# Deep Implicit Templates for 3D Shape Representation

arXiv: https://arxiv.org/abs/2011.14565 · HTML: https://mlsanity.com/paper/2011.14565/

## Key facts

- Cited by 86 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2020.

## Built on by (most cited first, 30 of 86)

- [Structured Local Radiance Fields for Human Avatar Modeling](https://mlsanity.com/paper/2203.14478/) (2022)
- [Towards Implicit Text-Guided 3D Shape Generation](https://mlsanity.com/paper/2203.14622/) (2022)
- [ImFace: A Nonlinear 3D Morphable Face Model with Implicit Neural Representations](https://mlsanity.com/paper/2203.14510/) (2022)
- [CaDeX: Learning Canonical Deformation Coordinate Space for Dynamic Surface Representation via Neural Homeomorphism](https://mlsanity.com/paper/2203.16529/) (2022)
- [Learning Implicit Templates for Point-Based Clothed Human Modeling](https://mlsanity.com/paper/2207.06955/) (2022)
- [Learning Deep Implicit Functions for 3D Shapes with Dynamic Code Clouds](https://mlsanity.com/paper/2203.14048/) (2022)
- [Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesis](https://mlsanity.com/paper/2204.11798/) (2022)
- [Registering Explicit to Implicit: Towards High-Fidelity Garment mesh Reconstruction from Single Images](https://mlsanity.com/paper/2203.15007/) (2022)
- [Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow](https://mlsanity.com/paper/2203.08652/) (2022)
- [Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes](https://mlsanity.com/paper/2206.04942/) (2022)
- [Instant Multi-View Head Capture through Learnable Registration](https://mlsanity.com/paper/2306.07437/) (2023)
- [Deformable Neural Radiance Fields using RGB and Event Cameras](https://mlsanity.com/paper/2309.08416/) (2023)
- [EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points](https://mlsanity.com/paper/2212.04247/) (2022)
- [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://mlsanity.com/paper/2205.06267/) (2022)
- [Neural Shape Deformation Priors](https://mlsanity.com/paper/2210.05616/) (2022)
- [AvatarCap: Animatable Avatar Conditioned Monocular Human Volumetric Capture](https://mlsanity.com/paper/2207.02031/) (2022)
- [InterTrack: Tracking Human Object Interaction without Object Templates](https://mlsanity.com/paper/2408.13953/) (2024)
- [Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space](https://mlsanity.com/paper/2207.04161/) (2022)
- [CloSET: Modeling Clothed Humans on Continuous Surface with Explicit Template Decomposition](https://mlsanity.com/paper/2304.03167/) (2023)
- [Medical Image Registration via Neural Fields](https://mlsanity.com/paper/2206.03111/) (2022)
- [NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching](https://mlsanity.com/paper/2301.05839/) (2023)
- [SDF4CHD: Generative Modeling of Cardiac Anatomies with Congenital Heart Defects](https://mlsanity.com/paper/2311.00332/) (2023)
- [Spectral-wise Implicit Neural Representation for Hyperspectral Image Reconstruction](https://mlsanity.com/paper/2312.01061/) (2023)
- [Partial-to-Partial Shape Matching with Geometric Consistency](https://mlsanity.com/paper/2404.12209/) (2024)
- [RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo](https://mlsanity.com/paper/2307.10233/) (2023)
- [4D Myocardium Reconstruction with Decoupled Motion and Shape Model](https://mlsanity.com/paper/2308.14083/) (2023)
- [Hierarchical Neural Semantic Representation for 3D Semantic Correspondence](https://mlsanity.com/paper/2509.17431/) (2025)
- [Implicit field supervision for robust non-rigid shape matching](https://mlsanity.com/paper/2203.07694/) (2022)
- [T2TD: Text-3D Generation Model based on Prior Knowledge Guidance](https://mlsanity.com/paper/2305.15753/) (2023)
- [An Implicit Parametric Morphable Dental Model](https://mlsanity.com/paper/2211.11402/) (2022)

## Abstract (arXiv)

Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power. However, unlike polygon mesh-based templates, it remains a challenge to reason dense correspondences or other semantic relationships across shapes represented by DIFs, which limits its applications in texture transfer, shape analysis and so on. To overcome this limitation and also make DIFs more interpretable, we propose Deep Implicit Templates, a new 3D shape representation that supports explicit correspondence reasoning in deep implicit representations. Our key idea is to formulate DIFs as conditional deformations of a template implicit function. To this end, we propose Spatial Warping LSTM, which decomposes the conditional spatial transformation into multiple affine transformations and guarantees generalization capability. Moreover, the training loss is carefully designed in order to achieve high reconstruction accuracy while learning a plausible template with accurate correspondences in an unsupervised manner. Experiments show that our method can not only learn a common implicit template for a collection of shapes, but also establish dense correspondences across all the shapes simultaneously without any supervision.