# Deep Deformation Network for Object Landmark Localization

arXiv: https://arxiv.org/abs/1605.01014 · HTML: https://mlsanity.com/paper/1605.01014/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 May 2016.

## Built on by (most cited first, 8 of 8)

- [Structure-Aware Motion Transfer with Deformable Anchor Model](https://mlsanity.com/paper/2204.05018/) (2022)
- [Supervision by Registration and Triangulation for Landmark Detection](https://mlsanity.com/paper/2101.09866/) (2021)
- [Unsupervised Part Segmentation through Disentangling Appearance and Shape](https://mlsanity.com/paper/2105.12405/) (2021)
- [Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection](https://mlsanity.com/paper/2305.01652/) (2023)
- [Unsupervised Landmark Detection Based Spatiotemporal Motion Estimation for 4D Dynamic Medical Images](https://mlsanity.com/paper/2109.14805/) (2021)
- [Scalable Semi-supervised Landmark Localization for X-ray Images using Few-shot Deep Adaptive Graph](https://mlsanity.com/paper/2104.14629/) (2021)
- [KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration](https://mlsanity.com/paper/2305.16437/) (2023)
- [Pretrained equivariant features improve unsupervised landmark discovery](https://mlsanity.com/paper/2104.02925/) (2021)

## Abstract (arXiv)

We propose a novel cascaded framework, namely deep deformation network (DDN), for localizing landmarks in non-rigid objects. The hallmarks of DDN are its incorporation of geometric constraints within a convolutional neural network (CNN) framework, ease and efficiency of training, as well as generality of application. A novel shape basis network (SBN) forms the first stage of the cascade, whereby landmarks are initialized by combining the benefits of CNN features and a learned shape basis to reduce the complexity of the highly nonlinear pose manifold. In the second stage, a point transformer network (PTN) estimates local deformation parameterized as thin-plate spline transformation for a finer refinement. Our framework does not incorporate either handcrafted features or part connectivity, which enables an end-to-end shape prediction pipeline during both training and testing. In contrast to prior cascaded networks for landmark localization that learn a mapping from feature space to landmark locations, we demonstrate that the regularization induced through geometric priors in the DDN makes it easier to train, yet produces superior results. The efficacy and generality of the architecture is demonstrated through state-of-the-art performances on several benchmarks for multiple tasks such as facial landmark localization, human body pose estimation and bird part localization.