Metraipolis › archive › dc_a4d47ea077d0
BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget — arXiv:2610.38278
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38278
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-01T02:40:22.201Z
- SHA-256 of the archived text
859cb651d40daa2712de50e046b606d01cbedb333b545718b9624b668cbc2eae- Stable URL of this page
https://metraipolis.com/documento/dc_a4d47ea077d0
How to cite
BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget — arXiv:2610.38278 — arXiv (en), https://arxiv.org/abs/2610.38278 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a4d47ea077d0 (Metraipolis archive dc_a4d47ea077d0, sha256 859cb651d40daa2712de50e046b606d01cbedb333b545718b9624b668cbc2eae)
BibTeX
@misc{dca4d47ea077d0,
title = {BudSplat: Feed-forward 3D Gaussian Splatting under a Rendering Budget — arXiv:2610.38278},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38278},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a4d47ea077d0; sha256 859cb651d40daa2712de50e046b606d01cbedb333b545718b9624b668cbc2eae},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38278. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Feed-forward 3D Gaussian Splatting has recently emerged as a promising alternative to per-scene optimization, enabling fast novel view synthesis by predicting Gaussian primitives directly from input images. However, it quickly faces a bottleneck of rendering efficiency while scaling from sparse to dense multi-view inputs, which offer more geometric constraints but produce a rapidly growing set of candidate Gaussians. Existing solutions cannot reliably distinguish redundant primitives, leading to many redundant primitives from repeatedly observed regions and increased rendering cost without much gain in visual quality. We propose BudSplat, a compact feed-forward 3DGS framework that learns to keep the most valuable Gaussians under a limited primitive count. BudSplat has two novel designs. The first is a detail-aware importance score that is extracted from multi-level visual tokens, providing an explicit cue for regions where pruning is likely to harm perceptual quality. The score can be injected into voxel fusion to preserve high-value local contributors during multi-view aggregation. The second is quality-aware Gaussian pruning that selects a compact set of primitives by jointly considering rendering contribution and detail importance. The quality-aware pruning enables local quota redistribution that helps avoid over-allocating primitives to large redundant regions. Experiments on RE10K, DL3DV, and ACID show that BudSplat achieves a favorable trade-off among rendering quality and efficiency. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.38278 — 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 2026-11-01T02:16:43.874Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).