AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 15 citations (OpenAlex)

Read the paperCheck 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 changedWhereMeasuredEffect
Replace conical Gaussian IPE approximation with exact pyramid-based IPEMip-NeRF · BlenderPSNR: 34.766 -> 34.707Hurt
Replace conical Gaussian IPE approximation with exact pyramid-based IPEMip-NeRF · BlenderLPIPS: 0.0675 -> 0.0667Helped
Replace conical Gaussian IPE approximation with exact pyramid-based IPEMip-NeRF · BlenderAvg: 0.0242 -> 0.0242No clear effect
Replace conical Gaussian IPE approximation with exact pyramid-based IPEMip-NeRF 360 · Mip-NeRF 360 datasetPSNR: 27.325 -> 27.230Hurt
Replace conical Gaussian IPE approximation with exact pyramid-based IPEMip-NeRF 360 · Mip-NeRF 360 datasetLPIPS: 0.6559 -> 0.6569Hurt
Replace conical Gaussian IPE approximation with exact pyramid-based IPEMip-NeRF 360 · Mip-NeRF 360 datasetAvg: 0.1077 -> 0.1088Hurt
Use exact pyramid-based encoding instead of Gaussian approximation for distant regionsMip-NeRF 360 · Mip-NeRF 360 datasetbackground reconstruction qualityHelped

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