mlsanityData to 14 Oct 2026

Self-Supervised 3D Human Pose Estimation in Static Video Via Neural Rendering

arXiv 2210.04514 ↗First posted 10 Oct 2022cs.CV cs.AI cs.GRcited by 2

Not on the map. Why?

Abstract (arXiv)

Inferring 3D human pose from 2D images is a challenging and long-standing problem in the field of computer vision with many applications including motion capture, virtual reality, surveillance or gait analysis for sports and medicine. We present preliminary results for a method to estimate 3D pose from 2D video containing a single person and a static background without the need for any manual landmark annotations. We achieve this by formulating a simple yet effective self-supervision task: our model is required to reconstruct a random frame of a video given a frame from another timepoint and a rendered image of a transformed human shape template. Crucially for optimisation, our ray casting based rendering pipeline is fully differentiable, enabling end to end training solely based on the reconstruction task.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 36 references that are in the map. First posted on arXiv 10 Oct 2022.

Builds on

24 of 36 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,299
  4. 2017End-to-end Recovery of Human Shape and Posecited by 885
  5. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  6. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  7. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  8. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  9. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  10. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  11. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  12. 2019Neural Volumes: Learning Dynamic Renderable Volumes from Imagescited by 173
12 more
  1. 2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
  2. 2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
  3. 2019Cross View Fusion for 3D Human Pose Estimationcited by 90
  4. 2017Exploiting temporal information for 3D pose estimationcited by 89
  5. 2018Unsupervised Geometry-Aware Representation for 3D Human Pose Estimationcited by 73
  6. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  7. 2020Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesiscited by 44
  8. 2021Unsupervised Human Pose Estimation through Transforming Shape Templatescited by 26
  9. 2018Rethinking Pose in 3D: Multi-stage Refinement and Recovery for Markerless Motion Capturecited by 17
  10. 2017Recurrent 3D Pose Sequence Machinescited by 12
  11. 2017A Dual-Source Approach for 3D Human Pose Estimation from a Single Imagecited by 7
  12. 2021Learning Foreground-Background Segmentation from Improved Layered GANscited by 7

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024MEGA: Masked Generative Autoencoder for Human Mesh Recoverycited by 14
  2. 2025SSPINNpose: A Self-Supervised PINN for Inertial Pose and Dynamics Estimationcited by 1