# Chirality Nets for Human Pose Regression

arXiv: https://arxiv.org/abs/1911.00029 · HTML: https://mlsanity.com/paper/1911.00029/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 30 of 31)

- [3D Human Pose Estimation with Spatial and Temporal Transformers](https://mlsanity.com/paper/2103.10455/) (2021)
- [MotionBERT: A Unified Perspective on Learning Human Motion Representations](https://mlsanity.com/paper/2210.06551/) (2022)
- [MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video](https://mlsanity.com/paper/2203.00859/) (2022)
- [Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats](https://mlsanity.com/paper/2212.14474/) (2022)
- [DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection](https://mlsanity.com/paper/2207.10758/) (2022)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations](https://mlsanity.com/paper/2110.04383/) (2021)
- [Ray3D: ray-based 3D human pose estimation for monocular absolute 3D localization](https://mlsanity.com/paper/2203.11471/) (2022)
- [Equivariance Discovery by Learned Parameter-Sharing](https://mlsanity.com/paper/2204.03640/) (2022)
- [Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional Networks](https://mlsanity.com/paper/2210.08001/) (2022)
- [Making Vision Transformers Truly Shift-Equivariant](https://mlsanity.com/paper/2305.16316/) (2023)
- [Truly Scale-Equivariant Deep Nets with Fourier Layers](https://mlsanity.com/paper/2311.02922/) (2023)
- [CrossFormer: Cross Spatio-Temporal Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2203.13387/) (2022)
- [Total Variation Optimization Layers for Computer Vision](https://mlsanity.com/paper/2204.03643/) (2022)
- [On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis](https://mlsanity.com/paper/2302.10433/) (2023)
- [Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room](https://mlsanity.com/paper/2108.11801/) (2021)
- [IVT: An End-to-End Instance-guided Video Transformer for 3D Pose Estimation](https://mlsanity.com/paper/2208.03431/) (2022)
- [Human Pose-based Estimation, Tracking and Action Recognition with Deep Learning: A Survey](https://mlsanity.com/paper/2310.13039/) (2023)
- [3D Skeleton-Based Action Recognition: A Review](https://mlsanity.com/paper/2506.00915/) (2025)
- [Motion Projection Consistency Based 3D Human Pose Estimation with Virtual Bones from Monocular Videos](https://mlsanity.com/paper/2106.14706/) (2021)
- [Group Downsampling with Equivariant Anti-aliasing](https://mlsanity.com/paper/2504.17258/) (2025)
- [Symmetry Understanding of 3D Shapes via Chirality Disentanglement](https://mlsanity.com/paper/2508.05505/) (2025)
- [Local Scale Equivariance with Latent Deep Equilibrium Canonicalizer](https://mlsanity.com/paper/2508.14187/) (2025)
- [CLIPSym: Delving into Symmetry Detection with CLIP](https://mlsanity.com/paper/2508.14197/) (2025)
- [Flow Matching for Probabilistic Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2601.16763/) (2026)
- [ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention](https://mlsanity.com/paper/2304.02147/) (2023)
- [Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers](https://mlsanity.com/paper/2401.16700/) (2024)
- [SplashNet: Split-and-Share Encoders for Accurate and Efficient Typing with Surface Electromyography](https://mlsanity.com/paper/2506.12356/) (2025)
- [Occlusion-Invariant Rotation-Equivariant Semi-Supervised Depth Based Cross-View Gait Pose Estimation](https://mlsanity.com/paper/2109.01397/) (2021)
- [Tunable Soft Equivariance with Guarantees](https://mlsanity.com/paper/2603.26657/) (2026)

## Abstract (arXiv)

We propose Chirality Nets, a family of deep nets that is equivariant to the "chirality transform," i.e., the transformation to create a chiral pair. Through parameter sharing, odd and even symmetry, we propose and prove variants of standard building blocks of deep nets that satisfy the equivariance property, including fully connected layers, convolutional layers, batch-normalization, and LSTM/GRU cells. The proposed layers lead to a more data efficient representation and a reduction in computation by exploiting symmetry. We evaluate chirality nets on the task of human pose regression, which naturally exploits the left/right mirroring of the human body. We study three pose regression tasks: 3D pose estimation from video, 2D pose forecasting, and skeleton based activity recognition. Our approach achieves/matches state-of-the-art results, with more significant gains on small datasets and limited-data settings.