Hejto.pl
Dodaj post

Wpisz coś do wyszukania (minimum 2 znaki)

#ospa

Lider

w Heheszki

43piorunów

#heheszki #matrix

GURU2piorunów

@A_a dla wszystkich którzy się martwią:
Szczepienie przeciwko ospie nie zapobiega digitalizacji. Dzięki współczesnym metodom takim jak gaussian splatting cele kalibracyjne na ciele nie są już potrzebne do 100% digitalizacji.
Tldr: Osoby które nie przeszły ospy tez są martwe
https://arxiv.org/abs/2503.05182

MGSR: 2D/3D Mutual-boosted Gaussian Splatting for High-fidelity Surface Reconstruction under Various Light ConditionsNovel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under diverse light conditions and failing to produce accurate surfaces, while GS-based reconstruction methods frequently compromise rendering quality. This raises a central question: must rendering and reconstruction always involve a trade-off? To address this, we propose MGSR, a 2D/3D Mutual-boosted Gaussian splatting for Surface Reconstruction that enhances both rendering quality and 3D reconstruction accuracy. MGSR introduces two branches--one based on 2D-GS and the other on 3D-GS. The 2D-GS branch excels in surface reconstruction, providing precise geometry information to the 3D-GS branch. Leveraging this geometry, the 3D-GS branch employs a geometry-guided illumination decomposition module that captures reflected and transmitted components, enabling realistic rendering under varied light conditions. Using the transmitted component as supervision, the 2D-GS branch also achieves high-fidelity surface reconstruction. Throughout the optimization process, the 2D-GS and 3D-GS branches undergo alternating optimization, providing mutual supervision. Prior to this, each branch completes an independent warm-up phase, with an early stopping strategy implemented to reduce computational costs. We evaluate MGSR on a diverse set of synthetic and real-world datasets, at both object and scene levels, demonstrating strong performance in rendering and surface reconstruction.arXiv.org
Gwiazdor1piorunów

@A_a mozna prosić o jakis update tej kopii?

Lider1piorunów

@Osiemgwiazdek best I can do is pojebana polityka i ciągły dekadentyzm ( ͡~ ͜ʖ ͡°)

Pokaż więcej komentarzy (4)