# DynamicVGGT: Learning Dynamic Point Maps for 4D Scene Reconstruction in Autonomous Driving

arXiv: https://arxiv.org/abs/2603.08254 · HTML: https://mlsanity.com/paper/2603.08254/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2026.

## Built on by (most cited first, 6 of 6)

- [Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2606.10656/) (2026)
- [DINO-VO: Learning Where to Focus for Enhanced State Estimation](https://mlsanity.com/paper/2604.04055/) (2026)
- [Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers](https://mlsanity.com/paper/2605.23892/) (2026)
- [DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation](https://mlsanity.com/paper/2606.31488/) (2026)
- [USR-Drive: Unified Driving Scene Representation via Joint Denoising of 3D Gaussians and Boxes](https://mlsanity.com/paper/2608.19036/) (2026)
- [VGGTWorld-VLA: Intent-Conditioned 3D World Evolution for Autonomous Driving](https://mlsanity.com/paper/2610.11161/) (2026)

## Abstract (arXiv)

Dynamic scene reconstruction in autonomous driving remains a fundamental challenge due to significant temporal variations, moving objects, and complex scene dynamics. Existing feed-forward 3D models have demonstrated strong performance in static reconstruction but still struggle to capture dynamic motion. To address these limitations, we propose DynamicVGGT, a unified feed-forward framework that extends VGGT from static 3D perception to dynamic 4D reconstruction. Our goal is to model point motion within feed-forward 3D models in a dynamic and temporally coherent manner. To this end, we jointly predict the current and future point maps within a shared reference coordinate system, allowing the model to implicitly learn dynamic point representations through temporal correspondence. To efficiently capture temporal dependencies, we introduce a Motion-aware Temporal Attention (MTA) module that learns motion continuity. Furthermore, we design a Dynamic 3D Gaussian Splatting Head that explicitly models point motion by predicting Gaussian velocities using learnable motion tokens under scene flow supervision. It refines dynamic geometry through continuous 3D Gaussian optimization. Extensive experiments on autonomous driving datasets demonstrate that DynamicVGGT significantly outperforms existing methods in reconstruction accuracy, achieving robust feed-forward 4D dynamic scene reconstruction under complex driving scenarios.