Research map / 3D vision / NeRF and radiance fields
DIVeR: Real-Time and Accurate Neural Radiance Fields With Deterministic Integration for Volume Rendering
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 deterministic feature integration instead of random sampling (ablation) | DIVeR64 · Lego | PSNR: 33.89 -> 35.52 | Helped |
| initialize voxel features with an implicit MLP, then optimize them explicitly (ablation) | DIVeR64 · Lego | PSNR: 34.69 -> 35.52; 34.02 -> 35.52 | Helped |
| reduce voxel grid size from 256 to 128 (ablation) | DIVeR64 · NeRF-Synthetic | PSNR: 32.32 -> 30.72 | Hurt |
| use DIVeR32 rather than DIVeR64 decoder (ablation) | DIVeR · NeRF-Synthetic | PSNR: 32.32 -> 32.16 | Hurt |
| enable real-time inference optimization (ablation) | DIVeR64 · NeRF-Synthetic | PSNR: 32.32 -> 32.30 | Hurt |
| store feature vectors as uint8 instead of float32 (ablation) | DIVeR64 · Lego | PSNR: 35.52 -> 35.44 | Hurt |
| use DIVeR64 for NeRF-Synthetic rather than NSVF | DIVeR · NeRF-Synthetic | PSNR: 31.74 -> 32.32 | Helped |
| use DIVeR64 for BlendedMVS rather than NSVF | DIVeR · BlendedMVS | LPIPS: 0.113 -> 0.073 | Helped |
| use DIVeR64 for Tanks & Temples rather than NSVF | DIVeR · Tanks & Temples | PSNR: 28.40 -> 28.18 | Hurt |
| use DIVeR64 for Tanks & Temples rather than NSVF | DIVeR · Tanks & Temples | LPIPS: 0.153 -> 0.116 | Helped |
| use DIVeR32 rather than JaxNeRF+ | DIVeR · NeRF-Synthetic | PSNR: 33.00 -> 32.16 | Hurt |
| use DIVeR32(RT) rather than SNeRG | DIVeR · NeRF-Synthetic | PSNR: 30.38 -> 32.12 | Helped |
Closest papers by meaning
- CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs (CVPR 2024 · similarity 0.86)
- Compact 3D Gaussian Representation for Radiance Field (CVPR 2024 · similarity 0.86)
- GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration (NeurIPS 2024 · similarity 0.86)
- HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfaces (CVPR 2024 · similarity 0.85)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.85)
- Sparse Voxels Rasterization: Real-time High-fidelity Radiance Field Rendering (CVPR 2025 · similarity 0.85)
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.