View LiDAR Synthesis

2024-04-03 · CVPR 2024 1 · Zehan Zheng, Fan Lu, Weiyi Xue, Guang Chen 외

Although neural radiance fields (NeRFs) have achieved triumphs in image novel view synthesis (NVS), LiDAR NVS remains largely unexplored. Previous LiDAR NVS methods employ a simple shift from image NVS methods while igno…

3D Reconstruction4D reconstructionAutonomous DrivingDynamic Reconstruction+3

Fast Hyperspectral Neutron Tomography

2024-10-29 · Mohammad Samin Nur Chowdhury, Diyu Yang, Shimin Tang, Singanallur V. Venkatakrishnan 외

Hyperspectral neutron computed tomography is a tomographic imaging technique in which thousands of wavelength-specific neutron radiographs are measured for each tomographic view. In conventional hyperspectral reconstruct…

Wonderland: Navigating 3D Scenes from a Single Image

2024-12-16 · CVPR 2025 1 · Hanwen Liang, Junli Cao, Vidit Goel, Guocheng Qian 외

This paper addresses a challenging question: How can we efficiently create high-quality, wide-scope 3D scenes from a single arbitrary image? Existing methods face several constraints, such as requiring multi-view data, t…

3D ReconstructionScene Generation

Semantically Coherent Co-Segmentation and Reconstruction of Dynamic Scenes

2017-07-01 · CVPR 2017 7 · Armin Mustafa, Adrian Hilton

In this paper we propose a framework for spatially and temporally coherent semantic co-segmentation and reconstruction of complex dynamic scenes from multiple static or moving cameras. Semantic co-segmentation exploits t…

3D ReconstructionSegmentation

STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes

2024-12-31 · Jiawei Yang, Jiahui Huang, Yuxiao Chen, Yan Wang 외

We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense ob…

Dynamic ReconstructionScene Flow EstimationScene UnderstandingSelf-Supervised Learning