# Pose-Robust Face Recognition via Deep Residual Equivariant Mapping

arXiv: https://arxiv.org/abs/1803.00839 · HTML: https://mlsanity.com/paper/1803.00839/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Mar 2018.

## Built on by (most cited first, 28 of 28)

- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [SynFace: Face Recognition with Synthetic Data](https://mlsanity.com/paper/2108.07960/) (2021)
- [Open-World Entity Segmentation](https://mlsanity.com/paper/2107.14228/) (2021)
- [REALY: Rethinking the Evaluation of 3D Face Reconstruction](https://mlsanity.com/paper/2203.09729/) (2022)
- [MyStyle: A Personalized Generative Prior](https://mlsanity.com/paper/2203.17272/) (2022)
- [H3WB: Human3.6M 3D WholeBody Dataset and Benchmark](https://mlsanity.com/paper/2211.15692/) (2022)
- [HiFace: High-Fidelity 3D Face Reconstruction by Learning Static and Dynamic Details](https://mlsanity.com/paper/2303.11225/) (2023)
- [LARNet: Lie Algebra Residual Network for Face Recognition](https://mlsanity.com/paper/2103.08147/) (2021)
- [My3DGen: A Scalable Personalized 3D Generative Model](https://mlsanity.com/paper/2307.05468/) (2023)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [PAM: Pose Attention Module for Pose-Invariant Face Recognition](https://mlsanity.com/paper/2111.11940/) (2021)
- [Median Pixel Difference Convolutional Network for Robust Face Recognition](https://mlsanity.com/paper/2205.15867/) (2022)
- [Information Maximization for Extreme Pose Face Recognition](https://mlsanity.com/paper/2209.03456/) (2022)
- [Pose Attention-Guided Profile-to-Frontal Face Recognition](https://mlsanity.com/paper/2209.07001/) (2022)
- [EMface: Detecting Hard Faces by Exploring Receptive Field Pyraminds](https://mlsanity.com/paper/2105.10104/) (2021)
- [Attention-guided Progressive Mapping for Profile Face Recognition](https://mlsanity.com/paper/2106.14124/) (2021)
- [Learning Domain and Pose Invariance for Thermal-to-Visible Face Recognition](https://mlsanity.com/paper/2211.09350/) (2022)
- [Fast and Reliable Probabilistic Face Embeddings in the Wild](https://mlsanity.com/paper/2102.04075/) (2021)
- [2D-3D Attention and Entropy for Pose Robust 2D Facial Recognition](https://mlsanity.com/paper/2505.09073/) (2025)
- [Harnessing Geometric Constraints from Emotion Labels to improve Face Verification](https://mlsanity.com/paper/2103.03862/) (2021)
- [Profile to Frontal Face Recognition in the Wild Using Coupled Conditional GAN](https://mlsanity.com/paper/2107.13742/) (2021)
- [How Self-Supervised Learning Can be Used for Fine-Grained Head Pose Estimation?](https://mlsanity.com/paper/2108.04893/) (2021)
- [Boosting of Head Pose Estimation by Knowledge Distillation](https://mlsanity.com/paper/2108.09183/) (2021)
- [Location-guided Head Pose Estimation for Fisheye Image](https://mlsanity.com/paper/2402.18320/) (2024)
- [Cross-Spectral Attention for Unsupervised RGB-IR Face Verification and Person Re-identification](https://mlsanity.com/paper/2411.19215/) (2024)
- [Pose-invariant face recognition via feature-space pose frontalization](https://mlsanity.com/paper/2505.16412/) (2025)
- [Towards Large-Scale Pose-Invariant Face Recognition Using Face Defrontalization](https://mlsanity.com/paper/2506.04496/) (2025)
- [The Good, the Better, and the Best: Improving the Discriminability of Face Embeddings through Attribute-aware Learning](https://mlsanity.com/paper/2603.15062/) (2026)

## Abstract (arXiv)

Face recognition achieves exceptional success thanks to the emergence of deep learning. However, many contemporary face recognition models still perform relatively poor in processing profile faces compared to frontal faces. A key reason is that the number of frontal and profile training faces are highly imbalanced - there are extensively more frontal training samples compared to profile ones. In addition, it is intrinsically hard to learn a deep representation that is geometrically invariant to large pose variations. In this study, we hypothesize that there is an inherent mapping between frontal and profile faces, and consequently, their discrepancy in the deep representation space can be bridged by an equivariant mapping. To exploit this mapping, we formulate a novel Deep Residual EquivAriant Mapping (DREAM) block, which is capable of adaptively adding residuals to the input deep representation to transform a profile face representation to a canonical pose that simplifies recognition. The DREAM block consistently enhances the performance of profile face recognition for many strong deep networks, including ResNet models, without deliberately augmenting training data of profile faces. The block is easy to use, light-weight, and can be implemented with a negligible computational overhead.