# Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering

arXiv: https://arxiv.org/abs/2505.17338 · HTML: https://mlsanity.com/paper/2505.17338/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 22 May 2025.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (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)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation](https://mlsanity.com/paper/2402.05054/) (2024)
- [TotalSegmentator: robust segmentation of 104 anatomical structures in CT images](https://mlsanity.com/paper/2208.05868/) (2022)
- [GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation](https://mlsanity.com/paper/2403.14621/) (2024)
- [nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation](https://mlsanity.com/paper/2404.09556/) (2024)
- [FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering](https://mlsanity.com/paper/2408.07967/) (2024)
- [Structure-Aware Sparse-View X-ray 3D Reconstruction](https://mlsanity.com/paper/2311.10959/) (2023)
- [Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models](https://mlsanity.com/paper/2012.08721/) (2020)
- [nnInteractive: Redefining 3D Promptable Segmentation](https://mlsanity.com/paper/2503.08373/) (2025)
- [Foundation Models in Radiology: What, How, When, Why and Why Not](https://mlsanity.com/paper/2411.18730/) (2024)
- [DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering](https://mlsanity.com/paper/2406.02518/) (2024)
- [6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering](https://mlsanity.com/paper/2410.04974/) (2024)
- [nnLandmark: A Self-Configuring Method for 3D Medical Landmark Detection](https://mlsanity.com/paper/2504.06742/) (2025)

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

- [Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos](https://mlsanity.com/paper/2509.23492/) (2025)
- [Hybrid Foveated Path Tracing with Peripheral Gaussians for Immersive Anatomy](https://mlsanity.com/paper/2601.22026/) (2026)
- [XClipGS: Exact Half-Space Clipping for Medical Volume Gaussian Splatting](https://mlsanity.com/paper/2608.07760/) (2026)
- [FactorSplat: Appearance-Controllable Gaussian Proxies for Medical Volume Rendering](https://mlsanity.com/paper/2610.02382/) (2026)

## Abstract (arXiv)

Photorealistic volumetric rendering of CT scans greatly benefits clinical workflows, yet neural approaches such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) require prohibitive per-scan optimization (hours for NeRF, about 30 minutes for 3DGS), making them impractical in clinical settings. We propose Render-FM, a feedforward model that eliminates this bottleneck by directly regressing 6D Gaussian Splatting (6DGS) parameters from a CT volume in a single 2.8-second forward pass, a 500x speedup over per-scan optimization. To bridge the domain gap between natural scene reconstruction and medical volumetric rendering, we introduce Anatomy-Guided Priming (AGP), which incorporates segmentation masks and transfer functions as structural and appearance priors, information that existing Gaussian splatting methods overlook. Built on an nnU-Net-inspired 3D U-Net trained on diverse CT scans, Render-FM predicts per-voxel 6DGS parameters and supports immediate real-time rendering. Unlike per-scan methods, it generalizes to unseen anatomies, novel transfer functions, and enables compositional organ visualization with zero additional preparation time. Optional 89-second fine-tuning further improves quality, surpassing per-scan optimized baselines. Project page: https://gaozhongpai.github.io/renderfm/.