# Pixel-in-Pixel Net: Towards Efficient Facial Landmark Detection in the Wild

arXiv: https://arxiv.org/abs/2003.03771 · HTML: https://mlsanity.com/paper/2003.03771/

## Key facts

- Cited by 74 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2020.

## Built on by (most cited first, 30 of 74)

- [AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding](https://mlsanity.com/paper/2405.03121/) (2024)
- [Avat3r: Large Animatable Gaussian Reconstruction Model for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2502.20220/) (2025)
- [POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition](https://mlsanity.com/paper/2204.04083/) (2022)
- [STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection](https://mlsanity.com/paper/2306.02763/) (2023)
- [DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars](https://mlsanity.com/paper/2311.18635/) (2023)
- [MonoNPHM: Dynamic Head Reconstruction from Monocular Videos](https://mlsanity.com/paper/2312.06740/) (2023)
- [FaceXFormer: A Unified Transformer for Facial Analysis](https://mlsanity.com/paper/2403.12960/) (2024)
- [Towards Accurate Facial Landmark Detection via Cascaded Transformers](https://mlsanity.com/paper/2208.10808/) (2022)
- [High-Res Facial Appearance Capture from Polarized Smartphone Images](https://mlsanity.com/paper/2212.01160/) (2022)
- [Fast Facial Landmark Detection and Applications: A Survey](https://mlsanity.com/paper/2101.10808/) (2021)
- [Cloning Outfits from Real-World Images to 3D Characters for Generalizable Person Re-Identification](https://mlsanity.com/paper/2204.02611/) (2022)
- [DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer](https://mlsanity.com/paper/2406.09622/) (2024)
- [HIH: Towards More Accurate Face Alignment via Heatmap in Heatmap](https://mlsanity.com/paper/2104.03100/) (2021)
- [RePFormer: Refinement Pyramid Transformer for Robust Facial Landmark Detection](https://mlsanity.com/paper/2207.03917/) (2022)
- [Faceptor: A Generalist Model for Face Perception](https://mlsanity.com/paper/2403.09500/) (2024)
- [DistilPose: Tokenized Pose Regression with Heatmap Distillation](https://mlsanity.com/paper/2303.02455/) (2023)
- [RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance](https://mlsanity.com/paper/2405.14677/) (2024)
- [FlexAvatar: Learning Complete 3D Head Avatars with Partial Supervision](https://mlsanity.com/paper/2512.15599/) (2025)
- [RSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printer](https://mlsanity.com/paper/2206.12590/) (2022)
- [Personalized Video Relighting With an At-Home Light Stage](https://mlsanity.com/paper/2311.08843/) (2023)
- [EDM: Efficient Deep Feature Matching](https://mlsanity.com/paper/2503.05122/) (2025)
- [A Chain of Diagnosis Framework for Accurate and Explainable Radiology Report Generation](https://mlsanity.com/paper/2508.09566/) (2025)
- [Generalizable Face Landmarking Guided by Conditional Face Warping](https://mlsanity.com/paper/2404.12322/) (2024)
- [VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstruction](https://mlsanity.com/paper/2409.09740/) (2024)
- [Heatmap-based 2D Landmark Detection with a Varying Number of Landmarks](https://mlsanity.com/paper/2101.02737/) (2021)
- [Unsupervised Domain Adaptation for Anatomical Landmark Detection](https://mlsanity.com/paper/2308.13286/) (2023)
- [Proto-Former: Unified Facial Landmark Detection by Prototype Transformer](https://mlsanity.com/paper/2510.15338/) (2025)
- [FastGHA: Generalized Few-Shot 3D Gaussian Head Avatars with Real-Time Animation](https://mlsanity.com/paper/2601.13837/) (2026)
- [When Liebig's Barrel Meets Facial Landmark Detection: A Practical Model](https://mlsanity.com/paper/2105.13150/) (2021)
- [KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration](https://mlsanity.com/paper/2305.16437/) (2023)

## Abstract (arXiv)

Recently, heatmap regression models have become popular due to their superior performance in locating facial landmarks. However, three major problems still exist among these models: (1) they are computationally expensive; (2) they usually lack explicit constraints on global shapes; (3) domain gaps are commonly present. To address these problems, we propose Pixel-in-Pixel Net (PIPNet) for facial landmark detection. The proposed model is equipped with a novel detection head based on heatmap regression, which conducts score and offset predictions simultaneously on low-resolution feature maps. By doing so, repeated upsampling layers are no longer necessary, enabling the inference time to be largely reduced without sacrificing model accuracy. Besides, a simple but effective neighbor regression module is proposed to enforce local constraints by fusing predictions from neighboring landmarks, which enhances the robustness of the new detection head. To further improve the cross-domain generalization capability of PIPNet, we propose self-training with curriculum. This training strategy is able to mine more reliable pseudo-labels from unlabeled data across domains by starting with an easier task, then gradually increasing the difficulty to provide more precise labels. Extensive experiments demonstrate the superiority of PIPNet, which obtains state-of-the-art results on three out of six popular benchmarks under the supervised setting. The results on two cross-domain test sets are also consistently improved compared to the baselines. Notably, our lightweight version of PIPNet runs at 35.7 FPS and 200 FPS on CPU and GPU, respectively, while still maintaining a competitive accuracy to state-of-the-art methods. The code of PIPNet is available at https://github.com/jhb86253817/PIPNet.