AI Paper Atlas

Research map / Point clouds / Point cloud classification

Multiresolution Tree Networks for 3D Point Cloud Processing

Matheus Gadelha, Rui Wang, Subhransu Maji

ECCV 2018 · Point clouds › Point cloud classification · approach: Local feature aggregation networks · 247 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 multiresolution convolution to the encoder (vs single resolution) (ablation)MRTNet encoder · ModelNet40 classificationaccuracy (%): 89.3 -> 91.7Improved
add data augmentation to the single-resolution model, kd-tree (ablation)single-resolution encoder · ModelNet40 classificationaccuracy (%): 86.2 -> 89.3Improved
use rp-tree instead of kd-tree ordering without augmentation (ablation)single-resolution encoder · ModelNet40 classificationaccuracy (%): 86.2 -> 87.4Improved
reduce filters by 4 to match parameter count (ablation)MRTNet encoder · ModelNet40 classificationaccuracy (%): 91.7 -> 91.7No clear effect
increase points from 1K to 4KMRTNet · ModelNet40 classificationaccuracy (%): 91.2 -> 91.7Improved
condition convolutions on splitting axes (KDNet) vs single-resolution baseline (ablation)KDNet-like single resolution · ModelNet40 classificationaccuracy (%): 1.3% less accuracy without itImproved
add multiresolution decoder instead of fully connected decoder (ablation)MRTNet decoder · ShapeNet shape inferencepred->GT error (x100): 1.824 -> 1.559Improved
add multiresolution decoder instead of fully connected decoder (ablation)MRTNet decoder · ShapeNet shape inferenceGT->pred error (x100): 2.297 -> 1.529Improved
add multiresolution convolution to the decoder instead of single-resolution (ablation)MRTNet decoder · ShapeNet shape inferencepred->GT error (x100): 1.708 -> 1.559Improved
add multiresolution convolution to the decoder instead of single-resolution (ablation)MRTNet decoder · ShapeNet shape inferenceGT->pred error (x100): 1.831 -> 1.529Improved
use MRTNet instead of voxel-based 3D-R2N2 (5 views)MRTNet · ShapeNet shape inferencepred->GT error (x100): 2.588 -> 1.559Improved
use MRTNet instead of Lin et al. multi-view methodMRTNet · ShapeNet shape inferenceGT->pred error (x100): 1.701 -> 1.529Mixed

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