Search papers, labs, and topics across Lattice.
The paper introduces SplAttN, a novel approach to point cloud completion that addresses the issue of Cross-Modal Entropy Collapse in multi-modal learning. SplAttN replaces hard projection with Differentiable Gaussian Splatting to create a dense, continuous image-plane representation, improving cross-modal connection learnability. Experiments on PCN, ShapeNet, and KITTI datasets demonstrate state-of-the-art performance and robust dependency on visual cues, validating the effectiveness of the proposed cross-modal connection.
Standard hard projection in multi-modal point cloud completion severs the connection between modalities, but SplAttN's differentiable Gaussian splatting fixes this, leading to state-of-the-art results.
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.
