# TIFu: Tri-directional Implicit Function for High-Fidelity 3D Character Reconstruction

arXiv: https://arxiv.org/abs/2401.14565 · HTML: https://mlsanity.com/paper/2401.14565/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 25 Jan 2024.

## Builds on (most cited first, 27 of 27)

- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [Implicit Geometric Regularization for Learning Shapes](https://mlsanity.com/paper/2002.10099/) (2020)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion](https://mlsanity.com/paper/2003.01456/) (2020)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [STAR: Sparse Trained Articulated Human Body Regressor](https://mlsanity.com/paper/2008.08535/) (2020)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images](https://mlsanity.com/paper/1901.11153/) (2019)
- [SMPLicit: Topology-aware Generative Model for Clothed People](https://mlsanity.com/paper/2103.06871/) (2021)
- [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018)
- [Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction](https://mlsanity.com/paper/2007.11432/) (2020)
- [Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing](https://mlsanity.com/paper/2204.08906/) (2022)
- [Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction](https://mlsanity.com/paper/2006.08072/) (2020)
- [MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images](https://mlsanity.com/paper/2106.11944/) (2021)
- [gDNA: Towards Generative Detailed Neural Avatars](https://mlsanity.com/paper/2201.04123/) (2022)
- [Photo Wake-Up: 3D Character Animation from a Single Photo](https://mlsanity.com/paper/1812.02246/) (2018)
- [Accurate 3D Body Shape Regression using Metric and Semantic Attributes](https://mlsanity.com/paper/2206.07036/) (2022)
- [High-Fidelity Clothed Avatar Reconstruction from a Single Image](https://mlsanity.com/paper/2304.03903/) (2023)
- [Reconstructing NBA Players](https://mlsanity.com/paper/2007.13303/) (2020)
- [Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images](https://mlsanity.com/paper/2008.07760/) (2020)

## Built on by (most cited first, 1 of 1)

- [HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence](https://mlsanity.com/paper/2601.21314/) (2026)

## Abstract (arXiv)

Recent advances in implicit function-based approaches have shown promising results in 3D human reconstruction from a single RGB image. However, these methods are not sufficient to extend to more general cases, often generating dragged or disconnected body parts, particularly for animated characters. We argue that these limitations stem from the use of the existing point-level 3D shape representation, which lacks holistic 3D context understanding. Voxel-based reconstruction methods are more suitable for capturing the entire 3D space at once, however, these methods are not practical for high-resolution reconstructions due to their excessive memory usage. To address these challenges, we introduce Tri-directional Implicit Function (TIFu), which is a vector-level representation that increases global 3D consistencies while significantly reducing memory usage compared to voxel representations. We also introduce a new algorithm in 3D reconstruction at an arbitrary resolution by aggregating vectors along three orthogonal axes, resolving inherent problems with regressing fixed dimension of vectors. Our approach achieves state-of-the-art performances in both our self-curated character dataset and the benchmark 3D human dataset. We provide both quantitative and qualitative analyses to support our findings.