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

Korean

훈련받은 3D Gaussian Splatting 장면을 축소하는 컴퓨팅 예산에 따라 배포하는 것은 작은 프리픽스에서 렌더링 할 때 효과적으로 유지하는 원시 세트가 필요합니다.이 지속적인 수준의 세부 사항 (LoD) 설정에서, 도전은 3DGS-MCMC 재구성에 대한 파일럿 연구는 3DGS-MCMC 재구성에 비해 재구성 능력을 유지해야한다는 것을 결정하는 것입니다. 그 후 KoalaGS에서 최적화하기 전에 입력 뷰에서 계산 된 이미지 복잡성은 재구성 오류가 이미지 및 3D 공간에 집중되는 곳을 예측합니다. 또한 간단한 지역이 너무 많은 Gaussians를 포함하고 더 낮은 예산에서 복잡한 것처럼 저하다는 것을 보여줍니다. 그 후 KoalaGS에서 우리는

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