Towards Accurate Human Motion Prediction via Iterative Refinement
- URL: http://arxiv.org/abs/2305.04443v1
- Date: Mon, 8 May 2023 03:43:51 GMT
- Title: Towards Accurate Human Motion Prediction via Iterative Refinement
- Authors: Jiarui Sun, Girish Chowdhary
- Abstract summary: FreqMRN takes into account both the kinematic structure of the human body and the temporal smoothness nature of motion.
We evaluate FreqMRN on several standard benchmark datasets, including Human3.6M, AMASS and 3DPW.
- Score: 9.910719309846128
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Human motion prediction aims to forecast an upcoming pose sequence given a
past human motion trajectory. To address the problem, in this work we propose
FreqMRN, a human motion prediction framework that takes into account both the
kinematic structure of the human body and the temporal smoothness nature of
motion. Specifically, FreqMRN first generates a fixed-size motion history
summary using a motion attention module, which helps avoid inaccurate motion
predictions due to excessively long motion inputs. Then, supervised by the
proposed spatial-temporal-aware, velocity-aware and global-smoothness-aware
losses, FreqMRN iteratively refines the predicted motion though the proposed
motion refinement module, which converts motion representations back and forth
between pose space and frequency space. We evaluate FreqMRN on several standard
benchmark datasets, including Human3.6M, AMASS and 3DPW. Experimental results
demonstrate that FreqMRN outperforms previous methods by large margins for both
short-term and long-term predictions, while demonstrating superior robustness.
Related papers
- MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning [57.078168638373874]
MotionWavelet is a human motion prediction framework that studies human motion patterns in the spatial-frequency domain.
Wavelet Diffusion Model learns a Wavelet Manifold by applying Wavelet Transformation on the motion data.
Wavelet Space Shaping Guidance mechanism refines the denoising process to improve conformity with the manifold structure.
arXiv Detail & Related papers (2024-11-25T22:09:19Z) - MDMP: Multi-modal Diffusion for supervised Motion Predictions with uncertainty [7.402769693163035]
This paper introduces a Multi-modal Diffusion model for Motion Prediction (MDMP)
It integrates skeletal data and textual descriptions of actions to generate refined long-term motion predictions with quantifiable uncertainty.
Our model consistently outperforms existing generative techniques in accurately predicting long-term motions.
arXiv Detail & Related papers (2024-10-04T18:49:00Z) - AdvMT: Adversarial Motion Transformer for Long-term Human Motion
Prediction [2.837740438355204]
We present the Adversarial Motion Transformer (AdvMT), a novel model that integrates a transformer-based motion encoder and a temporal continuity discriminator.
With adversarial training, our method effectively reduces the unwanted artifacts in predictions, thereby ensuring the learning of more realistic and fluid human motions.
arXiv Detail & Related papers (2024-01-10T09:15:50Z) - Motion-DVAE: Unsupervised learning for fast human motion denoising [18.432026846779372]
We introduce Motion-DVAE, a motion prior to capture the short-term dependencies of human motion.
Together with Motion-DVAE, we introduce an unsupervised learned denoising method unifying regression- and optimization-based approaches.
arXiv Detail & Related papers (2023-06-09T12:18:48Z) - Investigating Pose Representations and Motion Contexts Modeling for 3D
Motion Prediction [63.62263239934777]
We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task.
We propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction.
Our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency.
arXiv Detail & Related papers (2021-12-30T10:45:22Z) - Human Motion Prediction Using Manifold-Aware Wasserstein GAN [4.771549505875783]
We build a manifold-aware Wasserstein generative adversarial model that captures the temporal and spatial dependencies of human motion.
Our approach outperforms the state-of-the-art on CMU MoCap and Human 3.6M datasets.
arXiv Detail & Related papers (2021-05-18T17:56:10Z) - MotionRNN: A Flexible Model for Video Prediction with Spacetime-Varying
Motions [70.30211294212603]
This paper tackles video prediction from a new dimension of predicting spacetime-varying motions that are incessantly across both space and time.
We propose the MotionRNN framework, which can capture the complex variations within motions and adapt to spacetime-varying scenarios.
arXiv Detail & Related papers (2021-03-03T08:11:50Z) - Long Term Motion Prediction Using Keyposes [122.22758311506588]
We argue that, to achieve long term forecasting, predicting human pose at every time instant is unnecessary.
We call such poses "keyposes", and approximate complex motions by linearly interpolating between subsequent keyposes.
We show that learning the sequence of such keyposes allows us to predict very long term motion, up to 5 seconds in the future.
arXiv Detail & Related papers (2020-12-08T20:45:51Z) - Motion Prediction Using Temporal Inception Module [96.76721173517895]
We propose a Temporal Inception Module (TIM) to encode human motion.
Our framework produces input embeddings using convolutional layers, by using different kernel sizes for different input lengths.
The experimental results on standard motion prediction benchmark datasets Human3.6M and CMU motion capture dataset show that our approach consistently outperforms the state of the art methods.
arXiv Detail & Related papers (2020-10-06T20:26:01Z) - History Repeats Itself: Human Motion Prediction via Motion Attention [81.94175022575966]
We introduce an attention-based feed-forward network that explicitly leverages the observation that human motion tends to repeat itself.
In particular, we propose to extract motion attention to capture the similarity between the current motion context and the historical motion sub-sequences.
Our experiments on Human3.6M, AMASS and 3DPW evidence the benefits of our approach for both periodical and non-periodical actions.
arXiv Detail & Related papers (2020-07-23T02:12:27Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.