FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (11) · 9305-9313
DOI: 10.1609/aaai.v40i11.37889 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Guan Yuan Tan und 6 weiteren Autor:innen.
Abstract (Originalsprache)
We introduce FLAG-4D, a novel framework for generating novel views of dynamic scenes by reconstructing how 3D Gaussian primitives evolve through space and time. Existing methods typically rely on a single Multilayer Perceptron(MLP) to model temporal deformations, and they often struggle to capture complex point motions and fine-grained dynamic details consistently over time, especially from sparse input views. Our approach, FLAG-4D overcomes this by employing a dual-deformation network that dynamically warps a canonical set of 3D Gaussians over time into new positions and anisotropic shapes. This dual-deformation network consists of an Instantaneous Deformation Network (IDN) for modeling fine-grained, local deformations, and Global Motion Network (GMN) for capturing long-range dynamics, refined via mutual learning. To ensure these deformations are both accurate and temporally smooth, FLAG-4D incorporates dense motion features from a pretrained optical flow backbone. We fuse these motion cues from adjacent timeframes and use a deformation-guided attention mechanism to align this flow information with the current state of each evolving 3D Gaussian. Extensive experiments demonstrate that FLAG-4D achieves higher-fidelity and more temporally coherent reconstructions with finer detail preservation than state-of-the-art methods.
Zitieren
APA
Tan, G. Y., Vu, N. T., Pal, A., Rajanala, S., Phan, R. C. W., Srinivas, M., & Ting, C. (2026). FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence, 40(11), 9305-9313. https://doi.org/10.1609/aaai.v40i11.37889
Vancouver
Tan GY, Vu NT, Pal A, Rajanala S, Phan RCW, Srinivas M, et al. FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(11):9305-9313. doi:10.1609/aaai.v40i11.37889
BibTeX
@article{Tan2026,
author = {Tan, Guan Yuan and Vu, Ngoc Tuan and Pal, Arghya and Rajanala, Sailaja and Phan, Raphael C W and Srinivas, Mettu and Ting, Chee-Ming},
title = {FLAG-4D: Flow-Guided Local-Global Dual-Deformation Model for 4D Reconstruction},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {11},
pages = {9305--9313},
doi = {10.1609/aaai.v40i11.37889}
}
EUVIMED