{"id":32415,"date":"2026-01-21T17:01:55","date_gmt":"2026-01-21T17:01:55","guid":{"rendered":"https:\/\/lamarr-institute.org\/publication\/do-point-cloud-models-learn-object-contour-features\/"},"modified":"2026-09-17T11:24:06","modified_gmt":"2026-09-17T11:24:06","slug":"do-point-cloud-models-learn-object-contour-features","status":"publish","type":"publication","link":"https:\/\/lamarr-institute.org\/de\/publication\/do-point-cloud-models-learn-object-contour-features\/","title":{"rendered":"Do Point Cloud Models Learn Object Contour Features?"},"content":{"rendered":"<p>The explainability and transparency of point cloud models is still an understudied topic nowadays. Although enthusiasm for designing complex and high-performance models is ongoing, little work has been devoted to decomposing and dissecting existing popular models, even those with the simplest architectures. To fill this gap, this work presents a novel observation: the point cloud models with PointNet-like structure effectively learn the contours of 3D objects in their intermediate layers. This observation presents a counterfactual for the existing view that point cloud models make decisions based on critical points. Besides, it analyzes the learned contour features of point cloud models and provides a novel inspiration for point cloud synthesis. Based on this observation, we further propose an application called \u201cLatent Activation Maximization\u201d (Latent AM). Latent AM is a point cloud global explainability method which requires only the classifier to be explained and generates much higher quality explanations than other non-generative model-based AMs. We believe this observation will be an important contribution to future research in the areas of point cloud network transparency as well as 3D instance synthesis.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>The explainability and transparency of point cloud models is still an understudied topic nowadays. Although enthusiasm for designing complex and high-performance models is ongoing, little work has been devoted to decomposing and dissecting existing popular models, even those with the simplest architectures. To fill this gap, this work presents a novel observation: the point cloud models with PointNet-like structure effectively learn the contours of 3D objects in their intermediate layers. [&hellip;]<\/p>\n","protected":false},"author":14,"featured_media":0,"template":"","meta":{"_acf_changed":false,"footnotes":""},"publication-type":[32],"class_list":["post-32415","publication","type-publication","status-publish","hentry","publication-type-inproceedings"],"acf":[],"publishpress_future_workflow_manual_trigger":{"enabledWorkflows":[]},"_links":{"self":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32415","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication"}],"about":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/types\/publication"}],"author":[{"embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/users\/14"}],"version-history":[{"count":0,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication\/32415\/revisions"}],"wp:attachment":[{"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/media?parent=32415"}],"wp:term":[{"taxonomy":"publication-type","embeddable":true,"href":"https:\/\/lamarr-institute.org\/de\/wp-json\/wp\/v2\/publication-type?post=32415"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}