Related papers: DLFR-VAE: Dynamic Latent Frame Rate VAE for Video …
Spatio-temporal compression of videos, utilizing networks such as Variational Autoencoders (VAE), plays a crucial role in OpenAI's SORA and numerous other video generative models. For instance, many LLM-like video models learn the…
Diffusion Transformer(DiT)-based generation models have achieved remarkable success in video generation. However, their inherent computational demands pose significant efficiency challenges. In this paper, we exploit the inherent temporal…
Recent advances in Latent Video Diffusion Models (LVDMs) have revolutionized video generation by leveraging Video Variational Autoencoders (Video VAEs) to compress intricate video data into a compact latent space. However, as LVDM training…
Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…
We introduce LTX-Video, a transformer-based latent diffusion model that adopts a holistic approach to video generation by seamlessly integrating the responsibilities of the Video-VAE and the denoising transformer. Unlike existing methods,…
Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal…
Variational Autoencoder (VAE), compressing videos into latent representations, is a crucial preceding component of Latent Video Diffusion Models (LVDMs). With the same reconstruction quality, the more sufficient the VAE's compression for…
Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs), achieving higher compression rates is desirable; yet, the…
Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a…
Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model training costs. However, as the resolution and duration of…
Recent breakthroughs in video autoencoders (Video AEs) have advanced video generation, but existing methods fail to efficiently model spatio-temporal redundancies in dynamics, resulting in suboptimal compression factors. This shortfall…
Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when…
The usage of deep generative models for image compression has led to impressive performance gains over classical codecs while neural video compression is still in its infancy. Here, we propose an end-to-end, deep generative modeling…
The past few years have witnessed increasing interests in applying deep learning to video compression. However, the existing approaches compress a video frame with only a few number of reference frames, which limits their ability to fully…
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation. On the other hand,…
Existing frameworks for learned video compression suffer from a dilemma between inaccurate temporal alignment and error propagation for motion estimation and compensation (ME/MC). The separate-transform framework employs distinct transforms…
Video autoencoders compress videos into compact latent representations for efficient reconstruction, playing a vital role in enhancing the quality and efficiency of video generation. However, existing video autoencoders often entangle…
Modern video generation frameworks based on Latent Diffusion Models suffer from inefficiencies in tokenization due to the Frame-Proportional Information Assumption. Existing tokenizers provide fixed temporal compression rates, causing the…
Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different…
Video generation has seen remarkable progress thanks to advancements in generative deep learning. However, generating long sequences remains a significant challenge. Generated videos should not only display coherent and continuous movement…