AI Paper Atlas

Research map / 3D vision / Face and shape

TreeSRNF: Square-Root Normal Fields for Generative Modelling of the Geometric and Structural Variability in Tree-like 3D Objects

Tahmina Khanam, Hamid Laga, Mohammed Bennamoun, Guanjin Wang, Ferdous Sohel, Farid Boussaid, Anuj Srivastava

ECCV 2026 · 3D vision › Face and shape · approach: Optimization-based shape matching · 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
register trees with the SRNF-based full-surface metric instead of the skeleton-plus-thickness methodTreeSRNF · Registration geodesic distance error (16 tree pairs)mean geodesic distance: 140 -> 75.3 (before registration 152.6)Improved
use TreeSRNF registration instead of Pan et al. registrationTreeSRNF · Cycle consistency (threshold 0.1)cycle consistency error: 20.5% -> 0.1%Improved
use TreeSRNF registration at the strictest thresholdTreeSRNF · Cycle consistency (threshold 0.01)cycle consistency error: 33.5% -> 3%Improved
represent full branch surface instead of radial thickness approximationtree representation · point-wise reconstruction error heatmapspointwise errorImproved
use TreeSRNF instead of Pan et al. for registration timeTreeSRNF · Registration timetime: 43 s to 20 mins vs 2.5 mins to 6 hrsImproved

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