Existence Is Chaos: Enhancing 3D Human Motion Prediction with Uncertainty Consideration (2403.14104v1)
Abstract: Human motion prediction is consisting in forecasting future body poses from historically observed sequences. It is a longstanding challenge due to motion's complex dynamics and uncertainty. Existing methods focus on building up complicated neural networks to model the motion dynamics. The predicted results are required to be strictly similar to the training samples with L2 loss in current training pipeline. However, little attention has been paid to the uncertainty property which is crucial to the prediction task. We argue that the recorded motion in training data could be an observation of possible future, rather than a predetermined result. In addition, existing works calculate the predicted error on each future frame equally during training, while recent work indicated that different frames could play different roles. In this work, a novel computationally efficient encoder-decoder model with uncertainty consideration is proposed, which could learn proper characteristics for future frames by a dynamic function. Experimental results on benchmark datasets demonstrate that our uncertainty consideration approach has obvious advantages both in quantity and quality. Moreover, the proposed method could produce motion sequences with much better quality that avoids the intractable shaking artefacts. We believe our work could provide a novel perspective to consider the uncertainty quality for the general motion prediction task and encourage the studies in this field. The code will be available in https://github.com/Motionpre/Adaptive-Salient-Loss-SAGGB.
- A spatio-temporal transformer for 3d human motion prediction. In 2021 International Conference on 3D Vision (3DV), 565–574. IEEE.
- Deep representation learning for human motion prediction and classification. In Proceedings of the IEEE conference on computer vision and pattern recognition, 6158–6166.
- Learning progressive joint propagation for human motion prediction. In European Conference on Computer Vision, 226–242. Springer.
- MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 11467–11476.
- Uncertainty-aware Human Motion Prediction. arXiv preprint arXiv:2107.03575.
- Uncertainty-aware short-term motion prediction of traffic actors for autonomous driving. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2095–2104.
- Avatars grow legs: Generating smooth human motion from sparse tracking inputs with diffusion model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 481–490.
- Recurrent network models for human dynamics. In Proceedings of the IEEE international conference on computer vision, 4346–4354.
- Decompose More and Aggregate Better: Two Closer Looks at Frequency Representation Learning for Human Motion Prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6451–6460.
- Back to mlp: A simple baseline for human motion prediction. In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 4809–4819.
- Structural-rnn: Deep learning on spatio-temporal graphs. In Proceedings of the ieee conference on computer vision and pattern recognition, 5308–5317.
- Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition, 7482–7491.
- Anticipating human activities for reactive robotic response. In IROS, 2071. Tokyo.
- Convolutional sequence to sequence model for human dynamics. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 5226–5234.
- Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction. arXiv preprint arXiv:2208.00368.
- Dynamic multiscale graph neural networks for 3d skeleton based human motion prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 214–223.
- Efficient convolutional hierarchical autoencoder for human motion prediction. The Visual Computer, 35(6): 1143–1156.
- Trajectorycnn: a new spatio-temporal feature learning network for human motion prediction. IEEE Transactions on Circuits and Systems for Video Technology, 31(6): 2133–2146.
- Motion prediction using trajectory cues. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 13299–13308.
- Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6437–6446.
- History repeats itself: Human motion prediction via motion attention. In European Conference on Computer Vision, 474–489. Springer.
- Weakly-supervised action transition learning for stochastic human motion prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8151–8160.
- Learning trajectory dependencies for human motion prediction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 9489–9497.
- A survey of motion planning and control techniques for self-driving urban vehicles. IEEE Transactions on intelligent vehicles, 1(1): 33–55.
- Quaternet: A quaternion-based recurrent model for human motion. arXiv preprint arXiv:1805.06485.
- Space-time-separable graph convolutional network for pose forecasting. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 11209–11218.
- Motion prediction via joint dependency modeling in phase space. In Proceedings of the 29th ACM International Conference on Multimedia, 713–721.
- Auxiliary tasks benefit 3d skeleton-based human motion prediction. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 9509–9520.
- Dlow: Diversifying latent flows for diverse human motion prediction. In Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part IX 16, 346–364. Springer.
- Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 6447–6456.