mlsanityData to 7 Oct 2026

Forecasting Human Dynamics from Static Images

arXiv 1704.03432 ↗First posted 11 Apr 2017cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

This paper presents the first study on forecasting human dynamics from static images. The problem is to input a single RGB image and generate a sequence of upcoming human body poses in 3D. To address the problem, we propose the 3D Pose Forecasting Network (3D-PFNet). Our 3D-PFNet integrates recent advances on single-image human pose estimation and sequence prediction, and converts the 2D predictions into 3D space. We train our 3D-PFNet using a three-step training strategy to leverage a diverse source of training data, including image and video based human pose datasets and 3D motion capture (MoCap) data. We demonstrate competitive performance of our 3D-PFNet on 2D pose forecasting and 3D pose recovery through quantitative and qualitative results.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 11 Apr 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2019: 1; 2020: 0; 2021: 8; 2022: 2; 2023: 4; 2024: 0; 2025: 2.

17 papers.

Sort:

By area:

  1. 2021Synthesis of Compositional Animations from Textual Descriptionscited by 177
  2. 2021TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wildcited by 52
  3. 2019Imitation Learning for Human Pose Predictioncited by 44
  4. 2023Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchorscited by 34
  5. 2022A generic diffusion-based approach for 3D human pose prediction in the wildcited by 33
  6. 2021Image-to-Video Generation via 3D Facial Dynamicscited by 13
  7. 2023Toward Reliable Human Pose Forecasting with Uncertaintycited by 11
  8. 2023What Happened 3 Seconds Ago? Inferring the Past with Thermal Imagingcited by 7
  9. 2021Social Processes: Self-Supervised Meta-Learning over Conversational Groups for Forecasting Nonverbal Social Cuescited by 6
  10. 2021Exploring Versatile Prior for Human Motion via Motion Frequency Guidancecited by 5
  11. 2021Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networkscited by 3
  12. 2025mmPred: Radar-based Human Motion Prediction in the Darkcited by 3
5 more
  1. 2025Towards Consistent Long-Term Pose Generationcited by 1
  2. 2021Understanding in Artificial Intelligencecited by 0
  3. 2021LARNet: Latent Action Representation for Human Action Synthesiscited by 0
  4. 2022Unified Simulation, Perception, and Generation of Human Behaviorcited by 0
  5. 20233D Pose Nowcasting: Forecast the Future to Improve the Presentcited by 0