Newest papers

ClunoGS: Compact Language 3D Gaussian Splatting via Unified Optimization

Jian Xu, Yi Li, Ying Huang, Siyi Wu, Bingzhe Li, Yuede Ji, Miao Yin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.30013 · cited by 0 works (OpenAlex) · open-access PDF

German

Gaussian Semisegmentierung 3D-Semi-Segmentierung ermöglicht das offene Vokabular-Szeneverständnis, indem Gaussian-Primitiven mit Sprachmerkmalen assoziiert werden. Diese semantischen Attribute erhöhen die Modellspeicherung, während die meisten bestehenden 3DGS-Komprimierungsmethoden hauptsächlich dazu bestimmt sind, die RGB-Rendering-Qualität zu bewahren. Ein einfacher Ansatz besteht darin, Sparsifizierung und Quantizierung sequentiell anzuwenden. Allerdings kann das Abschneiden, das nur auf Rendering-Qualität basiert, Gaussianer entfernen, die kleine RGB-Beiträge haben, aber für die semantische Vorhersage wichtig sind. Sobald sie entfernt wurden, kann ihre

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

Abstract

Language 3D Gaussian Splatting enables open-vocabulary scene understanding by associating Gaussian primitives with language features. These semantic attributes increase model storage, while most existing 3DGS compression methods are designed mainly to preserve RGB rendering quality. One straightforward approach is to apply sparsification and quantization sequentially. However, pruning based only on rendering quality can remove Gaussians that have small RGB contributions but are important for semantic prediction. Once removed, their semantic information cannot be recovered by later quantization. We propose ClunoGS, a compact framework for Language 3DGS that combines semantics-aware Gaussian sparsification and vector quantization in a unified constrained objective. Semantic supervision is used during sparsification, and the objective jointly considers rendering quality, semantic accuracy, and compactness. We optimize the unified objective with alternating primal, sparsification, quantization, and dual updates. We evaluate ClunoGS on open-vocabulary localization and segmentation using the LERF and ScanNet-10 benchmarks. Under aggressive compression, our unified, semantics-aware formulation substantially alleviates the degradation of semantic representations caused by sequential compression and semantics-agnostic Gaussian sparsification. Ablations further show that jointly coordinating sparsification and quantization better preserves semantic accuracy than applying them independently.

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

Topics: Computer science, Vector quantization, Gaussian, Artificial intelligence, Rendering (computer graphics), Quantization (signal processing)

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