Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks

• URL: http://arxiv.org/abs/2412.00733v3
• Date: Sat, 04 Jan 2025 06:49:09 GMT
• Title: Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Diffusion Transformer Networks
• Authors: Jiahao Cui, Hui Li, Yun Zhan, Hanlin Shang, Kaihui Cheng, Yuqi Ma, Shan Mu, Hang Zhou, Jingdong Wang, Siyu Zhu,
• Abstract summary: We introduce the first application of a pretrained transformer-based video generative model for portrait animation. Our method is validated through experiments on benchmark and newly proposed wild datasets.
• Score: 25.39030226963548
• License:
• Abstract: Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait, and generating immersive, realistic backgrounds. In this paper, we introduce the first application of a pretrained transformer-based video generative model that demonstrates strong generalization capabilities and generates highly dynamic, realistic videos for portrait animation, effectively addressing these challenges. The adoption of a new video backbone model makes previous U-Net-based methods for identity maintenance, audio conditioning, and video extrapolation inapplicable. To address this limitation, we design an identity reference network consisting of a causal 3D VAE combined with a stacked series of transformer layers, ensuring consistent facial identity across video sequences. Additionally, we investigate various speech audio conditioning and motion frame mechanisms to enable the generation of continuous video driven by speech audio. Our method is validated through experiments on benchmark and newly proposed wild datasets, demonstrating substantial improvements over prior methods in generating realistic portraits characterized by diverse orientations within dynamic and immersive scenes. Further visualizations and the source code are available at: https://fudan-generative-vision.github.io/hallo3/.

Related papers

• T-SVG: Text-Driven Stereoscopic Video Generation [87.62286959918566]
  This paper introduces the Text-driven Stereoscopic Video Generation (T-SVG) system. It streamlines video generation by using text prompts to create reference videos. These videos are transformed into 3D point cloud sequences, which are rendered from two perspectives with subtle parallax differences.
  arXiv  Detail & Related papers  (2024-12-12T14:48:46Z)
• JoyVASA: Portrait and Animal Image Animation with Diffusion-Based Audio-Driven Facial Dynamics and Head Motion Generation [10.003794924759765]
  JoyVASA is a diffusion-based method for generating facial dynamics and head motion in audio-driven facial animation. We introduce a decoupled facial representation framework that separates dynamic facial expressions from static 3D facial representations. In the second stage, a diffusion transformer is trained to generate motion sequences directly from audio cues, independent of character identity.
  arXiv  Detail & Related papers  (2024-11-14T06:13:05Z)
• G3FA: Geometry-guided GAN for Face Animation [14.488117084637631]
  We introduce Geometry-guided GAN for Face Animation (G3FA) to tackle this limitation. Our novel approach empowers the face animation model to incorporate 3D information using only 2D images. In our face reenactment model, we leverage 2D motion warping to capture motion dynamics.
  arXiv  Detail & Related papers  (2024-08-23T13:13:24Z)
• WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models [132.77237314239025]
  Video virtual try-on aims to generate realistic sequences that maintain garment identity and adapt to a person's pose and body shape in source videos. Traditional image-based methods, relying on warping and blending, struggle with complex human movements and occlusions. We reconceptualize video try-on as a process of generating videos conditioned on garment descriptions and human motion. Our solution, WildVidFit, employs image-based controlled diffusion models for a streamlined, one-stage approach.
  arXiv  Detail & Related papers  (2024-07-15T11:21:03Z)
• 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)
• ReliTalk: Relightable Talking Portrait Generation from a Single Video [62.47116237654984]
  ReliTalk is a novel framework for relightable audio-driven talking portrait generation from monocular videos. Our key insight is to decompose the portrait's reflectance from implicitly learned audio-driven facial normals and images.
  arXiv  Detail & Related papers  (2023-09-05T17:59:42Z)
• High-Fidelity and Freely Controllable Talking Head Video Generation [31.08828907637289]
  We propose a novel model that produces high-fidelity talking head videos with free control over head pose and expression. We introduce a novel motion-aware multi-scale feature alignment module to effectively transfer the motion without face distortion. We evaluate our model on challenging datasets and demonstrate its state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-04-20T09:02:41Z)
• DynIBaR: Neural Dynamic Image-Based Rendering [79.44655794967741]
  We address the problem of synthesizing novel views from a monocular video depicting a complex dynamic scene. We adopt a volumetric image-based rendering framework that synthesizes new viewpoints by aggregating features from nearby views. We demonstrate significant improvements over state-of-the-art methods on dynamic scene datasets.
  arXiv  Detail & Related papers  (2022-11-20T20:57:02Z)
• PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering [56.762094966235566]
  A Portrait Image Neural Renderer is proposed to control the face motions with the parameters of three-dimensional morphable face models. The proposed model can generate photo-realistic portrait images with accurate movements according to intuitive modifications. Our model can generate coherent videos with convincing movements from only a single reference image and a driving audio stream.
  arXiv  Detail & Related papers  (2021-09-17T07:24:16Z)
• LipSync3D: Data-Efficient Learning of Personalized 3D Talking Faces from Video using Pose and Lighting Normalization [4.43316916502814]
  We present a video-based learning framework for animating personalized 3D talking faces from audio. We introduce two training-time data normalizations that significantly improve data sample efficiency. Our method outperforms contemporary state-of-the-art audio-driven video reenactment benchmarks in terms of realism, lip-sync and visual quality scores.
  arXiv  Detail & Related papers  (2021-06-08T08:56:40Z)

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.