RAC: Rectified Flow Auto Coder
This work provides a more efficient and higher-quality generative model for researchers and practitioners working with VAEs, addressing the reconstruction-generation gap.
This paper introduces the Rectified Flow Auto Coder (RAC), a new generative model that replaces traditional VAEs by using a multi-step decoding process inspired by Rectified Flow. The RAC model achieves state-of-the-art performance in both reconstruction and generation, while reducing computational cost by approximately 70% and parameter count by nearly 41%.
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.