mlsanityData to 7 Oct 2026

A New Spatio-Temporal Loss Function for 3D Motion Reconstruction and Extended Temporal Metrics for Motion Evaluation

arXiv 2210.08562 ↗First posted 16 Oct 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We propose a new loss function that we call Laplacian loss, based on spatio-temporal Laplacian representation of the motion as a graph. This loss function is intended to be used in training models for motion reconstruction through 3D human pose estimation from videos. It compares the differential coordinates of the joints obtained from the graph representation of the ground truth against the one of the estimation. We design a fully convolutional temporal network for motion reconstruction to achieve better temporal consistency of estimation. We use this generic model to study the impact of our proposed loss function on the benchmarks provided by Human3.6M. We also make use of various motion descriptors such as velocity, acceleration to make a thorough evaluation of the temporal consistency while comparing the results to some of the state-of-the-art solutions.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 15 of its 28 references that are in the map. First posted on arXiv 16 Oct 2022.

Builds on

15 of 28 references.

References · 15

  1. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  2. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  3. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  4. 20183D human pose estimation in video with temporal convolutions and semi-supervised trainingcited by 401
  5. 2019Semantic Graph Convolutional Networks for 3D Human Pose Regressioncited by 204
  6. 2022MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Videocited by 158
  7. 20191D Convolutional Neural Networks and Applications: A Surveycited by 152
  8. 20182D/3D Pose Estimation and Action Recognition using Multitask Deep Learningcited by 103
  9. 2019Unsupervised 3D Pose Estimation with Geometric Self-Supervisioncited by 95
  10. 2018LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Imagescited by 88
  11. 20183D Human Pose Estimation in the Wild by Adversarial Learningcited by 86
  12. 2020Motion Guided 3D Pose Estimation from Videoscited by 85
3 more
  1. 2019In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representationscited by 48
  2. 20223D Human Pose Estimation Using M"obius Graph Convolutional Networkscited by 6
  3. 2019Lifting 2d Human Pose to 3d : A Weakly Supervised Approachcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Web-Scale Collection of Video Data for 4D Animal Reconstructioncited by 8