# LoopReg: Self-supervised Learning of Implicit Surface Correspondences, Pose and Shape for 3D Human Mesh Registration

arXiv: https://arxiv.org/abs/2010.12447 · HTML: https://mlsanity.com/paper/2010.12447/

## Key facts

- Cited by 108 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 30 of 108)

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapes](https://mlsanity.com/paper/2104.03953/) (2021)
- [SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks](https://mlsanity.com/paper/2104.03313/) (2021)
- [GauHuman: Articulated Gaussian Splatting from Monocular Human Videos](https://mlsanity.com/paper/2312.02973/) (2023)
- [ARAH: Animatable Volume Rendering of Articulated Human SDFs](https://mlsanity.com/paper/2210.10036/) (2022)
- [Animatable Neural Radiance Fields from Monocular RGB Videos](https://mlsanity.com/paper/2106.13629/) (2021)
- [LEAP: Learning Articulated Occupancy of People](https://mlsanity.com/paper/2104.06849/) (2021)
- [imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose](https://mlsanity.com/paper/2108.10842/) (2021)
- [Neural-GIF: Neural Generalized Implicit Functions for Animating People in Clothing](https://mlsanity.com/paper/2108.08807/) (2021)
- [EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild](https://mlsanity.com/paper/2308.16894/) (2023)
- [CHORE: Contact, Human and Object REconstruction from a single RGB image](https://mlsanity.com/paper/2204.02445/) (2022)
- [The Power of Points for Modeling Humans in Clothing](https://mlsanity.com/paper/2109.01137/) (2021)
- [SHERF: Generalizable Human NeRF from a Single Image](https://mlsanity.com/paper/2303.12791/) (2023)
- [Hi4D: 4D Instance Segmentation of Close Human Interaction](https://mlsanity.com/paper/2303.15380/) (2023)
- [MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images](https://mlsanity.com/paper/2106.11944/) (2021)
- [MobRecon: Mobile-Friendly Hand Mesh Reconstruction from Monocular Image](https://mlsanity.com/paper/2112.02753/) (2021)
- [SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements](https://mlsanity.com/paper/2104.07660/) (2021)
- [TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement](https://mlsanity.com/paper/2205.07982/) (2022)
- [Learning Neural Volumetric Representations of Dynamic Humans in Minutes](https://mlsanity.com/paper/2302.12237/) (2023)
- [DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras](https://mlsanity.com/paper/2105.00261/) (2021)
- [LISA: Learning Implicit Shape and Appearance of Hands](https://mlsanity.com/paper/2204.01695/) (2022)
- [Visibility Aware Human-Object Interaction Tracking from Single RGB Camera](https://mlsanity.com/paper/2303.16479/) (2023)
- [MPS-NeRF: Generalizable 3D Human Rendering from Multiview Images](https://mlsanity.com/paper/2203.16875/) (2022)
- [Shape registration in the time of transformers](https://mlsanity.com/paper/2106.13679/) (2021)
- [A Skeleton-Driven Neural Occupancy Representation for Articulated Hands](https://mlsanity.com/paper/2109.11399/) (2021)
- [Learning Implicit Templates for Point-Based Clothed Human Modeling](https://mlsanity.com/paper/2207.06955/) (2022)

## Abstract (arXiv)

We address the problem of fitting 3D human models to 3D scans of dressed humans. Classical methods optimize both the data-to-model correspondences and the human model parameters (pose and shape), but are reliable only when initialized close to the solution. Some methods initialize the optimization based on fully supervised correspondence predictors, which is not differentiable end-to-end, and can only process a single scan at a time. Our main contribution is LoopReg, an end-to-end learning framework to register a corpus of scans to a common 3D human model. The key idea is to create a self-supervised loop. A backward map, parameterized by a Neural Network, predicts the correspondence from every scan point to the surface of the human model. A forward map, parameterized by a human model, transforms the corresponding points back to the scan based on the model parameters (pose and shape), thus closing the loop. Formulating this closed loop is not straightforward because it is not trivial to force the output of the NN to be on the surface of the human model - outside this surface the human model is not even defined. To this end, we propose two key innovations. First, we define the canonical surface implicitly as the zero level set of a distance field in R3, which in contrast to morecommon UV parameterizations, does not require cutting the surface, does not have discontinuities, and does not induce distortion. Second, we diffuse the human model to the 3D domain R3. This allows to map the NN predictions forward,even when they slightly deviate from the zero level set. Results demonstrate that we can train LoopRegmainly self-supervised - following a supervised warm-start, the model becomes increasingly more accurate as additional unlabelled raw scans are processed. Our code and pre-trained models can be downloaded for research.