AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

Robo3D: Towards Robust and Reliable 3D Perception against Corruptions

Lingdong Kong, Youquan Liu, Xin Li, Runnan Chen, Wenwei Zhang, Jiawei Ren, Liang Pan, Kai Chen, Ziwei Liu

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: LiDAR perception for driving · 137 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
state-of-the-art segmentors with higher clean accuracy versus the MinkUNet baselinerecent 3D segmentors (2DPASS, GFNet, RPVNet, CPGNet) · SemanticKITTI-CmCE: 2DPASS 106.1, GFNet 108.7 vs MinkUNet 100.0Hurt
use projection-based range-view or BEV representation instead of voxel/point-voxelLiDAR segmentors · SemanticKITTI-CmCE: SqueezeSeg 164.9, CENet 103.4 vs SPVCNN-34 99.2Hurt
use out-of-context augmentation (mixing scenes) instead of in-context augmentation (ablation)baseline segmentor · Robo3D segmentationmCE: 100.0 -> 86.0Improved
add flexible (randomized) voxelization (ablation)baseline with ICA · Robustness training (with ICA)mCE: 100.0 -> 97.4Improved
add completion loss (part2full) on top of flexible voxelization (ablation)density-insensitive training with ICA · Robustness training (with ICA)mCE: 97.4 -> 96.4Improved
add confirmation loss (full2part) in addition to completion loss (ablation)density-insensitive training with ICA · Robustness training (with ICA)mCE: 96.4 -> 96.1Improved
add flexible voxelization to OCA-trained model (ablation)baseline with OCA · Robustness training (with OCA)mCE: 86.0 -> 84.5Improved
add both consistency losses to OCA-trained model (ablation)baseline with OCA · Robustness training (with OCA)mRR: 84.7 -> 89.7Improved
apply flexible voxelization and density-insensitive training (ablation)baseline with OCA · Robustness training (with OCA)clean accuracy: 69.2 -> 68.1Hurt
apply flexible voxelization and density-insensitive training (ablation)baseline with ICA · Robustness training (with ICA)clean accuracy: 62.8 -> 62.7No clear effect
raise mask ratio beyond range of 0.3 to 0.6 (ablation)density-insensitive training · Robo3DmCEHurt
use larger versus smaller fixed voxel size (ablation)baseline segmentor · Robo3DmCEMixed

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