Generative Shape Reconstruction with Geometry-Guided Langevin Dynamics

TL;DR

GG-Langevin is a probabilistic method that combines measurement consistency with shape priors via Langevin dynamics, improving 3D shape reconstruction from incomplete or noisy data.

Contribution

It introduces a novel geometry-guided Langevin dynamics approach that unifies measurement fidelity with generative shape priors for robust 3D reconstruction.

Findings

Achieves higher geometric accuracy than existing methods.

Demonstrates greater robustness to missing data.

Effectively balances measurement consistency with shape plausibility.

Abstract

Reconstructing complete 3D shapes from incomplete or noisy observations is a fundamentally ill-posed problem that requires balancing measurement consistency with shape plausibility. Existing methods for shape reconstruction can achieve strong geometric fidelity in ideal conditions but fail under realistic conditions with incomplete measurements or noise. At the same time, recent generative models for 3D shapes can synthesize highly realistic and detailed shapes but fail to be consistent with observed measurements. In this work, we introduce GG-Langevin: Geometry-Guided Langevin dynamics, a probabilistic approach that unifies these complementary perspectives. By traversing the trajectories of Langevin dynamics induced by a diffusion model, while preserving measurement consistency at every step, we generatively reconstruct shapes that fit both the measurements and the data-informed prior. We demonstrate through extensive experiments that GG-Langevin achieves higher geometric accuracy and greater robustness to missing data than existing methods for surface reconstruction.