cs.CVNov 17, 2026

π4π^4: A Foundation Model for 4D Scene Geometry and Motion

Authors: Yifan Wang, Weiguang Zhao, Ni Yang, Haoyu Guo, Junting Dong, Weinan Zhang, Chunhua Shen

Organizations: Shanghai Artificial Intelligence Laboratory · Shanghai Jiao Tong University · Zhejiang University

Abstract

π4π^4 is a unified foundation model for 4D scene perception. From diverse, uncalibrated RGB observations in the wild---a single image, an unordered collection, or a video sequence---it recovers dense geometry, camera poses, and metric scale, together with 2D/3D point tracks and moving-object masks for multi-image inputs. It couples a geometry branch with a geometry-conditioned motion branch, which predicts image-space correspondences that are lifted into 3D using reconstructed target-view geometry. Across diverse benchmarks, π4π^4 achieves the best overall average rank in geometry evaluation, alongside competitive performance in single- and multiview 2D/3D point tracking and moving-object segmentation. With a shared backbone, the full geometry-and-motion system contains approximately 0.5B parameters---less than half the size of most baselines. It produces joint reconstructions and tracks in one forward pass, including large-scale scenes with thousands of input images despite training with contexts of at most 64 views. We further present the data and training recipe underlying these capabilities, together with empirical studies of key design choices. Code and models are available at https://github.com/yyfz/Pi4.

Figures & tables

Explore similar work

CardsList
  1. Gen4P: Video Generators are 4D Perceivers

    Oct 15, 2026Yitong Xia, Zeren Jiang, Chuanxia ZhengVideo Depth Estimation4D Scene Understanding

  2. Point4D: Long-range 4D Motion Reconstruction

    Sep 8, 2026Minsik Jeon, Jay Karhade, Deva Ramanan +1Point Tracking3D Point Tracking

  3. Dense4D: Pixel-Level 4D Human Correspondence

    Oct 15, 2026Rıza Alp Güler3D Point TrackingNon-Rigid Shape Correspondence