AI Paper Atlas

Research map / Point clouds / Shape and surface completion

Tree Skeletonization from 3D Point Clouds by Denoising Diffusion

Elias Ariel Marks, Lucas Nunes, Federico Magistri, Matteo Sodano, Rodrigo Marcuzzi, Lars Zimmermann, Jens Behley, Cyrill Stachniss

ICCV 2025 · Point clouds › Shape and surface completion · approach: Point cloud diffusion generation · 1 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 handcrafted skeletonization with diffusion-based node and flow prediction plus MSTDiffTS · BReTS orchard (real)F1-score (%): 25.72 -> 38.62Improved
use DiffTS instead of AdTree on real orchard dataDiffTS · BReTS orchard (real)Recall (%): 39.05 vs 54.96Hurt
use DiffTS on multi-species synthetic dataDiffTS · TreeNet3DF1-score (%): 79.30 -> 84.78Improved
train DiffTS on small synthetic apple dataset (100 samples)DiffTS · Smart-Tree synthetic apple dataF1-score (%): 35.61 vs AdTree 36.06No clear effect
limit predicted nodes to 3,000 due to memoryDiffTS · TreeNet3DRecall (%): 83.79 vs AdTree 93.72Hurt
vary random initialization of diffusionDiffTS · BReTS orchard (real)Chamfer distance (cm): std 0.047 cmNo clear effect

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