# HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers

arXiv: https://arxiv.org/abs/2506.03118 · HTML: https://mlsanity.com/paper/2506.03118/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 102 of its 149 references that are in the map.
- First posted on arXiv 3 Jun 2025.

## Builds on (most cited first, 30 of 102)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Efficient Geometry-aware 3D Generative Adversarial Networks](https://mlsanity.com/paper/2112.07945/) (2021)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [Convolutional Occupancy Networks](https://mlsanity.com/paper/2003.04618/) (2020)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [First Order Motion Model for Image Animation](https://mlsanity.com/paper/2003.00196/) (2020)
- [Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans](https://mlsanity.com/paper/2012.15838/) (2020)
- [One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization](https://mlsanity.com/paper/2306.16928/) (2023)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion](https://mlsanity.com/paper/2403.12008/) (2024)
- [Animatable Neural Radiance Fields for Modeling Dynamic Human Bodies](https://mlsanity.com/paper/2105.02872/) (2021)
- [Everybody Dance Now](https://mlsanity.com/paper/1808.07371/) (2018)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [ICON: Implicit Clothed humans Obtained from Normals](https://mlsanity.com/paper/2112.09127/) (2021)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Motion Representations for Articulated Animation](https://mlsanity.com/paper/2104.11280/) (2021)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [NeuMan: Neural Human Radiance Field from a Single Video](https://mlsanity.com/paper/2203.12575/) (2022)
- [PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction](https://mlsanity.com/paper/2007.03858/) (2020)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)

## Built on by (most cited first, 9 of 9)

- [UP2You: Fast Reconstruction of Yourself from Unconstrained Photo Collections](https://mlsanity.com/paper/2509.24817/) (2025)
- [LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D](https://mlsanity.com/paper/2506.13766/) (2025)
- [HART: Human Aligned Reconstruction Transformer](https://mlsanity.com/paper/2509.26621/) (2025)
- [Real-Time Human Frontal View Synthesis from a Single Image](https://mlsanity.com/paper/2603.15433/) (2026)
- [GenLCA: 3D Diffusion for Full-Body Avatars from In-the-Wild Videos](https://mlsanity.com/paper/2604.07273/) (2026)
- [Make-It-Poseable: Feed-forward Latent Posing Model for 3D Characters](https://mlsanity.com/paper/2512.16767/) (2025)
- [Real-Time Human Reconstruction and Animation using Feed-Forward Gaussian Splatting](https://mlsanity.com/paper/2604.10259/) (2026)
- [LUNA: Learning Universal 3D Human Animation Beyond Skinning](https://mlsanity.com/paper/2606.31981/) (2026)
- [AvatarDynamizer: From Static to Dynamic Human Avatars via Generative Dynamic Textures](https://mlsanity.com/paper/2608.19900/) (2026)

## Abstract (arXiv)

3D human reconstruction and animation are long-standing topics in computer graphics and vision. However, existing methods typically rely on sophisticated dense-view capture and/or time-consuming per-subject optimization procedures. To address these limitations, we propose HumanRAM, a novel feed-forward approach for generalizable human reconstruction and animation from monocular or sparse human images. Our approach integrates human reconstruction and animation into a unified framework by introducing explicit pose conditions, parameterized by a shared SMPL-X neural texture, into transformer-based large reconstruction models (LRM). Given monocular or sparse input images with associated camera parameters and SMPL-X poses, our model employs scalable transformers and a DPT-based decoder to synthesize realistic human renderings under novel viewpoints and novel poses. By leveraging the explicit pose conditions, our model simultaneously enables high-quality human reconstruction and high-fidelity pose-controlled animation. Experiments show that HumanRAM significantly surpasses previous methods in terms of reconstruction accuracy, animation fidelity, and generalization performance on real-world datasets. Video results are available at https://zju3dv.github.io/humanram/.