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

Spanish

El despliegue de una escena de 3D Gaussian Splatting entrenada bajo presupuestos de computación reducidos requiere un conjunto primitivo para permanecer efectivo cuando se realiza en prefijos más pequeños. En este nivel continuo de detalle (LoD), el desafío es decidir cuáles Gaussian deben mantener la capacidad a medida que el presupuesto disminuye. Un estudio piloto sobre reconstrucciones 3DGS-MCMC muestra que la complejidad de la imagen, calculada a partir de las vistas de entrada antes de la optimización, predice dónde se concentra el error de reconstrucción en la imagen y el espacio 3D. También revela que las regiones simples contienen demasiados Gaussian y degradan tanto como los complejos en presupuestos más bajos, a pesar de ser inherentemente más baratos para representar. Posteriormente, en KoalaGS, durante el

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