NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization

TL;DR

This paper introduces NoKSR, a transformer-based framework for large-scale point cloud surface reconstruction that efficiently converts irregular point clouds into signed distance fields, achieving state-of-the-art accuracy and speed.

Contribution

It proposes a novel serialization and multi-scale aggregation method for point clouds, improving reconstruction accuracy and efficiency over existing approaches.

Findings

Sets new state-of-the-art in accuracy and efficiency

Achieves similar or better performance with half the latency

Effective on outdoor datasets with sparse points

Abstract

We present a novel approach to large-scale point cloud surface reconstruction by developing an efficient framework that converts an irregular point cloud into a signed distance field (SDF). Our backbone builds upon recent transformer-based architectures (i.e., PointTransformerV3), that serializes the point cloud into a locality-preserving sequence of tokens. We efficiently predict the SDF value at a point by aggregating nearby tokens, where fast approximate neighbors can be retrieved thanks to the serialization. We serialize the point cloud at different levels/scales, and non-linearly aggregate a feature to predict the SDF value. We show that aggregating across multiple scales is critical to overcome the approximations introduced by the serialization (i.e. false negatives in the neighborhood). Our frameworks sets the new state-of-the-art in terms of accuracy and efficiency (better or similar performance with half the latency of the best prior method, coupled with a simpler implementation), particularly on outdoor datasets where sparse-grid methods have shown limited performance.