AI Paper Atlas

Research map / Point clouds / Point cloud classification

Unsupervised Depth Completion With Calibrated Backprojection Layers

Alex Wong, Stefano Soatto

ICCV 2021 · Point clouds › Point cloud classification · approach: LiDAR point cloud compression and completion · 102 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 the sparse-to-dense module (ablation)KBNet · KITTI validationMAE: 287.76 -> 260.44Improved
add calibrated backprojection layers instead of VGG blocks (ablation)KBNet · KITTI validationMAE: 285.97 -> 260.44Improved
use the learned S2D instead of scaffolding (ablation)KBNet · KITTI validationMAE: 275.56 -> 260.44Improved
use the learned S2D instead of spatial pyramid pooling (ablation)KBNet · KITTI validationMAE: 273.08 -> 260.44Improved
add scaffolding to VOICED (ablation)VOICED · KITTI validationMAE: 347.14 -> 305.06Improved
add S2D without calibrated layers vs VOICED (sparse geometry still helps) (ablation)KBNet w/o S2D · KITTI validationMAE: 305.06 -> 287.76Improved
decrease sparse depth density from 0.50% to 0.15% to 0.05% (ablation)KBNet · VOID testMAE: 39.80 -> 77.70 -> 131.54Hurt
decrease sparse density to 0.05% (vs ScaffNet) (ablation)KBNet · VOID test (0.05% density)RMSE: 263.54 vs 255.08Hurt
decrease input focal length by 20 to 25% (ablation)KBNet · KITTI validationerrorHurt
increase input focal length up to 20% (ablation)KBNet · VOID testerrorNo clear effect
train on VOID and test on NYUv2 instead of training on NYUv2 (ablation)KBNet · NYUv2 test (sensor transfer)MAE: 105.76 -> 117.18Hurt
train on VOID and test on NYUv2 instead of training on NYUv2ScaffNet · NYUv2 test (sensor transfer)MAE: 117.49 -> 155.20Hurt

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