Research map / 3D vision / Gaussian splatting
Gaussian Volumetric Representation for Efficient Shear–Warp Visualization
Mayuri Mathur, Ojaswa Sharma
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 |
|---|---|---|---|
| use MCE importance-sampled sparse voxel supervision instead of random plus high-gradient voxels (ablation) | Gaussian volumetric field · Cryosection | reconstruction PSNR: 33.46 -> 34.81 | Improved |
| add slice supervision curriculum to MCE voxel supervision (ablation) | Gaussian volumetric field · Cryosection | rendering PSNR: 52.34 -> 54.87 | Improved |
| add slice supervision curriculum to MCE voxel supervision (ablation) | Gaussian volumetric field · Cryosection | reconstruction PSNR: 32.40 -> 34.81 | Improved |
| order curriculum voxel first then slices with MCE instead of random voxel then random slices (ablation) | Gaussian volumetric field · Cryosection | reconstruction PSNR: 12.16 -> 34.81 | Improved |
| order curriculum voxel first then slices instead of slices first then random voxel (ablation) | Gaussian volumetric field · Cryosection | reconstruction PSNR: 22.64 -> 34.81 | Improved |
| add sparse voxel supervision to slice-only training (ablation) | Gaussian volumetric field · Cryosection | reconstruction PSNR: 14.350 -> 34.81 | Improved |
| use Gaussian shear-warp rendering instead of ray marching | Gaussian volumetric field · Cryosection | FPS: 15.05 -> 43.86 | Improved |
| use Gaussian representation instead of Voxel MLP | sparse volume reconstruction · Cryosection | rendering PSNR: 46.610 -> 54.87 | Improved |
| use Gaussian representation instead of UNet | sparse volume reconstruction · Cryosection | reconstruction PSNR: 26.70 -> 34.81 | 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.
- CVT-xRF — CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024) · better on 3 of 3 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
- Learning General-purpose Biomedical Volume Representations using Randomized Synthesis (ICLR 2025 · similarity 0.86)
- High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model (CVPR 2025 · similarity 0.85)
- R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction (NeurIPS 2024 · similarity 0.85)
- CycleINR: Cycle Implicit Neural Representation for Arbitrary-Scale Volumetric Super-Resolution of Medical Data (CVPR 2024 · similarity 0.85)
- Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting (NeurIPS 2025 · similarity 0.85)
- Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering (CVPR 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.
