TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models

• URL: http://arxiv.org/abs/2403.17005v1
• Date: Mon, 25 Mar 2024 17:59:40 GMT
• Title: TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models
• Authors: Zhongwei Zhang, Fuchen Long, Yingwei Pan, Zhaofan Qiu, Ting Yao, Yang Cao, Tao Mei,
• Abstract summary: 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.
• Score: 94.24861019513462
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless, the problem is not trivial when shaping diffusion models to animate static image (i.e., image-to-video generation). The difficulty originates from the aspect that the diffusion process of subsequent animated frames should not only preserve the faithful alignment with the given image but also pursue temporal coherence among adjacent frames. To alleviate this, we present TRIP, a new recipe of image-to-video diffusion paradigm that pivots on image noise prior derived from static image to jointly trigger inter-frame relational reasoning and ease the coherent temporal modeling via temporal residual learning. Technically, the image noise prior is first attained through one-step backward diffusion process based on both static image and noised video latent codes. Next, TRIP executes a residual-like dual-path scheme for noise prediction: 1) a shortcut path that directly takes image noise prior as the reference noise of each frame to amplify the alignment between the first frame and subsequent frames; 2) a residual path that employs 3D-UNet over noised video and static image latent codes to enable inter-frame relational reasoning, thereby easing the learning of the residual noise for each frame. Furthermore, both reference and residual noise of each frame are dynamically merged via attention mechanism for final video generation. Extensive experiments on WebVid-10M, DTDB and MSR-VTT datasets demonstrate the effectiveness of our TRIP for image-to-video generation. Please see our project page at https://trip-i2v.github.io/TRIP/.

Related papers

• Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model [31.70050311326183]
  Diffusion models tend to generate videos with less motion than expected. We address this issue from both inference and training aspects. Our methods outperform baselines by producing higher motion scores with lower errors.
  arXiv  Detail & Related papers  (2024-06-22T04:56:16Z)
• Explorative Inbetweening of Time and Space [46.77750028273578]
  We introduce bounded generation to control video generation based only on a given start and end frame. Time Reversal Fusion fuses the temporally forward and backward denoising paths conditioned on the start and end frame. We find that Time Reversal Fusion outperforms related work on all subtasks.
  arXiv  Detail & Related papers  (2024-03-21T17:57:31Z)
• Improving Diffusion-Based Image Synthesis with Context Prediction [49.186366441954846]
  Existing diffusion models mainly try to reconstruct input image from a corrupted one with a pixel-wise or feature-wise constraint along spatial axes. We propose ConPreDiff to improve diffusion-based image synthesis with context prediction. Our ConPreDiff consistently outperforms previous methods and achieves a new SOTA text-to-image generation results on MS-COCO, with a zero-shot FID score of 6.21.
  arXiv  Detail & Related papers  (2024-01-04T01:10:56Z)
• GenDeF: Learning Generative Deformation Field for Video Generation [89.49567113452396]
  We propose to render a video by warping one static image with a generative deformation field (GenDeF) Such a pipeline enjoys three appealing advantages.
  arXiv  Detail & Related papers  (2023-12-07T18:59:41Z)
• 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)
• You Can Ground Earlier than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos [56.676761067861236]
  Given an untrimmed video, temporal sentence grounding aims to locate a target moment semantically according to a sentence query. Previous respectable works have made decent success, but they only focus on high-level visual features extracted from decoded frames. We propose a new setting, compressed-domain TSG, which directly utilizes compressed videos rather than fully-decompressed frames as the visual input.
  arXiv  Detail & Related papers  (2023-03-14T12:53:27Z)
• Towards Smooth Video Composition [59.134911550142455]
  Video generation requires consistent and persistent frames with dynamic content over time. This work investigates modeling the temporal relations for composing video with arbitrary length, from a few frames to even infinite, using generative adversarial networks (GANs) We show that the alias-free operation for single image generation, together with adequately pre-learned knowledge, brings a smooth frame transition without compromising the per-frame quality.
  arXiv  Detail & Related papers  (2022-12-14T18:54:13Z)
• 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)
• Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask [14.265454188161819]
  We propose a learning-based approach for denoising raw videos captured under low lighting conditions. We first explicitly align the neighboring frames to the current frame using a convolutional neural network (CNN) We then fuse the registered frames using another CNN to obtain the final denoised frame.
  arXiv  Detail & Related papers  (2021-03-04T06:57:48Z)

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.