NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912237531168768 |
|---|---|
| author | Li, Zhen Sun, Weiwei Govindarajan, Shrisudhan Xia, Shaobo Rebain, Daniel Yi, Kwang Moo Tagliasacchi, Andrea |
| author_facet | Li, Zhen Sun, Weiwei Govindarajan, Shrisudhan Xia, Shaobo Rebain, Daniel Yi, Kwang Moo Tagliasacchi, Andrea |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_12534 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization Li, Zhen Sun, Weiwei Govindarajan, Shrisudhan Xia, Shaobo Rebain, Daniel Yi, Kwang Moo Tagliasacchi, Andrea Computer Vision and Pattern Recognition 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. |
| title | NoKSR: Kernel-Free Neural Surface Reconstruction via Point Cloud Serialization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.12534 |