AI Paper Atlas

Research map / 3D vision / 3D generation

YouTube-Occ: Learning Indoor 3D Semantic Occupancy Prediction from YouTube Videos

Haoming Chen, Lichen Yuan, TianFang Sun, Jingyu Gong, Zhizhong Zhang, Xin Tan, Yanyun Qu, Yuan Xie

ECCV 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction

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 YouTube-Occ pre-trainingSymphonies · NYUv2mIoU: 29.70 -> 31.65Improved
add YouTube-Occ pre-trainingSymphonies · Occ-ScanNetmIoU: 47.71 -> 49.38Improved
add YouTube-Occ pre-trainingEmbodiedOcc · NYUv2mIoU: 19.14 -> 20.18Improved
add YouTube-Occ pre-trainingEmbodiedOcc · Occ-ScanNetmIoU: 44.69 -> 46.17Improved
add YouTube-Occ pre-trainingMonoScene · NYUv2mIoU: 26.09 -> 27.02Improved
train Symphonies directly on pseudo-labels (zero-shot)Symphonies · Occ-ScanNetmIoU: 8.41 vs 10.06 raw pseudo-labelsHurt
joint-train with YouTube-Occ instead of NYUv2Symphonies · Occ-ScanNetmIoU: 40.17 -> 37.38Hurt
pre-train on YouTube-Occ with 5% labelsSymphonies · NYUv2 few-shotmIoU: 15.52 -> 18.81 (+3.29)Improved
pre-train on YouTube-Occ with 10% labelsSymphonies · NYUv2 few-shotmIoU: 17.43 -> 22.52 (+5.09)Improved
pre-train on YouTube-Occ with 10% labelsSymphonies · Occ-ScanNet few-shotmIoU: 34.18 -> 36.54 (+2.36)Improved
scale pre-training data from 50K subset to full YouTube-Occ (ablation)Symphonies · NYUv2 full labelsmIoU: 30.87 -> 31.45Improved
add region loss (ablation)Symphonies pre-training · NYUv2mIoU: 29.70 -> 31.12Improved

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