Newest papers

KoalaGS: Complexity-Aware Continuous Level of Detail for Gaussian Splatting

Radu Beche, Raoul de Charette · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.28615 · cited by 0 works (OpenAlex) · open-access PDF

German

Die Implementierung einer ausgebildeten 3D Gaussian Splatting-Szene unter schrumpfenden Berechnungsbudgets erfordert ein primitives Set, um bei kleineren Präfixen wirksam zu bleiben. In dieser kontinuierlichen Ebene der Details (LoD) -Einstellung besteht die Herausforderung darin, zu entscheiden, welche Gaussianer Kapazität behalten sollten, wenn das Budget sinkt. Eine Pilotstudie zu 3DGS-MCMC-Rekonstruktionen zeigt, dass die Bildkomplexität, berechnet von den Eingangsansichten vor der Optimierung, vorhersagt, wo der Rekonstruktionsfehler in Bild und 3D-Raum konzentriert ist. Es zeigt auch, dass einfache Regionen zu viele Gaussianer enthalten und so viel wie komplexe auf niedrigeren Budgets degrad

Machine translation (Meta M2M100); the English original follows.

Abstract

Deploying a trained 3D Gaussian Splatting scene under shrinking compute budgets requires one primitive set to remain effective when rendered at smaller prefixes. In this continuous level of detail (LoD) setting, the challenge is to decide which Gaussians should retain capacity as the budget decreases. A pilot study on 3DGS-MCMC reconstructions shows that image complexity, computed from the input views before optimization, predicts where reconstruction error concentrates in image and 3D space. It also reveals that simple regions contain too many Gaussians and degrade as much as complex ones at lower budgets, despite being inherently cheaper to represent. Subsequently, in KoalaGS, during training we use this complexity prior to bias relocation toward poorly reconstructed areas while ensuring smooth degradation across LoDs. A primitive importance score then enables inference at low-capacity, while preserving the scene structure. Tested across three datasets, KoalaGS maintains competitive full-capacity quality while significantly improving quality across the budget spectrum, yielding smoother transitions across LoDs, and enabling faster progressive streaming.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Gaussian, Inference, Set (abstract data type), Computer vision

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange