mlsanityData to 7 Oct 2026

Single Source One Shot Reenactment using Weighted motion From Paired Feature Points

arXiv 2104.03117 ↗First posted 7 Apr 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Image reenactment is a task where the target object in the source image imitates the motion represented in the driving image. One of the most common reenactment tasks is face image animation. The major challenge in the current face reenactment approaches is to distinguish between facial motion and identity. For this reason, the previous models struggle to produce high-quality animations if the driving and source identities are different (cross-person reenactment). We propose a new (face) reenactment model that learns shape-independent motion features in a self-supervised setup. The motion is represented using a set of paired feature points extracted from the source and driving images simultaneously. The model is generalised to multiple reenactment tasks including faces and non-face objects using only a single source image. The extensive experiments show that the model faithfully transfers the driving motion to the source while retaining the source identity intact.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 7 Apr 2021.

Builds on

23 of 32 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  3. 2019FaceForensics++: Learning to Detect Manipulated Facial Imagescited by 1,095
  4. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  5. 2020First Order Motion Model for Image Animationcited by 698
  6. 2020Face2Face: Real-time Face Capture and Reenactment of RGB Videoscited by 631
  7. 2019FSGAN: Subject Agnostic Face Swapping and Reenactmentcited by 319
  8. 2019Deep Closest Point: Learning Representations for Point Cloud Registrationcited by 318
  9. 2019Few-Shot Adversarial Learning of Realistic Neural Talking Head Modelscited by 284
  10. 2018Deep Video Portraitscited by 265
  11. 2018Animating Arbitrary Objects via Deep Motion Transfercited by 206
  12. 2019Few-shot Video-to-Video Synthesiscited by 196
11 more
  1. 2018X2Face: A network for controlling face generation by using images, audio, and pose codescited by 189
  2. 2018GANimation: Anatomically-aware Facial Animation from a Single Imagecited by 160
  3. 2020Fast Bi-layer Neural Synthesis of One-Shot Realistic Head Avatarscited by 116
  4. 2018Unsupervised Learning of Object Landmarks through Conditional Image Generationcited by 113
  5. 2020Neural Head Reenactment with Latent Pose Descriptorscited by 106
  6. 2019MarioNETte: Few-shot Face Reenactment Preserving Identity of Unseen Targetscited by 90
  7. 2018ReenactGAN: Learning to Reenact Faces via Boundary Transfercited by 85
  8. 2017On Face Segmentation, Face Swapping, and Face Perceptioncited by 71
  9. 2019ICface: Interpretable and Controllable Face Reenactment Using GANscited by 50
  10. 2020FACEGAN: Facial Attribute Controllable rEenactment GANcited by 32
  11. 2020Mesh Guided One-shot Face Reenactment using Graph Convolutional Networkscited by 30

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 2.

5 papers.

  1. 2022Expressive Talking Head Video Encoding in StyleGAN2 Latent-Spacecited by 4
  2. 2022A comprehensive survey on semantic facial attribute editing using generative adversarial networkscited by 3
  3. 2023MaskRenderer: 3D-Infused Multi-Mask Realistic Face Reenactmentcited by 3
  4. 2023CP-EB: Talking Face Generation with Controllable Pose and Eye Blinking Embeddingcited by 2
  5. 2022Semantic-aware One-shot Face Re-enactment with Dense Correspondence Estimationcited by 1