Metraipolis › archive › dc_c09b15933792

AQ3D: Adaptive Query Transformer for 3D Instance Segmentation — arXiv:2608.30618

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.30618
License (as archived)
CC0-1.0
Archived
2026-10-17T09:59:34.429Z
SHA-256 of the archived text
8af5994b8b1741748514832ba4e7031f362453922c67f7d7efd9319165d14b2a
Stable URL of this page
https://metraipolis.com/documento/dc_c09b15933792

How to cite

AQ3D: Adaptive Query Transformer for 3D Instance Segmentation — arXiv:2608.30618 — arXiv (en), https://arxiv.org/abs/2608.30618 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c09b15933792 (Metraipolis archive dc_c09b15933792, sha256 8af5994b8b1741748514832ba4e7031f362453922c67f7d7efd9319165d14b2a)
BibTeX
@misc{dcc09b15933792,
  title = {AQ3D: Adaptive Query Transformer for 3D Instance Segmentation — arXiv:2608.30618},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.30618},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c09b15933792; sha256 8af5994b8b1741748514832ba4e7031f362453922c67f7d7efd9319165d14b2a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30618. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transformer-based decoders for 3D instance segmentation typically commit to a fixed number of queries and positional modeling calibrated on the training distribution rather than on the scene at hand. Indoor scans vary widely in spatial extent and object count, so a fixed query set over-initializes small scenes and under-initializes large ones, while learned absolute and relative encodings are bound to the training scenes' extents and can saturate. We present AQ3D, which is designed to handle scenes of various sizes during training and inference. Queries are instantiated at a fixed ratio of the scene's superpoints, forming an overcomplete set whose background rejection is entirely left to the decoder. Positional information is encoded using 3D RoPE over quantized metric coordinates, replacing learned bounded lookup tables of prior decoders. Further, we improve the decoder itself by using attribution-based superpoint pooling, a mask refinement branch, and a cosine classifier for background rejection. Experiments show our method sets a new state-of-the-art on validation and hidden test splits across the datasets ScanNetV2, ScanNet200, and ScanNet++V2 among decoder methods trained without additional data augmentation. Code is available at \href{ this https URL }{ this http URL }.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.30618 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:28:48.160Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).