PAGE-4D: VGGT-4D Perception via Disentangled Pose and Geometry Estimation

TL;DR

PAGE-4D extends the VGGT model to dynamic scenes, enabling simultaneous camera pose, depth, and point cloud estimation without post-processing by disentangling static and dynamic information.

Contribution

It introduces a dynamics-aware aggregator that improves 4D perception by disentangling static and dynamic scene components in a feedforward model.

Findings

Outperforms VGGT in dynamic scenarios for pose and depth estimation

Achieves accurate 4D reconstruction without post-processing

Demonstrates robustness in complex real-world scenes

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: https://page4d.github.io/. Keywords: VGGT-4D, 4D Perception, Dynamic Scene Reconstruction.