SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion

TL;DR

SplAttN introduces a differentiable Gaussian Splatting approach to improve point cloud completion by maintaining robust cross-modal connections, achieving state-of-the-art results and real-world robustness.

Contribution

It replaces hard projection with Gaussian Splatting for dense, continuous representations, enhancing cross-modal learning and robustness in point cloud completion.

Findings

Achieves state-of-the-art performance on PCN and ShapeNet datasets.

Maintains visual dependency in real-world KITTI benchmark.

Addresses Cross-Modal Entropy Collapse with differentiable density estimation.

Abstract

Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse support, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse. To address this practical limitation, we propose SplAttN, which replaces hard projection with Differentiable Gaussian Splatting to produce a dense, continuous image-plane representation. By reformulating projection as continuous density estimation, SplAttN avoids collapsed sparse support, facilitates gradient flow, and improves cross-modal connection learnability. Extensive experiments show that SplAttN achieves state-of-the-art performance on PCN and ShapeNet-55/34. Crucially, we utilize the real-world KITTI benchmark as a stress test for multi-modal reliance. Counter-factual evaluation reveals that while baselines degenerate into unimodal template retrievers insensitive to visual removal, SplAttN maintains a robust dependency on visual cues, validating that our method establishes an effective cross-modal connection. Code is available at https://github.com/zay002/SplAttN.