Pith. sign in

REVIEW 13 cited by

MagicPose: Realistic Human Poses and Facial Expressions Retargeting with Identity-aware Diffusion

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2311.12052 v3 pith:KSSDAPQ7 submitted 2023-11-18 cs.CV

Di Chang , Yichun Shi , Quankai Gao , Jessica Fu , Hongyi Xu , Guoxian Song , Qing Yan , Yizhe Zhu
show 2 more authors
Xiao Yang Mohammad Soleymani
This is my paper
classification cs.CV
keywords facialhumandiffusionexpressionsmagicposeposesappearancecontrol
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we propose MagicPose, a diffusion-based model for 2D human pose and facial expression retargeting. Specifically, given a reference image, we aim to generate a person's new images by controlling the poses and facial expressions while keeping the identity unchanged. To this end, we propose a two-stage training strategy to disentangle human motions and appearance (e.g., facial expressions, skin tone and dressing), consisting of (1) the pre-training of an appearance-control block and (2) learning appearance-disentangled pose control. Our novel design enables robust appearance control over generated human images, including body, facial attributes, and even background. By leveraging the prior knowledge of image diffusion models, MagicPose generalizes well to unseen human identities and complex poses without the need for additional fine-tuning. Moreover, the proposed model is easy to use and can be considered as a plug-in module/extension to Stable Diffusion. The code is available at: https://github.com/Boese0601/MagicDance

Discussion (0). Sign in to comment.

Forward citations

Cited by 13 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation

    cs.GR 2025-12 unverdicted novelty 7.0 of 10

    FrameCache uses a Screen-Cache-Match strategy and Trajectory-Aware Autoregressive Generation to convert past frames into causal guidance for temporally coherent human animation videos.

  2. One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

    cs.CV 2025-11 unverdicted novelty 7.0 of 10

    One-to-All Animation enables alignment-free character animation and image pose transfer via self-supervised outpainting reformulation, reference extraction, hybrid fusion attention, identity-robust pose control, and t...

  3. MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A diffusion-based framework that animates multiple characters in one scene from separate reference images and pose sequences while preserving each character's identity.

  4. Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A DiT Mixture-of-Experts world model jointly learns locomotion, dual-arm manipulation, and egocentric hand control, with shared experts for world dynamics and progressive expert expansion for new modalities.

  5. EMOSH: Expressive Motion and Shape Disentanglement for Human Animation

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    EMOSH proposes an Expressive Human Model with disentangled parameters, coarse-to-fine motion injection, and spatially-aligned conditioning to generate high-fidelity expressive human videos without driving-subject shap...

  6. Interactive Multi-Turn Retrieval for Health Videos

    cs.IR 2026-05 unverdicted novelty 6.0 of 10

    DATR combines coarse CLIP-based retrieval with multi-turn query fusion and cross-encoder re-ranking to improve health video retrieval, supported by the new MHVRC corpus.

  7. OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation

    cs.CV 2026-04 conditional novelty 6.0 of 10

    A large-scale, hierarchically-annotated human-centric video dataset and a three-level benchmark (OHBench) are presented, showing that fine-tuning on a subset of the data improves audio-video generation model performance.

  8. OmniHuman: A Large-scale Dataset and Benchmark for Human-Centric Video Generation

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    OmniHuman is a new large-scale multi-scene dataset with video-, frame-, and individual-level annotations for human-centric video generation, accompanied by the OHBench benchmark that adds metrics aligned with human pe...

  9. Video Color Grading via Look-Up Table Generation

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A diffusion model generates a 3D look-up table from the feature difference between a source frame and a reference frame to grade video colors while preserving structure and enabling text-based retouching.

  10. Animate-X++: Universal Character Image Animation with Dynamic Backgrounds

    cs.CV 2025-08 conditional novelty 5.0 of 10

    Animate-X++ turns cartoon images into pose-driven animations with text-controlled moving backgrounds, claiming state-of-the-art results on a new synthetic anthropomorphic benchmark.

  11. Controllable Pedestrian Video Editing for Multi-View Driving Scenarios via Motion Sequence

    cs.CV 2025-08 conditional novelty 5.0 of 10

    A pose-conditioned video inpainting pipeline edits pedestrians in multi-view driving footage and reports a small downstream improvement in pedestrian detection accuracy.

  12. Human Motion Video Generation: A Survey

    cs.CV 2025-09 conditional novelty 4.0 of 10

    A comprehensive survey with a five-phase pipeline model for human motion video generation, covering over 200 papers and adding a new benchmark comparison of nine pose-guided methods.

  13. LIA-X: Interpretable Latent Portrait Animator

    cs.CV 2025-08 conditional novelty 4.0 of 10

    Adding an L1 sparsity penalty to the motion dictionary of the LIA portrait animator produces disentangled, human-interpretable motion vectors that support controllable image and video editing and scale to roughly one ...

Pith tools