NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization
This addresses surface reconstruction for 3D computer vision applications, offering a more efficient alternative to sparse-grid methods, though it builds incrementally on existing transformer architectures.
The paper tackles large-scale point cloud surface reconstruction by converting irregular point clouds into signed distance fields using a transformer-based serialization approach, achieving state-of-the-art accuracy and efficiency with half the latency of prior methods on outdoor datasets.
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.