RAC: Rectified Flow Auto Coder

TL;DR

RAC introduces a rectified flow-based auto-coding method that enables multi-step, correctable decoding, bidirectional inference, and improved generation quality with lower computational costs, surpassing state-of-the-art VAEs.

Contribution

The paper presents a novel rectified flow auto coder that enhances decoding, reduces parameters, and improves generative performance over traditional VAEs.

Findings

Outperforms SOTA VAEs in reconstruction and generation.

Reduces parameter count by nearly 41%.

Achieves approximately 70% lower computational cost.

Abstract

In this paper, we propose a Rectified Flow Auto Coder (RAC) inspired by Rectified Flow to replace the traditional VAE: 1. It achieves multi-step decoding by applying the decoder to flow timesteps. Its decoding path is straight and correctable, enabling step-by-step refinement. 2. The model inherently supports bidirectional inference, where the decoder serves as the encoder through time reversal (hence Coder rather than encoder or decoder), reducing parameter count by nearly 41%. 3. This generative decoding method improves generation quality since the model can correct latent variables along the path, partially addressing the reconstruction--generation gap. Experiments show that RAC surpasses SOTA VAEs in both reconstruction and generation with approximately 70% lower computational cost.