PhyloSDF: Phylogenetically-Conditioned Neural Generation of 3D Skull Morphology via Residual Flow Matching

TL;DR

PhyloSDF is a novel neural generative model that produces biologically plausible 3D skull shapes respecting phylogenetic relationships, even with limited data, outperforming existing methods in fidelity and diversity.

Contribution

The paper introduces PhyloSDF, combining a phylogenetically-regularized DeepSDF auto-decoder with Residual CFM for effective 3D biological shape generation from scarce data.

Findings

Achieves 88-129% of intra-species variation in generated skull meshes.

Outperforms diffusion and flow matching baselines in fidelity and diversity.

Demonstrates phylogenetic extrapolation and plausible ancestral shape interpolation.

Abstract

Generating novel, biologically plausible three-dimensional morphological structures is a fundamental challenge in computational evolutionary biology, hampered by extreme data scarcity and the requirement that generated shapes respect phylogenetic relationships among species. In this work, we present PhyloSDF, a phylogenetically-conditioned neural generative model for 3D biological morphology that integrates two innovations: (1) a DeepSDF auto-decoder regularized by a novel Phylogenetic Consistency Loss that structures the latent space to correlate with evolutionary distances (Pearson $r=0.993$); (2) a Residual Conditional Flow Matching (Residual CFM) architecture that factorizes generation into analytic species-centroid lookup and learned residual prediction, enabling generation from as few as ~4 specimens per species. We evaluate PhyloSDF on 100 micro-CT-scanned skulls of Darwin's Finches and their relatives across 24 species. The model generates novel meshes achieving 88-129% of real intra-species variation at the code level, with all 180 generated meshes verified as non-memorized. Residual CFM surpasses denoising diffusion (which fails entirely at this scale), standard flow matching (which mode-collapses to 3-6% variation), and a Gaussian mixture baseline in both fidelity (Chamfer Distance 0.00181 vs. 0.00190) and morphometric Fr\'{e}chet distance (10,641 vs. 13,322). Leave-one-species-out experiments across 18 species demonstrate phylogenetic extrapolation capability, and smooth latent interpolations produce biologically plausible ancestral skull reconstructions.