AI Paper Atlas

Research map / Point clouds / Point cloud classification

HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation

Sha Zhang, Jiajun Deng, Lei Bai, Houqiang Li, Wanli Ouyang, Yanyong Zhang

IJCV 2024 · Point clouds › Point cloud classification · approach: Self-supervised point cloud pretraining · 12 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 BEV distillation to IPV-only distillation (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 41.5 -> 42.7Improved
add IPV distillation to BEV-only distillation (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 37.8 -> 42.7Improved
pretrain with hybrid-view distillation vs random initHVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 28.3 -> 42.7Improved
pretrain with HVDistill vs SLidR on SemanticKITTIHVDistill · SemanticKITTI (1% labels)mIoU: 44.6 -> 49.7Improved
supervise image-to-BEV depth with projected points (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 39.6 -> 42.7Improved
supervise depth by projected points rather than only concatenating sparse depth map (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 42.2 -> 42.7Improved
use superpixel-to-superpoint instead of pixel-to-point contrast on IPV (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 41.1 -> 42.7Improved
add IPV contrast at all vs none (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 33.4 -> 42.7Improved
increase pretraining data from 5% to 100% of nuScenes (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 35.7 -> 42.7Improved
use DINO teacher instead of MoCoV2 (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 42.7 -> 41.4Hurt
use supervised ImageNet teacher instead of MoCoV2 (ablation)HVDistill · nuScenes semseg fine-tune (1% labels)mIoU: 42.7 -> 42.9No clear effect
change alpha:beta loss weight ratio from 1:1 to 4:1 (ablation)HVDistill · SemanticKITTI (1% labels)mIoU: 49.4 -> 50.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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