mlsanityData to 14 Oct 2026

Video Inference for Human Mesh Recovery with Vision Transformer

arXiv 2507.08981 ↗First posted 11 Jul 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Human Mesh Recovery (HMR) from an image is a challenging problem because of the inherent ambiguity of the task. Existing HMR methods utilized either temporal information or kinematic relationships to achieve higher accuracy, but there is no method using both. Hence, we propose "Video Inference for Human Mesh Recovery with Vision Transformer (HMR-ViT)" that can take into account both temporal and kinematic information. In HMR-ViT, a Temporal-kinematic Feature Image is constructed using feature vectors obtained from video frames by an image encoder. When generating the feature image, we use a Channel Rearranging Matrix (CRM) so that similar kinematic features could be located spatially close together. The feature image is then further encoded using Vision Transformer, and the SMPL pose and shape parameters are finally inferred using a regression network. Extensive evaluation on the 3DPW and Human3.6M datasets indicates that our method achieves a competitive performance in HMR.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 11 Jul 2025.

Builds on

32 of 42 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  7. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  8. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,064
  9. 2017End-to-end Recovery of Human Shape and Posecited by 885
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  11. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  12. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
20 more
  1. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 494
  2. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
  3. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 403
  4. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  5. 2018Learning 3D Human Dynamics from Videocited by 316
  6. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  7. 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
  8. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  9. 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
  10. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  11. 2017PoseTrack: A Benchmark for Human Pose Estimation and Trackingcited by 173
  12. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  13. 2018BodyNet: Volumetric Inference of 3D Human Body Shapescited by 141
  14. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  15. 20203D Human Motion Estimation via Motion Compression and Refinementcited by 98
  16. 2017Self-supervised Learning of Motion Capturecited by 97
  17. 2019TexturePose: Supervising Human Mesh Estimation with Texture Consistencycited by 53
  18. 2019Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wildcited by 38
  19. 2020Appearance Consensus Driven Self-Supervised Human Mesh Recoverycited by 27
  20. 2021Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learningcited by 17

Built on by

Not cited yet.