Adaptive 1D Video Diffusion Autoencoder
This addresses inefficiencies in video compression for generative modeling, though it is incremental as it builds on existing autoencoder and diffusion methods.
The paper tackled limitations in video autoencoders, such as fixed-rate compression and inflexible architectures, by proposing One-DVA, a transformer-based framework with adaptive 1D encoding and diffusion-based decoding, achieving comparable reconstruction performance to 3D-CNN VAEs at identical compression ratios while enabling higher compression ratios.
Recent video generation models largely rely on video autoencoders that compress pixel-space videos into latent representations. However, existing video autoencoders suffer from three major limitations: (1) fixed-rate compression that wastes tokens on simple videos, (2) inflexible CNN architectures that prevent variable-length latent modeling, and (3) deterministic decoders that struggle to recover appropriate details from compressed latents. To address these issues, we propose One-Dimensional Diffusion Video Autoencoder (One-DVA), a transformer-based framework for adaptive 1D encoding and diffusion-based decoding. The encoder employs query-based vision transformers to extract spatiotemporal features and produce latent representations, while a variable-length dropout mechanism dynamically adjusts the latent length. The decoder is a pixel-space diffusion transformer that reconstructs videos with the latents as input conditions. With a two-stage training strategy, One-DVA achieves performance comparable to 3D-CNN VAEs on reconstruction metrics at identical compression ratios. More importantly, it supports adaptive compression and thus can achieve higher compression ratios. To better support downstream latent generation, we further regularize the One-DVA latent distribution for generative modeling and fine-tune its decoder to mitigate artifacts caused by the generation process.