Metraipolis › archive › dc_9ebfe4c33dab

VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization — arXiv:2609.21498

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21498
License (as archived)
CC0-1.0
Archived
2026-10-10T02:29:35.082Z
SHA-256 of the archived text
491151f639a34919859ee38f0524576a71c2f12bb8cbf24621d77880d90140ac
Stable URL of this page
https://metraipolis.com/documento/dc_9ebfe4c33dab

How to cite

VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization — arXiv:2609.21498 — arXiv (en), https://arxiv.org/abs/2609.21498 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9ebfe4c33dab (Metraipolis archive dc_9ebfe4c33dab, sha256 491151f639a34919859ee38f0524576a71c2f12bb8cbf24621d77880d90140ac)
BibTeX
@misc{dc9ebfe4c33dab,
  title = {VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization — arXiv:2609.21498},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21498},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9ebfe4c33dab; sha256 491151f639a34919859ee38f0524576a71c2f12bb8cbf24621d77880d90140ac},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21498. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent feed-forward 3D Gaussian Splatting (3DGS) methods typically regress pixel-aligned Gaussian primitives, often causing excessive overlap and artifacts, while inaccuracies in predicted camera poses can lead to misalignment in novel-view synthesis (NVS). We present VoxelTTO, a feed-forward framework for reconstructing geometrically accurate 3DGS scenes from an arbitrary number of images and optional camera parameters. VoxelTTO aggregates dense image features into a global voxel representation and decodes Gaussians from voxel features, breaking the pixel-to-Gaussian correspondence. To exploit known camera parameters while keeping the pretrained visual foundation model (VFM) parameters frozen, we introduce test-time optimization (TTO) that adapts lightweight LoRA modules using pose supervision. We further replace vanilla 3DGS rasterization with stochastic solid volume rendering during training and inference, improving geometric fidelity. Training updates only the voxel-aligned Gaussian reconstruction modules, requiring 80 GPU hours. Experiments on Replica, Tanks and Temples, and DTU demonstrate improved RGB-D NVS and camera-pose estimation relative to prior methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.21498 — 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 2026-10-10T02:07:36.070Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).