Bootstrapping Human Optical Flow and Pose
Not on the map. Why?
Abstract (arXiv)
We propose a bootstrapping framework to enhance human optical flow and pose. We show that, for videos involving humans in scenes, we can improve both the optical flow and the pose estimation quality of humans by considering the two tasks at the same time. We enhance optical flow estimates by fine-tuning them to fit the human pose estimates and vice versa. In more detail, we optimize the pose and optical flow networks to, at inference time, agree with each other. We show that this results in state-of-the-art results on the Human 3.6M and 3D Poses in the Wild datasets, as well as a human-related subset of the Sintel dataset, both in terms of pose estimation accuracy and the optical flow accuracy at human joint locations. Code available at https://github.com/ubc-vision/bootstrapping-human-optical-flow-and-pose
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 27 Oct 2022.
Builds on
33 of 44 references.
References · 33
- 2017Attention Is All You Needcited by 60,361
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
- 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
- 2017Deep Image Priorcited by 1,098
- 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,059
- 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
- 2017End-to-end Recovery of Human Shape and Posecited by 885
- 2015A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimationcited by 881
- 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 784
- 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
- 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
21 more
- 2016Optical Flow Estimation using a Spatial Pyramid Networkcited by 424
- 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 418
- 2017A simple yet effective baseline for 3d human pose estimationcited by 401
- 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 337
- 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
- 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
- 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 224
- 2016Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Posecited by 221
- 2020STAR: Sparse Trained Articulated Human Body Regressorcited by 194
- 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
- 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
- 2019Exploiting temporal context for 3D human pose estimation in the wildcited by 110
- 2017Exploiting temporal information for 3D pose estimationcited by 89
- 20163D Human Pose Estimation from a Single Image via Distance Matrix Regressioncited by 73
- 2015Flowing ConvNets for Human Pose Estimation in Videoscited by 55
- 2021Deep Dual Consecutive Network for Human Pose Estimationcited by 51
- 2021EventHPE: Event-based 3D Human Pose and Shape Estimationcited by 42
- 2019Learning Multi-Human Optical Flowcited by 26
- 2016A Simple, Fast and Highly-Accurate Algorithm to Recover 3D Shape from 2D Landmarks on a Single Imagecited by 8
- 2015Deep End2End Voxel2Voxel Predictioncited by 7
- 2018Learning Human Optical Flowcited by 7
Built on by
Citing papers per year: 2024: 1.
1 paper.