AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Self-Supervised Pretraining of 3D Features on Any Point-Cloud

Zaiwei Zhang, Rohit Girdhar, Armand Joulin, Ishan Misra

ICCV 2021 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 310 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
self-supervised DepthContrast pretraining instead of scratchVoteNet PointNet++ · S3DIS detectionAP25: 31.2 -> 43.3Improved
self-supervised DepthContrast pretraining instead of scratchVoteNet PointNet++ · ScanNet detectionAP25: 58.6 -> 61.3Improved
self-supervised DepthContrast pretraining instead of scratchVoteNet PointNet++ · SUNRGBD detectionAP25: 57.4 -> 60.4Improved
DepthContrast instead of supervised ScanNet detection pretrainingVoteNet PointNet++ · SUNRGBD detectionAP25: 59.1 -> 60.4Improved
DepthContrast instead of supervised ScanNet detection pretrainingVoteNet PointNet++ · S3DIS detectionAP25: 48.5 -> 43.3Hurt
add across-format loss to within-format only (ablation)joint point and voxel pretraining · S3DIS voxel transfertransfer score: 66.5 -> 70.6Improved
add across-format loss to within-format only (ablation)joint point and voxel pretraining · ScanNet point transferAP25: 61.3 -> 62.2Improved
add within-format loss to across-format only (ablation)joint point and voxel pretraining · SUNRGBD point transferAP25: 60.0 -> 60.7Improved
pretrain on combined Redwood-vid and ScanNet-vid and use larger model with H3DNetH3DNet · ScanNet detectionAP25: 67.2 -> 69.0Improved
pretrain on combined Redwood-vid and ScanNet-vid and use larger model with H3DNetH3DNet · SUNRGBD detectionAP25: 60.1 -> 63.5Improved
DepthContrast pretraining for VoteNet instead of PointContrastVoteNet · ScanNet detectionAP25: 59.2 -> 64.0Improved
increase model width with scratch training (ablation)PointNet++ · S3DIS detectionAP25No clear effect

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