Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation

• URL: http://arxiv.org/abs/2409.12532v1
• Date: Thu, 19 Sep 2024 07:50:34 GMT
• Title: Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation
• Authors: Chenyu Wang, Shuo Yan, Yixuan Chen, Yujiang Wang, Mingzhi Dong, Xiaochen Yang, Dongsheng Li, Robert P. Dick, Qin Lv, Fan Yang, Tun Lu, Ning Gu, Li Shang,
• Abstract summary: This work presents a Diffusion Reuse MOtion network to accelerate latent video generation. coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames. Dr. Mo propagates those coarse-grained noises onto the next frame by incorporating carefully designed, lightweight inter-frame motions.
• Score: 36.098738197088124
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation. Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames. Following this observation, Dr. Mo propagates those coarse-grained noises onto the next frame by incorporating carefully designed, lightweight inter-frame motions, eliminating massive computational redundancy in frame-wise diffusion models. The more sensitive and fine-grained noises are still acquired via later denoising steps, which can be essential to retain visual qualities. As such, deciding which intermediate steps should switch from motion-based propagations to denoising can be a crucial problem and a key tradeoff between efficiency and quality. Dr. Mo employs a meta-network named Denoising Step Selector (DSS) to dynamically determine desirable intermediate steps across video frames. Extensive evaluations on video generation and editing tasks have shown that Dr. Mo can substantially accelerate diffusion models in video tasks with improved visual qualities.

Related papers

• Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models [64.2445487645478]
  Large Language Models have shown remarkable efficacy in generating streaming data such as text and audio. We present Live2Diff, the first attempt at designing a video diffusion model with uni-directional temporal attention, specifically targeting live streaming video translation.
  arXiv  Detail & Related papers  (2024-07-11T17:34:51Z)
• TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models [94.24861019513462]
  TRIP is a new recipe of image-to-video diffusion paradigm. It pivots on image noise prior derived from static image to jointly trigger inter-frame relational reasoning. Extensive experiments on WebVid-10M, DTDB and MSR-VTT datasets demonstrate TRIP's effectiveness.
  arXiv  Detail & Related papers  (2024-03-25T17:59:40Z)
• EulerMormer: Robust Eulerian Motion Magnification via Dynamic Filtering within Transformer [30.470336098766765]
  Video Motion Magnification (VMM) aims to break the resolution limit of human visual perception capability. This paper proposes a novel dynamic filtering strategy to achieve static-dynamic field adaptive denoising. We demonstrate extensive experiments that EulerMormer achieves more robust video motion magnification from the Eulerian perspective.
  arXiv  Detail & Related papers  (2023-12-07T09:10:16Z)
• EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation [57.539634387672656]
  Current state-of-the-art generative diffusion models have produced impressive results but struggle to achieve fast generation without sacrificing quality. We introduce Efficient Motion Diffusion Model (EMDM) for fast and high-quality human motion generation.
  arXiv  Detail & Related papers  (2023-12-04T18:58:38Z)
• Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution [15.197746480157651]
  We propose an effective real-world VSR algorithm by leveraging the strength of pre-trained latent diffusion models. We exploit the temporal dynamics in LR videos to guide the diffusion process by optimizing the latent sampling path with a motion-guided loss. The proposed motion-guided latent diffusion based VSR algorithm achieves significantly better perceptual quality than state-of-the-arts on real-world VSR benchmark datasets.
  arXiv  Detail & Related papers  (2023-12-01T14:40:07Z)
• VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation [88.49030739715701]
  This work presents a decomposed diffusion process via resolving the per-frame noise into a base noise that is shared among all frames and a residual noise that varies along the time axis. Experiments on various datasets confirm that our approach, termed as VideoFusion, surpasses both GAN-based and diffusion-based alternatives in high-quality video generation.
  arXiv  Detail & Related papers  (2023-03-15T02:16:39Z)
• Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising [137.5080784570804]
  Video denoising aims at removing noise from videos to recover clean ones. Some existing works show that optical flow can help the denoising by exploiting the additional spatial-temporal clues from nearby frames. We propose a new multi-scale refined optical flow-guided video denoising method, which is more robust to different noise levels.
  arXiv  Detail & Related papers  (2022-08-25T00:09:18Z)
• Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer [29.03463312813923]
  Video denoising aims to recover high-quality frames from the noisy video. Most existing approaches adopt convolutional neural networks(CNNs) to separate the noise from the original visual content. We propose a Dual-stage Spatial-Channel Transformer (DSCT) for coarse-to-fine video denoising.
  arXiv  Detail & Related papers  (2022-04-30T09:01:21Z)

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.