AI Paper Atlas

Research map / 3D vision / 3D generation

Virtual Multi-view Fusion for 3D Semantic Segmentation

Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru

ECCV 2020 · 3D vision › 3D generation · approach: Semantic scene completion · 180 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
render virtual views instead of using real photographic images (ablation)multiview fusion · ScanNet val3D mIoU: 60.1 -> 63.2Improved
add normal and global coordinate channels to the rendered input (ablation)virtual-view model · ScanNet val3D mIoU: 63.2 -> 66.1Improved
increase field of view to 2x (ablation)virtual-view model · ScanNet val3D mIoU: 66.1 -> 67.9Improved
add virtual view sampling with backface culling (ablation)virtual-view model · ScanNet val3D mIoU: 67.9 -> 70.1Improved
add multiview fusion after single-view prediction (real views) (ablation)2D segmentation model · ScanNet val2D image IoU: 60.1 -> 68.5Improved
add multiview fusion after single-view prediction (full method) (ablation)2D segmentation model · ScanNet val2D image IoU: 67.0 -> 74.9Improved
use virtual multiview fusion instead of real-view fusion with small training sets (ablation)multiview fusion · ScanNet (low resolution, fewer training scenes)3D mIoUImproved
use all ~2000 virtual views instead of ~10 at inference (ablation)Ours · ScanNet val3D mIoU: 61.7 -> 70.1Improved
use all ~2000 virtual views instead of ~40 at inference (ablation)Ours · ScanNet val3D mIoU: 68.2 -> 70.1Improved
average features across views instead of picking max-probability category (ablation)fusion function · ScanNet val3D mIoUImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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