# Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos arXiv: https://arxiv.org/abs/2103.03319 ยท HTML: https://mlsanity.com/paper/2103.03319/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 37 of its 68 references that are in the map. - First posted on arXiv 4 Mar 2021. ## Builds on (most cited first, 30 of 37) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017) - [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019) - [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017) - [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017) - [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019) - [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016) - [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016) - [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018) - [NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding](https://mlsanity.com/paper/1905.04757/) (2019) - [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020) - [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017) - [I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.03713/) (2020) - [Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose](https://mlsanity.com/paper/2008.09047/) (2020) - [Video Based Reconstruction of 3D People Models](https://mlsanity.com/paper/1803.04758/) (2018) - [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020) - [Consistent Video Depth Estimation](https://mlsanity.com/paper/2004.15021/) (2020) - [Unite the People: Closing the Loop Between 3D and 2D Human Representations](https://mlsanity.com/paper/1701.02468/) (2017) - [Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation](https://mlsanity.com/paper/1808.05942/) (2018) - [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019) - [Tex2Shape: Detailed Full Human Body Geometry From a Single Image](https://mlsanity.com/paper/1904.08645/) (2019) - [Deep Appearance Models for Face Rendering](https://mlsanity.com/paper/1808.00362/) (2018) - [Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video](https://mlsanity.com/paper/2011.08627/) (2020) - [Monocular Total Capture: Posing Face, Body, and Hands in the Wild](https://mlsanity.com/paper/1812.01598/) (2018) - [DeepCap: Monocular Human Performance Capture Using Weak Supervision](https://mlsanity.com/paper/2003.08325/) (2020) - [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018) - [DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene from Sparse LiDAR Data and Single Color Image](https://mlsanity.com/paper/1812.00488/) (2018) - [Learning the Depths of Moving People by Watching Frozen People](https://mlsanity.com/paper/1904.11111/) (2019) - [Deep Depth Completion of a Single RGB-D Image](https://mlsanity.com/paper/1803.09326/) (2018) - [DeepWrinkles: Accurate and Realistic Clothing Modeling](https://mlsanity.com/paper/1808.03417/) (2018) ## Built on by (most cited first, 12 of 12) - [Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos](https://mlsanity.com/paper/2407.16124/) (2024) - [Video Diffusion Models: A Survey](https://mlsanity.com/paper/2405.03150/) (2024) - [WildVidFit: Video Virtual Try-On in the Wild via Image-Based Controlled Diffusion Models](https://mlsanity.com/paper/2407.10625/) (2024) - [DiffSim: Taming Diffusion Models for Evaluating Visual Similarity](https://mlsanity.com/paper/2412.14580/) (2024) - [Deep Learning-based Depth Estimation Methods from Monocular Image and Videos: A Comprehensive Survey](https://mlsanity.com/paper/2406.19675/) (2024) - [Grid: Omni Visual Generation](https://mlsanity.com/paper/2412.10718/) (2024) - [PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence](https://mlsanity.com/paper/2512.13465/) (2025) - [TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection](https://mlsanity.com/paper/2512.10652/) (2025) - [GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion](https://mlsanity.com/paper/2505.23085/) (2025) - [IM-Animation: An Implicit Motion Representation for Identity-decoupled Character Animation](https://mlsanity.com/paper/2602.07498/) (2026) - [Composed Object Retrieval: Object-level Retrieval via Composed Expressions](https://mlsanity.com/paper/2508.04424/) (2025) - [Pro-Pose: Unpaired Full-Body Portrait Synthesis via Canonical UV Maps](https://mlsanity.com/paper/2512.17143/) (2025) ## Abstract (arXiv) A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D human reconstruction when applying to real-world imagery. We address this challenge by leveraging a new data resource: a number of social media dance videos that span diverse appearance, clothing styles, performances, and identities. Each video depicts dynamic movements of the body and clothes of a single person while lacking the 3D ground truth geometry. To learn a visual representation from these videos, we present a new self-supervised learning method to use the local transformation that warps the predicted local geometry of the person from an image to that of another image at a different time instant. This allows self-supervision by enforcing a temporal coherence over the predictions. In addition, we jointly learn the depths along with the surface normals that are highly responsive to local texture, wrinkle, and shade by maximizing their geometric consistency. Our method is end-to-end trainable, resulting in high fidelity depth estimation that predicts fine geometry faithful to the input real image. We further provide a theoretical bound of self-supervised learning via an uncertainty analysis that characterizes the performance of the self-supervised learning without training. We demonstrate that our method outperforms the state-of-the-art human depth estimation and human shape recovery approaches on both real and rendered images.