Identity-Preserving Text-to-Video Generation by Frequency Decomposition

• URL: http://arxiv.org/abs/2411.17440v1
• Date: Tue, 26 Nov 2024 13:58:24 GMT
• Title: Identity-Preserving Text-to-Video Generation by Frequency Decomposition
• Authors: Shenghai Yuan, Jinfa Huang, Xianyi He, Yunyuan Ge, Yujun Shi, Liuhan Chen, Jiebo Luo, Li Yuan,
• Abstract summary: Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in literature. We propose ConsisID, a tuning-free DiT-based controllable IPT2V model to keep human identity consistent in the generated video.
• Score: 52.19475797580653
• License:
• Abstract: Identity-preserving text-to-video (IPT2V) generation aims to create high-fidelity videos with consistent human identity. It is an important task in video generation but remains an open problem for generative models. This paper pushes the technical frontier of IPT2V in two directions that have not been resolved in literature: (1) A tuning-free pipeline without tedious case-by-case finetuning, and (2) A frequency-aware heuristic identity-preserving DiT-based control scheme. We propose ConsisID, a tuning-free DiT-based controllable IPT2V model to keep human identity consistent in the generated video. Inspired by prior findings in frequency analysis of diffusion transformers, it employs identity-control signals in the frequency domain, where facial features can be decomposed into low-frequency global features and high-frequency intrinsic features. First, from a low-frequency perspective, we introduce a global facial extractor, which encodes reference images and facial key points into a latent space, generating features enriched with low-frequency information. These features are then integrated into shallow layers of the network to alleviate training challenges associated with DiT. Second, from a high-frequency perspective, we design a local facial extractor to capture high-frequency details and inject them into transformer blocks, enhancing the model's ability to preserve fine-grained features. We propose a hierarchical training strategy to leverage frequency information for identity preservation, transforming a vanilla pre-trained video generation model into an IPT2V model. Extensive experiments demonstrate that our frequency-aware heuristic scheme provides an optimal control solution for DiT-based models. Thanks to this scheme, our ConsisID generates high-quality, identity-preserving videos, making strides towards more effective IPT2V.

Related papers

• PersonalVideo: High ID-Fidelity Video Customization without Dynamic and Semantic Degradation [36.21554597804604]
  Identity-specific human video generation with customized ID images is still under-explored. We propose a novel framework, dubbed textbfPersonalVideo, that applies direct supervision on videos synthesized by the T2V model. Our method's superiority in delivering high identity faithfulness while preserving the inherent video generation qualities of the original T2V model, outshining prior approaches.
  arXiv  Detail & Related papers  (2024-11-26T02:25:38Z)
• T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design [79.7289790249621]
  Our proposed method, T2V-Turbo-v2, introduces a significant advancement by integrating various supervision signals. We highlight the crucial importance of tailoring datasets to specific learning objectives. We demonstrate the potential of this approach by extracting motion guidance from the training datasets and incorporating it into the ODE solver.
  arXiv  Detail & Related papers  (2024-10-08T04:30:06Z)
• Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation [72.90144343056227]
  We explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We introduce a novel framework, termed "VD-IT", tailored with dedicatedly designed components built upon a fixed T2V model. Our VD-IT achieves highly competitive results, surpassing many existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-03-18T17:59:58Z)
• Denoising Vision Transformers [43.03068202384091]
  We propose a two-stage denoising approach, termed Denoising Vision Transformers (DVT) In the first stage, we separate the clean features from those contaminated by positional artifacts by enforcing cross-view feature consistency with neural fields on a per-image basis. In the second stage, we train a lightweight transformer block to predict clean features from raw ViT outputs, leveraging the derived estimates of the clean features as supervision.
  arXiv  Detail & Related papers  (2024-01-05T18:59:52Z)
• I2V-Adapter: A General Image-to-Video Adapter for Diffusion Models [80.32562822058924]
  Text-guided image-to-video (I2V) generation aims to generate a coherent video that preserves the identity of the input image. I2V-Adapter adeptly propagates the unnoised input image to subsequent noised frames through a cross-frame attention mechanism. Our experimental results demonstrate that I2V-Adapter is capable of producing high-quality videos.
  arXiv  Detail & Related papers  (2023-12-27T19:11:50Z)
• Generative AI Beyond LLMs: System Implications of Multi-Modal Generation [12.827526286642282]
  We present the first work towards understanding this new system design space for multi-modal text-to-image (TTI) and text-to-video (TTV) generation models. Our systematic performance characterization on a suite of eight representative TTI/TTV models shows that after state-of-the-art optimization techniques such as Flash Attention are applied, Convolution accounts for up to 44% of execution time for Diffusion-based TTI models. We additionally observe that Diffusion-based TTI models resemble the Prefill stage of LLM inference, and benefit from 1.1-2.5x greater speedup from Flash
  arXiv  Detail & Related papers  (2023-12-22T02:21:26Z)
• DiffiT: Diffusion Vision Transformers for Image Generation [88.08529836125399]
  Vision Transformer (ViT) has demonstrated strong modeling capabilities and scalability, especially for recognition tasks. We study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT) DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency.
  arXiv  Detail & Related papers  (2023-12-04T18:57:01Z)
• Laplacian-Former: Overcoming the Limitations of Vision Transformers in Local Texture Detection [3.784298636620067]
  Vision Transformer (ViT) models have demonstrated a breakthrough in a wide range of computer vision tasks. These models struggle to capture high-frequency components of images, which can limit their ability to detect local textures and edge information. We propose a new technique, Laplacian-Former, that enhances the self-attention map by adaptively re-calibrating the frequency information in a Laplacian pyramid.
  arXiv  Detail & Related papers  (2023-08-31T19:56:14Z)
• 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)
• Improved Transformer for High-Resolution GANs [69.42469272015481]
  We introduce two key ingredients to Transformer to address this challenge. We show in the experiments that the proposed HiT achieves state-of-the-art FID scores of 31.87 and 2.95 on unconditional ImageNet $128 times 128$ and FFHQ $256 times 256$, respectively.
  arXiv  Detail & Related papers  (2021-06-14T17:39:49Z)

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.