MV2MAE: Multi-View Video Masked Autoencoders

TL;DR

MV2MAE introduces a self-supervised learning framework for multi-view videos using cross-view reconstruction and motion-weighted loss, enhancing 3D understanding and robustness to viewpoint changes.

Contribution

It presents a novel multi-view masked autoencoder with cross-view decoding and motion-weighted loss for improved video representation learning.

Findings

Achieves state-of-the-art results on multiple datasets.

Demonstrates robustness to viewpoint variations.

Improves temporal modeling in video representations.

Abstract

Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from synchronized multi-view videos. We use a cross-view reconstruction task to inject geometry information in the model. Our approach is based on the masked autoencoder (MAE) framework. In addition to the same-view decoder, we introduce a separate cross-view decoder which leverages cross-attention mechanism to reconstruct a target viewpoint video using a video from source viewpoint, to help representations robust to viewpoint changes. For videos, static regions can be reconstructed trivially which hinders learning meaningful representations. To tackle this, we introduce a motion-weighted reconstruction loss which improves temporal modeling. We report state-of-the-art results on the NTU-60, NTU-120 and ETRI datasets, as well as in the transfer learning setting on NUCLA, PKU-MMD-II and ROCOG-v2 datasets, demonstrating the robustness of our approach. Code will be made available.