Metraipolis › archive › dc_d22e551e1bea
Less Is More: Genetic Frame Selection for Efficient Novel View Synthesis — arXiv:2609.35573
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35573
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:54:52.443Z
- SHA-256 of the archived text
3e8ef2cbcf4b77dc2d6c8bafa18ffc4081f64f1856e895f9fcbfe1f5a904d47c- Stable URL of this page
https://metraipolis.com/documento/dc_d22e551e1bea
How to cite
Less Is More: Genetic Frame Selection for Efficient Novel View Synthesis — arXiv:2609.35573 — arXiv (en), https://arxiv.org/abs/2609.35573 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d22e551e1bea (Metraipolis archive dc_d22e551e1bea, sha256 3e8ef2cbcf4b77dc2d6c8bafa18ffc4081f64f1856e895f9fcbfe1f5a904d47c)
BibTeX
@misc{dcd22e551e1bea,
title = {Less Is More: Genetic Frame Selection for Efficient Novel View Synthesis — arXiv:2609.35573},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35573},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d22e551e1bea; sha256 3e8ef2cbcf4b77dc2d6c8bafa18ffc4081f64f1856e895f9fcbfe1f5a904d47c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35573. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward novel view synthesis reconstructs a scene from many input images in a single forward pass, yet more views do not necessarily improve performance: redundant or poorly chosen frames increase computational cost and may degrade reconstruction quality. We address the problem of selecting, from an already captured sequence, a fixed-size subset of input views that is most informative for reconstructing specified target viewpoints. We propose a render-free view selector that scores candidate frames based on three complementary criteria: target-view coverage, measured against observed frames that stand in for the targets, redundancy with previously selected views, and image sharpness. A lightweight scoring network then selects the most informative frames without rendering, reconstruction, or per-scene optimization at inference time. To train the selector, we distill an expensive offline search procedure in which a genetic algorithm identifies high-quality subsets by directly optimizing reconstruction performance on training scenes. The selector learns to reproduce these choices from geometric and image-level features alone. Across six datasets and multiple input budgets, our method consistently outperforms both geometric and reconstruction-aware view-selection baselines while incurring significantly lower selection costs than reconstruction-based alternatives. Moreover, carefully selected subsets can outperform feed-forward reconstruction from the full input sequence. The learned selector generalizes across diverse reconstruction paradigms (feed-forward, 3D Gaussian Splatting, and NeRF), to object-targeted reconstruction and to a cross-capture setting in which the target views come from a separate acquisition pass. More broadly, our results indicate that explicitly reasoning about target relevance and inter-view redundancy is a fundamental factor in efficient scene reconstruction. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.35573 — 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 2026-10-07T23:29:27.596Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).