AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Deep FusionNet for Point Cloud Semantic Segmentation

Feihu Zhang Jin Fang Benjamin Wah Philip Torr

ECCV 2020 · Point clouds › Segmentation and detection · approach: Point cloud semantic segmentation · 187 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
add neighborhood-voxel point feature aggregation to voxel convolution (ablation)sparse conv baseline · Semantic KITTImean IoU (%): 54.8 -> 58.9Improved
add inner-voxel aggregation (ablation)FusionNet without inner-voxel · Semantic KITTImean IoU (%): 58.9 -> 63.7Improved
add inner-voxel aggregation (ablation)FusionNet without inner-voxel · Semantic KITTImean accuracy (%): 90.7 -> 91.8Improved
add voxel-level aggregation to point-only network (ablation)point feature aggregation only · Semantic KITTImean IoU (%): 41.6 -> 63.7Improved
add point-level features to voxel-only network (full FusionNet) (ablation)sparse conv baseline · Semantic KITTImean accuracy (%): 89.6 -> 91.8Improved
use FusionNet instead of sparse convolution MinkNet42MinkNet42 · Semantic KITTI testmIoU (%): 54.3 -> 61.3Improved
use FusionNet instead of MinkNetMinkNet · ScanNetmIoU (%): 67.9 -> 68.8Improved
use FusionNet instead of KPConvKPConv · S3DIS Area 5mIoU (%): 67.1 -> 67.2No clear effect
use FusionNet at 5cm voxel instead of sparse conv at 3cm voxelsparse convolution · Semantic KITTI valmean IoUImproved
use finer voxel size (ablation)voxel-based networks · Semantic KITTI valmean IoU / memoryMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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