WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model

• URL: http://arxiv.org/abs/2411.17459v3
• Date: Fri, 11 Apr 2025 12:31:07 GMT
• Title: WF-VAE: Enhancing Video VAE by Wavelet-Driven Energy Flow for Latent Video Diffusion Model
• Authors: Zongjian Li, Bin Lin, Yang Ye, Liuhan Chen, Xinhua Cheng, Shenghai Yuan, Li Yuan,
• Abstract summary: Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space.<n>VAE is a key component of most Latent Video Diffusion Models (LVDMs)
• Score: 15.171544722138806
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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 generated videos increase, the encoding cost of Video VAEs becomes a limiting bottleneck in training LVDMs. Moreover, the block-wise inference method adopted by most LVDMs can lead to discontinuities of latent space when processing long-duration videos. The key to addressing the computational bottleneck lies in decomposing videos into distinct components and efficiently encoding the critical information. Wavelet transform can decompose videos into multiple frequency-domain components and improve the efficiency significantly, we thus propose Wavelet Flow VAE (WF-VAE), an autoencoder that leverages multi-level wavelet transform to facilitate low-frequency energy flow into latent representation. Furthermore, we introduce a method called Causal Cache, which maintains the integrity of latent space during block-wise inference. Compared to state-of-the-art video VAEs, WF-VAE demonstrates superior performance in both PSNR and LPIPS metrics, achieving 2x higher throughput and 4x lower memory consumption while maintaining competitive reconstruction quality. Our code and models are available at https://github.com/PKU-YuanGroup/WF-VAE.

