AI Paper Atlas

Research map / Point clouds / Shape and surface completion

InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion

Fangzhou Lin, Yun Yue, Ziming Zhang, Songlin Hou, Kazunori Yamada, Vijaya B Kolachalama, Venkatesh Saligrama

NeurIPS 2023 · Point clouds › Shape and surface completion · approach: Point cloud completion networks · 6 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
replace L1-CD loss with InfoCDCP-Net · ShapeNet-PartL2-CD x10^3: 4.16 -> 4.01Improved
replace L2-CD loss with InfoCDCP-Net · ShapeNet-PartL2-CD x10^3: 4.82 -> 4.01Improved
replace DCD loss with InfoCDCP-Net · ShapeNet-PartL2-CD x10^3: 5.74 -> 4.01Improved
replace HyperCD loss with InfoCDCP-Net · ShapeNet-PartL2-CD x10^3: 4.03 -> 4.01No clear effect
train with InfoCD instead of CDSeedFormer · PCNavg L1-CD x1000: 6.74 -> 6.52Improved
train with InfoCD instead of CDPoinTr · PCNavg L1-CD x1000: 8.38 -> 7.24Improved
train with InfoCD instead of CDFoldingNet · PCNavg L1-CD x1000: 14.31 -> 12.14Improved
train with InfoCD instead of CDSnowflakeNet · PCNavg L1-CD x1000: 7.21 -> 6.86Improved
train with InfoCD instead of CD using original TensorFlow PCNPCN · PCNavg L1-CD x1000: 10.28 -> 9.86Improved
train with InfoCD instead of CDPCN · MVPavg L2-CD x10^4: 9.78 -> 9.41Improved
train with InfoCD instead of CDPCN · MVPavg EMD x10^2: 6.80 -> 5.17Improved
train with InfoCD instead of CDPoinTr · ShapeNet-34 unseenavg L2-CD x1000: 2.05 -> 1.41Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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