# DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

arXiv: https://arxiv.org/abs/1803.02188 · HTML: https://mlsanity.com/paper/1803.02188/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2018.

## Built on by (most cited first, 30 of 32)

- [EMOCA: Emotion Driven Monocular Face Capture and Animation](https://mlsanity.com/paper/2204.11312/) (2022)
- [Fake It Till You Make It: Face analysis in the wild using synthetic data alone](https://mlsanity.com/paper/2109.15102/) (2021)
- [Towards Metrical Reconstruction of Human Faces](https://mlsanity.com/paper/2204.06607/) (2022)
- [SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis](https://mlsanity.com/paper/2404.04104/) (2024)
- [Real-time Pose and Shape Reconstruction of Two Interacting Hands With a Single Depth Camera](https://mlsanity.com/paper/2106.08059/) (2021)
- [3D face reconstruction with dense landmarks](https://mlsanity.com/paper/2204.02776/) (2022)
- [Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2407.07532/) (2024)
- [Instant Multi-View Head Capture through Learnable Registration](https://mlsanity.com/paper/2306.07437/) (2023)
- [FNeVR: Neural Volume Rendering for Face Animation](https://mlsanity.com/paper/2209.10340/) (2022)
- [3D Face Tracking from 2D Video through Iterative Dense UV to Image Flow](https://mlsanity.com/paper/2404.09819/) (2024)
- [PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning](https://mlsanity.com/paper/2105.05643/) (2021)
- [Detailed Avatar Recovery from Single Image](https://mlsanity.com/paper/2108.02931/) (2021)
- [3DGazeNet: Generalizing Gaze Estimation with Weak-Supervision from Synthetic Views](https://mlsanity.com/paper/2212.02997/) (2022)
- [UltraPose: Synthesizing Dense Pose with 1 Billion Points by Human-body Decoupling 3D Model](https://mlsanity.com/paper/2110.15267/) (2021)
- [MultiMorph: On-demand Atlas Construction](https://mlsanity.com/paper/2504.00247/) (2025)
- [A Review on Visual Privacy Preservation Techniques for Active and Assisted Living](https://mlsanity.com/paper/2112.09422/) (2021)
- [Contrastive Attention Network with Dense Field Estimation for Face Completion](https://mlsanity.com/paper/2112.10310/) (2021)
- [DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment](https://mlsanity.com/paper/2305.11522/) (2023)
- [SPARK: Self-supervised Personalized Real-time Monocular Face Capture](https://mlsanity.com/paper/2409.07984/) (2024)
- [Perspective Reconstruction of Human Faces by Joint Mesh and Landmark Regression](https://mlsanity.com/paper/2208.07142/) (2022)
- [Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos](https://mlsanity.com/paper/2205.02361/) (2022)
- [3D Dense Face Alignment with Fused Features by Aggregating CNNs and GCNs](https://mlsanity.com/paper/2203.04643/) (2022)
- [Semi-supervised Dense Keypoints Using Unlabeled Multiview Images](https://mlsanity.com/paper/2109.09299/) (2021)
- [A lightweight 3D dense facial landmark estimation model from position map data](https://mlsanity.com/paper/2308.15170/) (2023)
- [DenseSeg: Joint Learning for Semantic Segmentation and Landmark Detection Using Dense Image-to-Shape Representation](https://mlsanity.com/paper/2405.19746/) (2024)
- [Registration-Free Learnable Multi-View Capture of Faces in Dense Semantic Correspondence](https://mlsanity.com/paper/2605.01450/) (2026)
- [Learning Dense Correspondence from Synthetic Environments](https://mlsanity.com/paper/2203.12919/) (2022)
- [Inferring Implicit 3D Representations from Human Figures on Pictorial Maps](https://mlsanity.com/paper/2209.02385/) (2022)
- [OFER: Occluded Face Expression Reconstruction](https://mlsanity.com/paper/2410.21629/) (2024)
- [Human Pose-Constrained UV Map Estimation](https://mlsanity.com/paper/2501.08815/) (2025)

## Abstract (arXiv)

In this work we use deep learning to establish dense correspondences between a 3D object model and an image "in the wild". We introduce "DenseReg", a fully-convolutional neural network (F-CNN) that densely regresses at every foreground pixel a pair of U-V template coordinates in a single feedforward pass. To train DenseReg we construct a supervision signal by combining 3D deformable model fitting and 2D landmark annotations. We define the regression task in terms of the intrinsic, U-V coordinates of a 3D deformable model that is brought into correspondence with image instances at training time. A host of other object-related tasks (e.g. part segmentation, landmark localization) are shown to be by-products of this task, and to largely improve thanks to its introduction. We obtain highly-accurate regression results by combining ideas from semantic segmentation with regression networks, yielding a 'quantized regression' architecture that first obtains a quantized estimate of position through classification, and refines it through regression of the residual. We show that such networks can boost the performance of existing state-of-the-art systems for pose estimation. Firstly, we show that our system can serve as an initialization for Statistical Deformable Models, as well as an element of cascaded architectures that jointly localize landmarks and estimate dense correspondences. We also show that the obtained dense correspondence can act as a source of 'privileged information' that complements and extends the pure landmark-level annotations, accelerating and improving the training of pose estimation networks. We report state-of-the-art performance on the challenging 300W benchmark for facial landmark localization and on the MPII and LSP datasets for human pose estimation.