Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion

TL;DR

Simba introduces a diffusion-based framework for point cloud completion that preserves fine details and structural integrity while improving robustness and generalization over previous regression-based methods.

Contribution

The paper proposes a novel diffusion model approach reformulating point-wise transformations as distribution learning, enhancing robustness and avoiding overfitting in point cloud completion.

Findings

Achieves state-of-the-art performance on multiple benchmarks.

Effectively preserves geometric details and global structure.

Demonstrates robustness to input noise.

Abstract

Point cloud completion is a fundamental task in 3D vision. A persistent challenge in this field is simultaneously preserving fine-grained details present in the input while ensuring the global structural integrity of the completed shape. While recent works leveraging local symmetry transformations via direct regression have significantly improved the preservation of geometric structure details, these methods suffer from two major limitations: (1) These regression-based methods are prone to overfitting which tend to memorize instant-specific transformations instead of learning a generalizable geometric prior. (2) Their reliance on point-wise transformation regression lead to high sensitivity to input noise, severely degrading their robustness and generalization. To address these challenges, we introduce Simba, a novel framework that reformulates point-wise transformation regression as a distribution learning problem. Our approach integrates symmetry priors with the powerful generative capabilities of diffusion models, avoiding instance-specific memorization while capturing robust geometric structures. Additionally, we introduce a hierarchical Mamba-based architecture to achieve high-fidelity upsampling. Extensive experiments across the PCN, ShapeNet, and KITTI benchmarks validate our method's state-of-the-art (SOTA) performance.