# PuzzleAvatar: Assembling 3D Avatars from Personal Albums

arXiv: https://arxiv.org/abs/2405.14869 · HTML: https://mlsanity.com/paper/2405.14869/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 64 of its 109 references that are in the map.
- First posted on arXiv 23 May 2024.

## Builds on (most cited first, 30 of 64)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference](https://mlsanity.com/paper/2310.04378/) (2023)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation](https://mlsanity.com/paper/2303.13873/) (2023)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation](https://mlsanity.com/paper/2212.00774/) (2022)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [AI Choreographer: Music Conditioned 3D Dance Generation with AIST++](https://mlsanity.com/paper/2101.08779/) (2021)
- [ReconFusion: 3D Reconstruction with Diffusion Priors](https://mlsanity.com/paper/2312.02981/) (2023)
- [GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image](https://mlsanity.com/paper/2403.12013/) (2024)
- [ARCH: Animatable Reconstruction of Clothed Humans](https://mlsanity.com/paper/2004.04572/) (2020)
- [Video Based Reconstruction of 3D People Models](https://mlsanity.com/paper/1803.04758/) (2018)
- [NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior](https://mlsanity.com/paper/2212.07388/) (2022)
- [DreamBooth3D: Subject-Driven Text-to-3D Generation](https://mlsanity.com/paper/2303.13508/) (2023)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [ECON: Explicit Clothed humans Optimized via Normal integration](https://mlsanity.com/paper/2212.07422/) (2022)
- [DeepHuman: 3D Human Reconstruction from a Single Image](https://mlsanity.com/paper/1903.06473/) (2019)

## Built on by (most cited first, 16 of 16)

- [LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds](https://mlsanity.com/paper/2503.10625/) (2025)
- [Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior](https://mlsanity.com/paper/2503.01610/) (2025)
- [DRiVE: Diffusion-based Rigging Empowers Generation of Versatile and Expressive Characters](https://mlsanity.com/paper/2411.17423/) (2024)
- [PERSONA: Personalized Whole-Body 3D Avatar with Pose-Driven Deformations from a Single Image](https://mlsanity.com/paper/2508.09973/) (2025)
- [Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds](https://mlsanity.com/paper/2412.07766/) (2024)
- [UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections](https://mlsanity.com/paper/2509.24817/) (2025)
- [ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness](https://mlsanity.com/paper/2503.10624/) (2025)
- [HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers](https://mlsanity.com/paper/2506.03118/) (2025)
- [GarmentCrafter: Progressive Novel View Synthesis for Single-View 3D Garment Reconstruction and Editing](https://mlsanity.com/paper/2503.08678/) (2025)
- [LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D](https://mlsanity.com/paper/2506.13766/) (2025)
- [FRESA: Feedforward Reconstruction of Personalized Skinned Avatars from Few Images](https://mlsanity.com/paper/2503.19207/) (2025)
- [DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image](https://mlsanity.com/paper/2503.19373/) (2025)
- [Creating Your Editable 3D Photorealistic Avatar with Tetrahedron-constrained Gaussian Splatting](https://mlsanity.com/paper/2504.20403/) (2025)
- [BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices](https://mlsanity.com/paper/2508.03313/) (2025)
- [HART: Human Aligned Reconstruction Transformer](https://mlsanity.com/paper/2509.26621/) (2025)
- [Astrolabe: Spherical-Map Guidance Across Diffusion Pipelines for Full-Body Capture from Unconstrained Images](https://mlsanity.com/paper/2608.01276/) (2026)

## Abstract (arXiv)

Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body images in controlled settings. What if a user could just upload their personal "OOTD" (Outfit Of The Day) photo collection and get a faithful avatar in return? The challenge is that such casual photo collections contain diverse poses, challenging viewpoints, cropped views, and occlusion (albeit with a consistent outfit, accessories and hairstyle). We address this novel "Album2Human" task by developing PuzzleAvatar, a novel model that generates a faithful 3D avatar (in a canonical pose) from a personal OOTD album, while bypassing the challenging estimation of body and camera pose. To this end, we fine-tune a foundational vision-language model (VLM) on such photos, encoding the appearance, identity, garments, hairstyles, and accessories of a person into (separate) learned tokens and instilling these cues into the VLM. In effect, we exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar. Importantly, we can customize avatars by simply inter-changing tokens. As a benchmark for this new task, we collect a new dataset, called PuzzleIOI, with 41 subjects in a total of nearly 1K OOTD configurations, in challenging partial photos with paired ground-truth 3D bodies. Evaluation shows that PuzzleAvatar not only has high reconstruction accuracy, outperforming TeCH and MVDreamBooth, but also a unique scalability to album photos, and strong robustness. Our code and data are publicly available for research purpose at https://puzzleavatar.is.tue.mpg.de/