# Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images

arXiv: https://arxiv.org/abs/2003.08124 · HTML: https://mlsanity.com/paper/2003.08124/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2020.

## Built on by (most cited first, 30 of 37)

- [Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation](https://mlsanity.com/paper/2104.11116/) (2021)
- [Audio-Driven Emotional Video Portraits](https://mlsanity.com/paper/2104.07452/) (2021)
- [MoFaNeRF: Morphable Facial Neural Radiance Field](https://mlsanity.com/paper/2112.02308/) (2021)
- [Learning in Audio-visual Context: A Review, Analysis, and New Perspective](https://mlsanity.com/paper/2208.09579/) (2022)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [Finding Directions in GAN's Latent Space for Neural Face Reenactment](https://mlsanity.com/paper/2202.00046/) (2022)
- [View Generalization for Single Image Textured 3D Models](https://mlsanity.com/paper/2106.06533/) (2021)
- [LARNet: Lie Algebra Residual Network for Face Recognition](https://mlsanity.com/paper/2103.08147/) (2021)
- [High-fidelity Face Tracking for AR/VR via Deep Lighting Adaptation](https://mlsanity.com/paper/2103.15876/) (2021)
- [Learning-by-Novel-View-Synthesis for Full-Face Appearance-Based 3D Gaze Estimation](https://mlsanity.com/paper/2201.07927/) (2022)
- [Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors](https://mlsanity.com/paper/2403.11503/) (2024)
- [Injecting 3D Perception of Controllable NeRF-GAN into StyleGAN for Editable Portrait Image Synthesis](https://mlsanity.com/paper/2207.10257/) (2022)
- [GAN2X: Non-Lambertian Inverse Rendering of Image GANs](https://mlsanity.com/paper/2206.09244/) (2022)
- [POCE: Pose-Controllable Expression Editing](https://mlsanity.com/paper/2304.08938/) (2023)
- [PoseFace: Pose-Invariant Features and Pose-Adaptive Loss for Face Recognition](https://mlsanity.com/paper/2107.11721/) (2021)
- [3D Face Reconstruction: the Road to Forensics](https://mlsanity.com/paper/2309.11357/) (2023)
- [FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifold](https://mlsanity.com/paper/2109.09378/) (2021)
- [Efficient Virtual View Selection for 3D Hand Pose Estimation](https://mlsanity.com/paper/2203.15458/) (2022)
- [One-shot Neural Face Reenactment via Finding Directions in GAN's Latent Space](https://mlsanity.com/paper/2402.03553/) (2024)
- [Expression-preserving face frontalization improves visually assisted speech processing](https://mlsanity.com/paper/2204.02810/) (2022)
- [3D Face Reconstruction for Forensic Recognition -- A Survey](https://mlsanity.com/paper/2303.11164/) (2023)
- [Exploiting Multiple Representations: 3D Face Biometrics Fusion with Application to Surveillance](https://mlsanity.com/paper/2504.18886/) (2025)
- [Weakly-Supervised Photo-realistic Texture Generation for 3D Face Reconstruction](https://mlsanity.com/paper/2106.08148/) (2021)
- [The impact of removing head movements on audio-visual speech enhancement](https://mlsanity.com/paper/2202.00538/) (2022)
- [One-Shot Face Reenactment on Megapixels](https://mlsanity.com/paper/2205.13368/) (2022)
- [Domain-Adaptive Full-Face Gaze Estimation via Novel-View-Synthesis and Feature Disentanglement](https://mlsanity.com/paper/2305.16140/) (2023)
- [Exploring 3D Face Reconstruction and Fusion Methods for Face Verification: A Case-Study in Video Surveillance](https://mlsanity.com/paper/2409.10481/) (2024)
- [Generate and Edit Your Own Character in a Canonical View](https://mlsanity.com/paper/2205.02974/) (2022)
- [Geometrically Adaptive Dictionary Attack on Face Recognition](https://mlsanity.com/paper/2111.04371/) (2021)
- [Learning to Deblur and Rotate Motion-Blurred Faces](https://mlsanity.com/paper/2112.07599/) (2021)

## Abstract (arXiv)

Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods. The current generative models heavily rely on datasets with multi-view images of the same person. Thus, their generated results are restricted by the scale and domain of the data source. To overcome these challenges, we propose a novel unsupervised framework that can synthesize photo-realistic rotated faces using only single-view image collections in the wild. Our key insight is that rotating faces in the 3D space back and forth, and re-rendering them to the 2D plane can serve as a strong self-supervision. We leverage the recent advances in 3D face modeling and high-resolution GAN to constitute our building blocks. Since the 3D rotation-and-render on faces can be applied to arbitrary angles without losing details, our approach is extremely suitable for in-the-wild scenarios (i.e. no paired data are available), where existing methods fall short. Extensive experiments demonstrate that our approach has superior synthesis quality as well as identity preservation over the state-of-the-art methods, across a wide range of poses and domains. Furthermore, we validate that our rotate-and-render framework naturally can act as an effective data augmentation engine for boosting modern face recognition systems even on strong baseline models.