PhysMorph-GS: Render-Guided Volumetric Morphing with Differentiable Physics

TL;DR

PhysMorph-GS introduces a render-guided volumetric morphing framework coupling physics simulation with differentiable rendering, significantly improving shape accuracy by guiding elastic simulation with visual deformation cues.

Contribution

The paper proposes a novel render-guided morphing method that injects visual supervision through deformation gradients, enhancing physical plausibility and shape accuracy in volumetric morphing.

Findings

Reduces silhouette error by up to 49.9% on complex models.

Uses deformation gradient for visual guidance, improving stability.

Plasticity-driven rest-state migration leads to consistent shape targets.

Abstract

Differentiable particle-based simulation can produce physically plausible motion, but target-driven volumetric shape morphing remains underconstrained: physics-only mass matching captures coarse global structure yet struggles with fine geometric detail, while naive image-space coupling destabilizes elastic dynamics. We present PhysMorph-GS, a render-guided morphing framework that couples material point method simulation with differentiable 3D Gaussian splatting. The key idea is to inject visual supervision through the deformation gradient $\mathbf{F}$ rather than particle positions, so render gradients act as control-space guidance while trajectories remain governed by physics. We further introduce phased Chamfer-guided plasticity that delays rest-state migration until coarse structure has formed; in practice, rendering is evaluated on a surface-focused particle subset for efficiency and gradient concentration. Relative to a physics-only baseline, our method reduces silhouette error by 25.8\%, 10.8\%, and 49.9\% on representative examples, with the largest gains on models with thin features. These results suggest that the main challenge in render-guided differentiable morphing is not simply adding stronger image losses, but injecting visual guidance in a way that remains compatible with elastic simulation. We further observe that plasticity-driven rest-state migration drives different sources toward a shared target-determined attractor, distinguishing physics-based morphing from interpolation between registered shape pairs.