Related papers

• Plug-and-Play Versatile Compressed Video Enhancement [57.62582951699999]
  Video compression effectively reduces the size of files, making it possible for real-time cloud computing. However, it comes at the cost of visual quality, challenges the robustness of downstream vision models. We present a versatile-aware enhancement framework that adaptively enhance videos under different compression settings.
  arXiv  Detail & Related papers  (2025-04-21T18:39:31Z)
• Generating, Fast and Slow: Scalable Parallel Video Generation with Video Interface Networks [21.710127132217526]
  We introduce a new paradigm called Video Interface Networks (VINs), which augment DiTs with an abstraction module to enable parallel inference of video chunks. VINs encode global semantics from the noisy input of local chunks and the encoded representations, in turn, guide DiTs in denoising chunks in parallel. Our approach attains state-of-the-art motion smoothness while using 25-40% fewer FLOPs than full generation.
  arXiv  Detail & Related papers  (2025-03-21T21:13:02Z)
• LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models [17.29580459404157]
  We propose LeanVAE, a novel and ultra-efficient Video VAE framework. Our model offers up to 50x fewer FLOPs and 44x faster inference speed. Our experiments validate LeanVAE's superiority in video reconstruction and generation.
  arXiv  Detail & Related papers  (2025-03-18T14:58:59Z)
• REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder [52.698595889988766]
  We present a novel perspective on learning video embedders for generative modeling. Rather than requiring an exact reproduction of an input video, an effective embedder should focus on visually plausible reconstructions. We propose replacing the conventional encoder-decoder video embedder with an encoder-generator framework.
  arXiv  Detail & Related papers  (2025-03-11T17:51:07Z)
• Token-Efficient Long Video Understanding for Multimodal LLMs [101.70681093383365]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs. We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• Rethinking Video Tokenization: A Conditioned Diffusion-based Approach [58.164354605550194]
  New tokenizer, Diffusion Conditioned-based Gene Tokenizer, replaces GAN-based decoder with conditional diffusion model. We trained using only a basic MSE diffusion loss for reconstruction, along with KL term and LPIPS perceptual loss from scratch. Even a scaled-down version of CDT (3$times inference speedup) still performs comparably with top baselines.
  arXiv  Detail & Related papers  (2025-03-05T17:59:19Z)
• Large Motion Video Autoencoding with Cross-modal Video VAE [52.13379965800485]
  Video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Existing Video VAEs have begun to address temporal compression; however, they often suffer from inadequate reconstruction performance. We present a novel and powerful video autoencoder capable of high-fidelity video encoding.
  arXiv  Detail & Related papers  (2024-12-23T18:58:24Z)
• Improved Video VAE for Latent Video Diffusion Model [55.818110540710215]
  Video Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora. Most of existing VAEs inflate a pretrained image VAE into the 3D causal structure for temporal-spatial compression. We propose a new KTC architecture and a group causal convolution (GCConv) module to further improve video VAE (IV-VAE)
  arXiv  Detail & Related papers  (2024-11-10T12:43:38Z)
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
  Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds. We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache) We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
  arXiv  Detail & Related papers  (2024-11-04T18:59:44Z)
• OD-VAE: An Omni-dimensional Video Compressor for Improving Latent Video Diffusion Model [33.766339921655025]
  Variational Autoencoder (VAE) compressing videos into latent representations is a crucial component of Latent Video Diffusion Models (LVDMs) Most LVDMs utilize 2D image VAE, whose compression for videos is only in the spatial dimension and often ignored in the temporal dimension. We propose an omni-dimension compression VAE, named OD-VAE, which can temporally and spatially compress videos.
  arXiv  Detail & Related papers  (2024-09-02T12:20:42Z)
• When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding [112.44822009714461]
  Cross-Modality Video Coding (CMVC) is a pioneering approach to explore multimodality representation and video generative models in video coding. During decoding, previously encoded components and video generation models are leveraged to create multiple encoding-decoding modes. Experiments indicate that TT2V achieves effective semantic reconstruction, while IT2V exhibits competitive perceptual consistency.
  arXiv  Detail & Related papers  (2024-08-15T11:36:18Z)
• QVD: Post-training Quantization for Video Diffusion Models [33.13078954859106]
  Post-training quantization (PTQ) is an effective technique to reduce memory footprint and improve computational efficiency. We introduce the first PTQ strategy tailored for video diffusion models, dubbed QVD. We achieve near-lossless performance degradation on W8A8, outperforming the current methods by 205.12 in FVD.
  arXiv  Detail & Related papers  (2024-07-16T10:47:27Z)
• An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models [65.37846460916042]
  We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs. We introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency.
  arXiv  Detail & Related papers  (2024-03-11T14:35:32Z)
• NU-Class Net: A Novel Approach for Video Quality Enhancement [1.7763979745248648]
  This paper introduces NU-Class Net, an innovative deep-learning model designed to mitigate compression artifacts stemming from lossy compression codecs. By employing the NU-Class Net, the video encoder within the video-capturing node can reduce output quality, thereby generating low-bit-rate videos. Experimental results affirm the efficacy of the proposed model in enhancing the perceptible quality of videos, especially those streamed at low bit rates.
  arXiv  Detail & Related papers  (2024-01-02T11:46:42Z)
• VNVC: A Versatile Neural Video Coding Framework for Efficient Human-Machine Vision [59.632286735304156]
  It is more efficient to enhance/analyze the coded representations directly without decoding them into pixels. We propose a versatile neural video coding (VNVC) framework, which targets learning compact representations to support both reconstruction and direct enhancement/analysis.
  arXiv  Detail & Related papers  (2023-06-19T03:04:57Z)
• Deep Video Coding with Dual-Path Generative Adversarial Network [39.19042551896408]
  This paper proposes an efficient codecs namely dual-path generative adversarial network-based video (DGVC) Our DGVC reduces the average bit-per-pixel (bpp) by 39.39%/54.92% at the same PSNR/MS-SSIM.
  arXiv  Detail & Related papers  (2021-11-29T11:39:28Z)
• Multi-Density Attention Network for Loop Filtering in Video Compression [9.322800480045336]
  We propose a on-line scaling based multi-density attention network for loop filtering in video compression. Experimental results show that 10.18% bit-rate reduction at the same video quality can be achieved over the latest Versatile Video Coding (VVC) standard.
  arXiv  Detail & Related papers  (2021-04-08T05:46:38Z)
• Multi-level Wavelet-based Generative Adversarial Network for Perceptual Quality Enhancement of Compressed Video [51.631731922593225]
  Existing methods mainly focus on enhancing the objective quality of compressed video while ignoring its perceptual quality. We propose a novel generative adversarial network (GAN) based on multi-level wavelet packet transform (WPT) to enhance the perceptual quality of compressed video.
  arXiv  Detail & Related papers  (2020-08-02T15:01:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.