AI Paper Atlas

Research map / 3D vision / 3D generation

PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes

Xiao Yun Fu, Shangzhan Zhang, Tianrun Chen, Yichong Lu, Xiaowei Zhou, Andreas Geiger, Yiyi Liao

TPAMI 2025 · 3D vision › 3D generation · approach: Semantic scene completion · 11 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
use PanopticNeRF-360 instead of 3D-2D CRFlabel transfer · KITTI-360 fisheyemIoU: 64.4 -> 76.3Improved
use PanopticNeRF-360 instead of 3D-2D CRFlabel transfer · KITTI-360 forward-facingmIoU: 79.5 -> 81.9Improved
add label-guided geometry loss on fixed semantic field (ablation)PanopticNeRF-360 · KITTI-360 one scenedepth RMSE: 16.90 -> 7.27Improved
add fisheye semantic predictions as input (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 74.8 -> 76.1Improved
add 2D loss on learned semantic field (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 74.6 -> 76.1Improved
add per-point 3D semantic loss (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 75.0 -> 76.1Improved
add weak stereo depth loss (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 74.4 -> 76.1Improved
add ray masking (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 75.1 -> 76.1Improved
use bounding-primitive-guided sampling instead of uniform sampling (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 67.3 -> 76.1Improved
add class-frequency weight w(k) (ablation)PanopticNeRF-360 · KITTI-360 one scenemIoU*: 75.6 -> 76.1Mixed
use hybrid MLP+hash grid instead of pure MLPscene representation · KITTI-360 forward-facing (4 scenes)PSNR: 23.78 -> 27.25Mixed
use hybrid MLP+hash grid instead of iNGPscene representation · KITTI-360 forward-facing (4 scenes)mIoU: 79.0 -> 80.9Improved

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