Any4D: Unified Feed-Forward Metric 4D Reconstruction

TL;DR

Any4D introduces a scalable multi-view transformer for dense 4D scene reconstruction, capable of integrating multiple sensor modalities and providing accurate, efficient predictions of motion and geometry from various input types.

Contribution

It presents a novel modular 4D scene representation and a transformer-based approach that outperforms prior methods in accuracy and speed, supporting diverse sensor data.

Findings

2-3X lower error compared to previous methods

15X faster computation than prior approaches

Effective across multiple sensor modalities and setups

Abstract

We present Any4D, a scalable multi-view transformer for metric-scale, dense feed-forward 4D reconstruction. Any4D directly generates per-pixel motion and geometry predictions for N frames, in contrast to prior work that typically focuses on either 2-view dense scene flow or sparse 3D point tracking. Moreover, unlike other recent methods for 4D reconstruction from monocular RGB videos, Any4D can process additional modalities and sensors such as RGB-D frames, IMU-based egomotion, and Radar Doppler measurements, when available. One of the key innovations that allows for such a flexible framework is a modular representation of a 4D scene; specifically, per-view 4D predictions are encoded using a variety of egocentric factors (depthmaps and camera intrinsics) represented in local camera coordinates, and allocentric factors (camera extrinsics and scene flow) represented in global world coordinates. We achieve superior performance across diverse setups - both in terms of accuracy (2-3X lower error) and compute efficiency (15X faster), opening avenues for multiple downstream applications.