# Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction

arXiv: https://arxiv.org/abs/2303.13796 · HTML: https://mlsanity.com/paper/2303.13796/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 70 references that are in the map.
- First posted on arXiv 24 Mar 2023.

## Builds on (most cited first, 30 of 51)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [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)
- [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)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [Monocular, One-stage, Regression of Multiple 3D People](https://mlsanity.com/paper/2008.12272/) (2020)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB](https://mlsanity.com/paper/1712.03453/) (2017)
- [Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation](https://mlsanity.com/paper/1808.05942/) (2018)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)

## Built on by (most cited first, 30 of 41)

- [SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2309.17448/) (2023)
- [TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation](https://mlsanity.com/paper/2404.16752/) (2024)
- [EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation](https://mlsanity.com/paper/2312.02256/) (2023)
- [C·ASE: Learning Conditional Adversarial Skill Embeddings for Physics-based Characters](https://mlsanity.com/paper/2309.11351/) (2023)
- [SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling](https://mlsanity.com/paper/2303.17368/) (2023)
- [Digital Life Project: Autonomous 3D Characters with Social Intelligence](https://mlsanity.com/paper/2312.04547/) (2023)
- [AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2403.17934/) (2024)
- [Disentangled Clothed Avatar Generation from Text Descriptions](https://mlsanity.com/paper/2312.05295/) (2023)
- [SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation](https://mlsanity.com/paper/2501.09782/) (2025)
- [UniTalker: Scaling up Audio-Driven 3D Facial Animation through A Unified Model](https://mlsanity.com/paper/2408.00762/) (2024)
- [PhysPT: Physics-aware Pretrained Transformer for Estimating Human Dynamics from Monocular Videos](https://mlsanity.com/paper/2404.04430/) (2024)
- [BEDLAM2.0: Synthetic Humans and Cameras in Motion](https://mlsanity.com/paper/2511.14394/) (2025)
- [UniPose: A Unified Multimodal Framework for Human Pose Comprehension, Generation and Editing](https://mlsanity.com/paper/2411.16781/) (2024)
- [Synergistic Global-space Camera and Human Reconstruction from Videos](https://mlsanity.com/paper/2405.14855/) (2024)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [SIMS: Simulating Stylized Human-Scene Interactions with Retrieval-Augmented Script Generation](https://mlsanity.com/paper/2411.19921/) (2024)
- [Human Mesh Modeling for Anny Body](https://mlsanity.com/paper/2511.03589/) (2025)
- [PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds](https://mlsanity.com/paper/2308.14492/) (2023)
- [DICE: End-to-end Deformation Capture of Hand-Face Interactions from a Single Image](https://mlsanity.com/paper/2406.17988/) (2024)
- [Diffusion Models are Efficient Data Generators for Human Mesh Recovery](https://mlsanity.com/paper/2403.11111/) (2024)
- [MeshPose: Unifying DensePose and 3D Body Mesh reconstruction](https://mlsanity.com/paper/2406.10180/) (2024)
- [ADHMR: Aligning Diffusion-based Human Mesh Recovery via Direct Preference Optimization](https://mlsanity.com/paper/2505.10250/) (2025)
- [KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation](https://mlsanity.com/paper/2405.19833/) (2024)
- [MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Images](https://mlsanity.com/paper/2506.09919/) (2025)
- [UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation](https://mlsanity.com/paper/2603.22282/) (2026)
- [W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration](https://mlsanity.com/paper/2311.17460/) (2023)
- [PersPose: 3D Human Pose Estimation with Perspective Encoding and Perspective Rotation](https://mlsanity.com/paper/2508.17239/) (2025)
- [M"obius Transform for Mitigating Perspective Distortions in Representation Learning](https://mlsanity.com/paper/2405.02296/) (2024)
- [VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery](https://mlsanity.com/paper/2602.19180/) (2026)
- [Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking](https://mlsanity.com/paper/2606.14841/) (2026)

## Abstract (arXiv)

As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body. The naive focal length assumptions can harm this task with the incorrectly formulated projection matrices. To solve this, we propose Zolly, the first 3DHMR method focusing on perspective-distorted images. Our approach begins with analysing the reason for perspective distortion, which we find is mainly caused by the relative location of the human body to the camera center. We propose a new camera model and a novel 2D representation, termed distortion image, which describes the 2D dense distortion scale of the human body. We then estimate the distance from distortion scale features rather than environment context features. Afterwards, we integrate the distortion feature with image features to reconstruct the body mesh. To formulate the correct projection matrix and locate the human body position, we simultaneously use perspective and weak-perspective projection loss. Since existing datasets could not handle this task, we propose the first synthetic dataset PDHuman and extend two real-world datasets tailored for this task, all containing perspective-distorted human images. Extensive experiments show that Zolly outperforms existing state-of-the-art methods on both perspective-distorted datasets and the standard benchmark (3DPW).