Data to 7 Oct 2026

PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization

arXiv 2004.00452 ↗First posted 1 Apr 2020cs.CV cs.GRcited by 521

Not on the map. Why?

Cited by 37 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent advances in image-based 3D human shape estimation have been driven by the significant improvement in representation power afforded by deep neural networks. Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images. We argue that this limitation stems primarily form two conflicting requirements; accurate predictions require large context, but precise predictions require high resolution. Due to memory limitations in current hardware, previous approaches tend to take low resolution images as input to cover large spatial context, and produce less precise (or low resolution) 3D estimates as a result. We address this limitation by formulating a multi-level architecture that is end-to-end trainable. A coarse level observes the whole image at lower resolution and focuses on holistic reasoning. This provides context to an fine level which estimates highly detailed geometry by observing higher-resolution images. We demonstrate that our approach significantly outperforms existing state-of-the-art techniques on single image human shape reconstruction by fully leveraging 1k-resolution input images.

Key facts. Cited by 521 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 103; 2022: 108; 2023: 126; 2024: 86; 2025: 68; 2026: 30.

521 papers.

Sort:

By area:

2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,701
2021Neural Fields in Visual Computing and Beyondcited by 539
2021Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesiscited by 459
2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
2021GAN Inversion: A Surveycited by 366
2021Advances in Neural Renderingcited by 365
2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
2021Neural RGB-D Surface Reconstructioncited by 312
2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 311
2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289

38 more

2021ICON: Implicit Clothed humans Obtained from Normalscited by 283
2021Mixture of Volumetric Primitives for Efficient Neural Renderingcited by 277
2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
2024Sapiens: Foundation for Human Vision Modelscited by 229
2021Editing Conditional Radiance Fieldscited by 222
2021SNARF: Differentiable Forward Skinning for Animating Non-Rigid Neural Implicit Shapescited by 221
2021Fake It Till You Make It: Face analysis in the wild using synthetic data alonecited by 200
2022ECON: Explicit Clothed humans Optimized via Normal integrationcited by 199
2021Neural Articulated Radiance Fieldcited by 196
2021Neural Rays for Occlusion-aware Image-based Renderingcited by 192
2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
2023GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesiscited by 170
2023GauHuman: Articulated Gaussian Splatting from Monocular Human Videoscited by 168
2021Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Renderingcited by 158
2021SMPLicit: Topology-aware Generative Model for Clothed Peoplecited by 154
2023HUGS: Human Gaussian Splatscited by 154
2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
2022ARAH: Animatable Volume Rendering of Articulated Human SDFscited by 139
2022InstantAvatar: Learning Avatars from Monocular Video in 60 Secondscited by 138
2021Collaborative Regression of Expressive Bodies using Moderationcited by 137
2021SPEC: Seeing People in the Wild with an Estimated Cameracited by 134
2023Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decompositioncited by 134
2022Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothingcited by 126
2023GART: Gaussian Articulated Template Modelscited by 121
2022Realistic One-shot Mesh-based Head Avatarscited by 119
2022Structured Local Radiance Fields for Human Avatar Modelingcited by 116
2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
2021A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representationcited by 113
2021HumanNeRF: Efficiently Generated Human Radiance Field from Sparse Inputscited by 112
2021Animatable Neural Radiance Fields from Monocular RGB Videoscited by 109
2023TADA! Text to Animatable Digital Avatarscited by 109
2021LEAP: Learning Articulated Occupancy of Peoplecited by 107
2023TeCH: Text-guided Reconstruction of Lifelike Clothed Humanscited by 104
2023DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Renderingcited by 103

50 most cited of 521 All 521 (JSON)