# LIFe-GoM: Generalizable Human Rendering with Learned Iterative Feedback Over Multi-Resolution Gaussians-on-Mesh

arXiv: https://arxiv.org/abs/2502.09617 · HTML: https://mlsanity.com/paper/2502.09617/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 55 references that are in the map.
- First posted on arXiv 13 Feb 2025.

## Builds on (most cited first, 30 of 48)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [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 learn by gradient descent by gradient descent](https://mlsanity.com/paper/1606.04474/) (2016)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video](https://mlsanity.com/paper/2201.04127/) (2022)
- [DeepIM: Deep Iterative Matching for 6D Pose Estimation](https://mlsanity.com/paper/1804.00175/) (2018)
- [GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians](https://mlsanity.com/paper/2312.02069/) (2023)
- [DeepView: View Synthesis with Learned Gradient Descent](https://mlsanity.com/paper/1906.07316/) (2019)
- [Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors](https://mlsanity.com/paper/2105.01859/) (2021)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians](https://mlsanity.com/paper/2312.02134/) (2023)
- [GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis](https://mlsanity.com/paper/2312.02155/) (2023)
- [Neural Human Performer: Learning Generalizable Radiance Fields for Human Performance Rendering](https://mlsanity.com/paper/2109.07448/) (2021)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [Solving ill-posed inverse problems using iterative deep neural networks](https://mlsanity.com/paper/1704.04058/) (2017)
- [InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds](https://mlsanity.com/paper/2212.10550/) (2022)
- [Human Pose Estimation with Iterative Error Feedback](https://mlsanity.com/paper/1507.06550/) (2015)
- [GART: Gaussian Articulated Template Models](https://mlsanity.com/paper/2311.16099/) (2023)
- [Learned Optimizers that Scale and Generalize](https://mlsanity.com/paper/1703.04813/) (2017)
- [TADA! Text to Animatable Digital Avatars](https://mlsanity.com/paper/2308.10899/) (2023)
- [DNA-Rendering: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering](https://mlsanity.com/paper/2307.10173/) (2023)
- [SHERF: Generalizable Human NeRF from a Single Image](https://mlsanity.com/paper/2303.12791/) (2023)
- [MonoHuman: Animatable Human Neural Field from Monocular Video](https://mlsanity.com/paper/2304.02001/) (2023)
- [Learning Neural Volumetric Representations of Dynamic Humans in Minutes](https://mlsanity.com/paper/2302.12237/) (2023)
- [X-Avatar: Expressive Human Avatars](https://mlsanity.com/paper/2303.04805/) (2023)
- [Drivable Volumetric Avatars using Texel-Aligned Features](https://mlsanity.com/paper/2207.09774/) (2022)
- [Structured Prediction Energy Networks](https://mlsanity.com/paper/1511.06350/) (2015)

## Built on by (most cited first, 11 of 11)

- [ReSplat: Learning Recurrent Gaussian Splatting](https://mlsanity.com/paper/2510.08575/) (2025)
- [AniCrafter: Customizing Realistic Human-Centric Animation via Avatar-Background Conditioning in Video Diffusion Models](https://mlsanity.com/paper/2505.20255/) (2025)
- [IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting](https://mlsanity.com/paper/2601.03824/) (2026)
- [SAT: Supervisor Regularization and Animation Augmentation for Two-process Monocular Texture 3D Human Reconstruction](https://mlsanity.com/paper/2508.19688/) (2025)
- [FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation](https://mlsanity.com/paper/2512.01444/) (2025)
- [Stable Diffusion-Based Approach for Human De-Occlusion](https://mlsanity.com/paper/2508.12663/) (2025)
- [NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses](https://mlsanity.com/paper/2511.16673/) (2025)
- [PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction](https://mlsanity.com/paper/2602.05190/) (2026)
- [Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency](https://mlsanity.com/paper/2604.25466/) (2026)
- [Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos](https://mlsanity.com/paper/2606.19156/) (2026)
- [FlowBender: Feedback-Aware Training for Self-Correcting Conditional Flows](https://mlsanity.com/paper/2606.20404/) (2026)

## Abstract (arXiv)

Generalizable rendering of an animatable human avatar from sparse inputs relies on data priors and inductive biases extracted from training on large data to avoid scene-specific optimization and to enable fast reconstruction. This raises two main challenges: First, unlike iterative gradient-based adjustment in scene-specific optimization, generalizable methods must reconstruct the human shape representation in a single pass at inference time. Second, rendering is preferably computationally efficient yet of high resolution. To address both challenges we augment the recently proposed dual shape representation, which combines the benefits of a mesh and Gaussian points, in two ways. To improve reconstruction, we propose an iterative feedback update framework, which successively improves the canonical human shape representation during reconstruction. To achieve computationally efficient yet high-resolution rendering, we study a coupled-multi-resolution Gaussians-on-Mesh representation. We evaluate the proposed approach on the challenging THuman2.0, XHuman and AIST++ data. Our approach reconstructs an animatable representation from sparse inputs in less than 1s, renders views with 95.1FPS at 1024 × 1024, and achieves PSNR/LPIPS*/FID of 24.65/110.82/51.27 on THuman2.0, outperforming the state-of-the-art in rendering quality.