AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields

Seungtae Nam, Daniel Rho, Jong Hwan Ko, Eunbyung Park

NeurIPS 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 3 citations (OpenAlex)

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 changedWhereMeasuredEffect
Add learned convolutional multi-scale grids from a shared gridTensoRF · Multi-scale Blender testaverage PSNR: 30.70 -> 35.23Improved
Add learned convolutional multi-scale grids from shared planesK-Planes · Multi-scale Blender testaverage PSNR: 29.76 -> 32.27Improved
Add learned convolutional multi-scale grids from a shared gridTensoRF · Multi-scale LLFF testaverage PSNR: 26.03 -> 30.48Improved
Use four independent scale-specific models instead of one shared modelTensoRF · Multi-scale Blender testaverage PSNR: 30.70 -> 34.77Improved
Use four independent scale-specific models instead of one shared modelK-Planes · Multi-scale Blender testaverage PSNR: 29.76 -> 32.24Improved
Use continuous rather than discrete scale coordinates (ablation)Mip-TensoRF · Multi-scale Blender test, especially unseen resolutionsPSNR: 34.54 -> 34.73Improved
Add distance from ray origin as a second scale coordinate (ablation)Mip-TensoRF · Multi-scale Blender test, eight resolutionsaverage PSNR: 34.54 -> 34.88Improved
Use fixed Gaussian kernels with increasing standard deviations across scales (ablation)Mip-TensoRF · Multi-scale Blender testaverage PSNR: 30.99 -> 34.05Improved
Learn kernel weights instead of keeping Gaussian kernels fixed (ablation)Mip-TensoRF · Multi-scale Blender testaverage PSNR: 34.05 -> 35.40Improved
Increase the number of generated grids from 2 to 4 (ablation)Mip-TensoRF · Hotdog, multi-scale Blenderaverage PSNR: 39.43 -> 39.78No clear effect
Increase kernel size from 3 to 11 (ablation)Mip-TensoRF · Hotdog, multi-scale Blender, low-resolution renderingPSNR: 40.49 -> 41.01Improved
Use kernel sizes that are too small for low-scale grids (ablation)Mip-TensoRF · Hotdog, multi-scale Blender, low-resolution renderingPSNRHurt

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy