# Sapiens2

arXiv: https://arxiv.org/abs/2604.21681 · HTML: https://mlsanity.com/paper/2604.21681/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 63 references that are in the map.
- First posted on arXiv 23 Apr 2026.

## Builds on (most cited first, 30 of 56)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Scaling Vision Transformers to 22 Billion Parameters](https://mlsanity.com/paper/2302.05442/) (2023)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [Depth Pro: Sharp Monocular Metric Depth in Less Than a Second](https://mlsanity.com/paper/2410.02073/) (2024)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image](https://mlsanity.com/paper/2307.10984/) (2023)
- [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017)

## Built on by (most cited first, 4 of 4)

- [Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model](https://mlsanity.com/paper/2608.29928/) (2026)
- [Cross-Model Distillation of a Human-Pose Foundation Model from Unannotated Infant Video for Markerless 3D Pose Estimation](https://mlsanity.com/paper/2609.01840/) (2026)
- [SynthGait-19K: A Physically Grounded Synthetic Video Dataset for Gait Parameter Estimation](https://mlsanity.com/paper/2609.08108/) (2026)
- [PACT: End-to-End Learning of Human Pose, Contacts, and Forces from Video](https://mlsanity.com/paper/2610.00451/) (2026)

## Abstract (arXiv)

We present Sapiens2, a model family of high-resolution transformers for human-centric vision focused on generalization, versatility, and high-fidelity outputs. Our model sizes range from 0.4 to 5 billion parameters, with native 1K resolution and hierarchical variants that support 4K. Sapiens2 substantially improves over its predecessor in both pretraining and post-training. First, to learn features that capture low-level details (for dense prediction) and high-level semantics (for zero-shot or few-label settings), we combine masked image reconstruction with self-distilled contrastive objectives. Our evaluations show that this unified pretraining objective is better suited for a wider range of downstream tasks. Second, along the data axis, we pretrain on a curated dataset of 1 billion high-quality human images and improve the quality and quantity of task annotations. Third, architecturally, we incorporate advances from frontier models that enable longer training schedules with improved stability. Our 4K models adopt windowed attention to reason over longer spatial context and are pretrained with 2K output resolution. Sapiens2 sets a new state-of-the-art and improves over the first generation on pose (+4 mAP), body-part segmentation (+24.3 mIoU), normal estimation (45.6% lower angular error) and extends to new tasks such as pointmap and albedo estimation. Code: https://github.com/facebookresearch/sapiens2