Research map / 3D vision / Gaussian splatting
Render-FM: Feedforward Model for Real-time Photorealistic Volumetric Rendering
Zhongpai Gao, Benjamin Planche, Meng Zheng, Anwesa Choudhuri, Van Nguyen, Terrence Chen, Ziyan Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add anatomy-guided priming (AGP) initialization (ablation) | 6DGS · TotalSegmentator ID (seen TF) | PSNR: 26.63 -> 28.92 | Improved |
| add AGP initialization (ablation) | 6DGS · CT-ORG OOD (seen TF) | PSNR: 25.97 -> 29.36 | Improved |
| add AGP initialization (ablation) | 6DGS · CT-ORG OOD (unseen TF) | PSNR: 26.59 -> 29.66 | Improved |
| add AGP initialization (ablation) | 6DGS · CT-ORG OOD (skeleton group) | PSNR: 26.78 -> 28.95 | Improved |
| add AGP initialization (ablation) | 6DGS · TotalSegmentator ID (seen TF) | number of Gaussians: 68,785 -> 135,827 | Improved |
| add AGP initialization (ablation) | 6DGS · TotalSegmentator ID (seen TF) | preparation time (s): 1463.9 -> 1786.5 | Hurt |
| add AGP (priors) to feedforward training (ablation) | Render-FM · training | convergence | Improved |
| add 300-iteration fine-tuning | Render-FM · TotalSegmentator ID (seen TF) | PSNR: 27.30 -> 31.67 | Improved |
| add 300-iteration fine-tuning | Render-FM · CT-ORG OOD (seen TF) | PSNR: 26.21 -> 32.48 | Improved |
| add 300-iteration fine-tuning | Render-FM · CT-ORG OOD (unseen TF) | PSNR: 26.77 -> 31.91 | Improved |
| add 300-iteration fine-tuning | Render-FM · CT-ORG OOD (skeleton group) | PSNR: 26.10 -> 30.74 | Improved |
| replace per-scan 6DGS optimization with feedforward Render-FM | 6DGS · TotalSegmentator ID (seen TF) | preparation time (s): 1463.9 -> 2.8 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- 6DGS — 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering (ICLR 2025) · better on 10 of 10 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging (NeurIPS 2025 · similarity 0.86)
- Gaussian Volumetric Representation for Efficient Shear–Warp Visualization (ECCV 2026 · similarity 0.86)
- MedGSSR: Generalizable Medical Image Super-Resolution 3D Reconstruction via Hierarchical Feed-forward Gaussian Splatting (ECCV 2026 · similarity 0.86)
- Pixel-Level Residual Diffusion Transformer: Scalable 3D CT Volume Generation (ICLR 2026 · similarity 0.86)
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024 · similarity 0.84)
- 6DGS: Enhanced Direction-Aware Gaussian Splatting for Volumetric Rendering (ICLR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
