ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis

• URL: http://arxiv.org/abs/2604.19720v1
• Date: Tue, 21 Apr 2026 17:47:26 GMT
• Title: ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
• Abstract summary: We propose a pose- and viewpoint-controllable pipeline that combines a pretrained image backbone with SMPL-X-based motion guidance.<n>Our method produces high-quality, temporally consistent videos under diverse poses and viewpoints.
• Score: 46.87481841960487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods often address these factors separately, resulting in limited controllability or reduced visual quality. We revisit this problem from an image-first perspective, where high-quality human appearance is learned via image generation and used as a prior for video synthesis, decoupling appearance modeling from temporal consistency. We propose a pose- and viewpoint-controllable pipeline that combines a pretrained image backbone with SMPL-X-based motion guidance, together with a training-free temporal refinement stage based on a pretrained video diffusion model. Our method produces high-quality, temporally consistent videos under diverse poses and viewpoints. We also release a canonical human dataset and an auxiliary model for compositional human image synthesis. Code and data are publicly available at https://github.com/Taited/ReImagine.

Related papers

• Human Video Generation from a Single Image with 3D Pose and View Control [62.676151243249556]
  We present Human Video Generation in 4D (HVG), a latent video diffusion model capable of generating high-quality multi-view,temporally coherent human videos from a single image.<n>HVG achieves this through three key designs: (i) Articulated Pose Modulation, which captures the anatomical relationships of 3D joints via a novel dual-dimensional bone map and resolves self-occlusions across views by introducing 3D information; (ii) View and Temporal Alignment, which ensures multi-view consistency and alignment between a reference image and pose sequences for frame-to-frame stability; and (iii)
  arXiv  Detail & Related papers  (2026-02-24T18:42:20Z)
• HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers [60.86393841247567]
  HumanRAM is a novel feed-forward approach for generalizable human reconstruction and animation from monocular or sparse human images.<n>Our approach integrates human reconstruction and animation into a unified framework by introducing explicit pose conditions.<n> Experiments show that HumanRAM significantly surpasses previous methods in terms of reconstruction accuracy, animation fidelity, and generalization performance on real-world datasets.
  arXiv  Detail & Related papers  (2025-06-03T17:50:05Z)
• HumanGif: Single-View Human Diffusion with Generative Prior [25.516544735593087]
  We propose HumanGif, a single-view human diffusion model with generative priors.<n>Specifically, we formulate the single-view-based 3D human novel view and pose synthesis as a single-view-conditioned human diffusion process.<n>We show that HumanGif achieves the best perceptual performance, with better generalizability for novel view and pose synthesis.
  arXiv  Detail & Related papers  (2025-02-17T17:55:27Z)
• GAS: Generative Avatar Synthesis from a Single Image [54.95198111659466]
  We present a framework for synthesizing view-consistent and temporally coherent avatars from a single image.<n>Our approach combines the reconstruction power of regression-based 3D human reconstruction with the generative capabilities of a diffusion model.
  arXiv  Detail & Related papers  (2025-02-10T19:00:39Z)
• MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild [32.6521941706907]
  We present MultiPly, a novel framework to reconstruct multiple people in 3D from monocular in-the-wild videos. We first define a layered neural representation for the entire scene, composited by individual human and background models. We learn the layered neural representation from videos via our layer-wise differentiable volume rendering.
  arXiv  Detail & Related papers  (2024-06-03T17:59:57Z)
• VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis [40.869862603815875]
  VLOGGER is a method for audio-driven human video generation from a single input image. We use a novel diffusion-based architecture that augments text-to-image models with both spatial and temporal controls. We show applications in video editing and personalization.
  arXiv  Detail & Related papers  (2024-03-13T17:59:02Z)
• Neural Rendering of Humans in Novel View and Pose from Monocular Video [68.37767099240236]
  We introduce a new method that generates photo-realistic humans under novel views and poses given a monocular video as input. Our method significantly outperforms existing approaches under unseen poses and novel views given monocular videos as input.
  arXiv  Detail & Related papers  (2022-04-04T03:09:20Z)
• Image Comes Dancing with Collaborative Parsing-Flow Video Synthesis [124.48519390371636]
  Transfering human motion from a source to a target person poses great potential in computer vision and graphics applications. Previous work has either relied on crafted 3D human models or trained a separate model specifically for each target person. This work studies a more general setting, in which we aim to learn a single model to parsimoniously transfer motion from a source video to any target person.
  arXiv  Detail & Related papers  (2021-10-27T03:42:41Z)
• StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN [70.31913835035206]
  We present a novel approach to the video synthesis problem that helps to greatly improve visual quality. We make use of a pre-trained StyleGAN network, the latent space of which allows control over the appearance of the objects it was trained for. Our temporal architecture is then trained not on sequences of RGB frames, but on sequences of StyleGAN latent codes.
  arXiv  Detail & Related papers  (2021-07-15T09:58:15Z)

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.