AI Paper Atlas

Research map / Point clouds / Shape and surface completion

DiffPMAE: Diffusion Masked Autoencoders for Point Cloud Reconstruction

Yanlong LI, Chamara Madarasingha, Kanchana Thilakarathna

ECCV 2024 · Point clouds › Shape and surface completion · approach: Point cloud upsampling and normals · 7 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
train loss on entire object (masked + visible) instead of masked regions only (ablation)DiffPMAE · ShapeNet-55, r=75%MMD CD (x1e-3): 1.947 -> 1.125 (entire-object eval); masked-only eval is worse for setting (a)Mixed
increase mask ratio from 40% to 75% (ablation)DiffPMAE · ShapeNet-55 masked-onlyMMD CD (x1e-3): 6.187 -> 2.847Improved
use block masking instead of random masking (ablation)DiffPMAE · ShapeNet-55, r=75%MMD CD (x1e-3): 1.125 -> 1.051No clear effect
use G64 N32 patching instead of G32 N64 or G128 N16 (ablation)DiffPMAE · ShapeNet-55MMD CD (x1e-3): 1.441 -> 1.125 (vs G32 N64); 1.604 -> 1.125 (vs G128 N16)Improved
increase latent width from 192 to 384 (ablation)DiffPMAE · ShapeNet-55MMD CD (x1e-3): 1.370 -> 1.125Improved
increase latent width from 384 to 768 (ablation)DiffPMAE · ShapeNet-55MMD CD (x1e-3): 1.125 -> 1.043No clear effect
increase diffusion steps from 200 to 300 (ablation)DiffPMAE · ShapeNet-55MMD CD (x1e-3): 1.125 -> 1.506Hurt
reduce diffusion steps from 200 to 100 (ablation)DiffPMAE · ShapeNet-55MMD CD (x1e-3): 1.125 -> 1.449Hurt
train longer (600 epochs), larger decoder at t=300 (ablation)DiffPMAE · ShapeNet-55MMD CD (x1e-3): 1.506 -> 2.128 (e=600); 1.792 (d=8,h=6,e=600)No clear effect
add MAE position embedding as conditional input in completion (ablation)DiffPMAE · Completion, mask 75%MMD CD (x1e-3): 4.403 -> 1.901Improved
pre-train on ShapeNet instead of training from scratch on ScanObjectNN (ablation)DiffPMAE · ScanObjectNN with backgroundMMD CD (x1e-3): 1.685 -> 1.120Improved
fine-tune ShapeNet-pretrained model on ScanObjectNN (ablation)DiffPMAE · ScanObjectNN with backgroundMMD CD (x1e-3): 1.120 -> 1.244No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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