Abstract:Recent 3D feed-forward models, such as the Visual Geometry Grounded Transformer (VGGT), have shown strong capability in inferring 3D attributes of static scenes. However, since they are typically trained on static datasets, these models often struggle in real-world scenarios involving complex dynamic elements, such as moving humans or deformable objects like umbrellas. To address this limitation, we introduce PAGE-4D, a feedforward model that extends VGGT to dynamic scenes, enabling camera pose estimation, depth prediction and point cloud reconstruction - all without post-processing. A central challenge in multitask 4D reconstruction is the inherent conflict between tasks: accurate camera pose estimation requires suppressing dynamic regions, while geometry reconstruction requires modeling them. To resolve this tension, we propose a dynamics aware aggregator that disentangles static and dynamic information by predicting a dynamics-aware mask - suppressing motion cues for pose estimation while amplifying them for geometry reconstruction. Extensive experiments show that PAGE-4D consistently outperforms the original VGGT in dynamic scenarios, achieving superior results in camera pose estimation, monocular and video depth estimation, and dense point map reconstruction. Necessary code and additional demos are available at Link: this https URL. Keywords: VGGT-4D, 4D Perception, Dynamic Scene Reconstruction.
| Comments: | ICLR 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2510.17568 [cs.CV] |
| (or arXiv:2510.17568v5 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2510.17568 arXiv-issued DOI via DataCite |
From: Kaichen Zhou [view email]
[v1]
Mon, 20 Oct 2025 14:17:16 UTC (8,495 KB)
[v2]
Tue, 21 Oct 2025 18:59:28 UTC (8,495 KB)
[v3]
Mon, 8 Dec 2025 22:50:06 UTC (8,220 KB)
[v4]
Sat, 21 Mar 2026 16:00:40 UTC (8,119 KB)
[v5]
Wed, 15 Apr 2026 23:21:48 UTC (8,120 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。