Search papers, labs, and topics across Lattice.
PhyloSDF, a novel phylogenetically-conditioned neural generative model, was developed to generate biologically plausible 3D skull morphologies while respecting phylogenetic relationships, addressing data scarcity in evolutionary biology. The model combines a DeepSDF auto-decoder with a Phylogenetic Consistency Loss to structure the latent space based on evolutionary distances and a Residual Conditional Flow Matching (Residual CFM) architecture for generation. Evaluated on 100 micro-CT scans of Darwin's Finches, PhyloSDF generates novel meshes achieving 88-129% of real intra-species variation, outperforming denoising diffusion, standard flow matching, and Gaussian mixture baselines in fidelity and morphometric Fr茅chet distance.
Generating realistic 3D skull shapes for rare species is now possible with as few as four examples, thanks to a phylogenetically-informed neural generator that beats diffusion models and even allows for plausible reconstructions of ancestral forms.
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.
