DeCo-VAE: Learning Compact Latents for Video Reconstruction via Decoupled Representation

TL;DR

DeCo-VAE introduces a decoupled approach to video VAEs, decomposing content into keyframes, motion, and residuals, leading to more compact latent representations and improved reconstruction quality.

Contribution

The paper proposes a novel decoupled VAE architecture with dedicated encoders for video components, enhancing latent compactness and reconstruction accuracy.

Findings

Achieves superior video reconstruction performance

Effectively decomposes video content into distinct components

Ensures stable training through decoupled adaptation strategy

Abstract

Existing video Variational Autoencoders (VAEs) generally overlook the similarity between frame contents, leading to redundant latent modeling. In this paper, we propose decoupled VAE (DeCo-VAE) to achieve compact latent representation. Instead of encoding RGB pixels directly, we decompose video content into distinct components via explicit decoupling: keyframe, motion and residual, and learn dedicated latent representation for each. To avoid cross-component interference, we design dedicated encoders for each decoupled component and adopt a shared 3D decoder to maintain spatiotemporal consistency during reconstruction. We further utilize a decoupled adaptation strategy that freezes partial encoders while training the others sequentially, ensuring stable training and accurate learning of both static and dynamic features. Extensive quantitative and qualitative experiments demonstrate that DeCo-VAE achieves superior video reconstruction performance.