# Pixel2ISDF: Implicit Signed Distance Fields based Human Body Model from Multi-view and Multi-pose Images

arXiv: https://arxiv.org/abs/2212.02765 · HTML: https://mlsanity.com/paper/2212.02765/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 6 Dec 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [VarifocalNet: An IoU-aware Dense Object Detector](https://mlsanity.com/paper/2008.13367/) (2020)
- [Monocular Expressive Body Regression through Body-Driven Attention](https://mlsanity.com/paper/2008.09062/) (2020)
- [SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video](https://mlsanity.com/paper/2201.12792/) (2022)
- [DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor](https://mlsanity.com/paper/1804.06023/) (2018)
- [MatteFormer: Transformer-Based Image Matting via Prior-Tokens](https://mlsanity.com/paper/2203.15662/) (2022)
- [Iso-Points: Optimizing Neural Implicit Surfaces with Hybrid Representations](https://mlsanity.com/paper/2012.06434/) (2020)
- [NormalGAN: Learning Detailed 3D Human from a Single RGB-D Image](https://mlsanity.com/paper/2007.15340/) (2020)

## Abstract (arXiv)

In this report, we focus on reconstructing clothed humans in the canonical space given multiple views and poses of a human as the input. To achieve this, we utilize the geometric prior of the SMPLX model in the canonical space to learn the implicit representation for geometry reconstruction. Based on the observation that the topology between the posed mesh and the mesh in the canonical space are consistent, we propose to learn latent codes on the posed mesh by leveraging multiple input images and then assign the latent codes to the mesh in the canonical space. Specifically, we first leverage normal and geometry networks to extract the feature vector for each vertex on the SMPLX mesh. Normal maps are adopted for better generalization to unseen images compared to 2D images. Then, features for each vertex on the posed mesh from multiple images are integrated by MLPs. The integrated features acting as the latent code are anchored to the SMPLX mesh in the canonical space. Finally, latent code for each 3D point is extracted and utilized to calculate the SDF. Our work for reconstructing the human shape on canonical pose achieves 3rd performance on WCPA MVP-Human Body Challenge.