AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Neural Volumetric Object Selection

CVPR 2022 · 3D vision › NeRF and radiance fields · approach: NeRF for scene decomposition and understanding · 49 citations (OpenAlex)

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 changedWhereMeasuredEffect
use the proposed volumetric method instead of the strongest 2D interactive baselineobject selection · LLFFIoU: 7.4% IoUHelped
use the proposed volumetric method instead of the strongest 2D interactive baselineobject selection · ShinyIoU: 10.8% IoUHelped
use the proposed volumetric method instead of 3D graph-cutobject selection · LLFFSSIM: +0.167 SSIMHelped
use the proposed volumetric method instead of 3D graph-cutobject selection · ShinySSIM: +0.158 SSIMHelped
add multi-view image features (ablation)Ours · LLFFIoU: 5.4% IoUHelped
add IBR features (ablation)Ours · LLFFIoU: 9.7% IoUHelped
add positional encoding (ablation)Ours · LLFFIoU: 16.9%Helped
use a DTU-pretrained 3D U-Net instead of a Kinetics-pretrained 3D CNN encoder (ablation)Ours · LLFFIoU: -16.2% IoUHelped
add graph-cut post-processing (ablation)Ours · LLFFIoU: 2.1% IoUHelped

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