Gen-LangSplat: Generalized Language Gaussian Splatting with Pre-Trained Feature Compression

• URL: http://arxiv.org/abs/2510.22930v1
• Date: Mon, 27 Oct 2025 02:13:38 GMT
• Title: Gen-LangSplat: Generalized Language Gaussian Splatting with Pre-Trained Feature Compression
• Abstract summary: We introduce Gen-LangSplat, that replaces the scene-wise autoencoder with a generalized autoencoder, pre-trained extensively on the large-scale ScanNet dataset.<n>This architectural shift enables the use of a fixed, compact latent space for language features across any new scene without any scene-specific training.<n>Our results demonstrate that generalized embeddings can efficiently and accurately support open-vocabulary querying in novel 3D scenes.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modeling open-vocabulary language fields in 3D is essential for intuitive human-AI interaction and querying within physical environments. State-of-the-art approaches, such as LangSplat, leverage 3D Gaussian Splatting to efficiently construct these language fields, encoding features distilled from high-dimensional models like CLIP. However, this efficiency is currently offset by the requirement to train a scene-specific language autoencoder for feature compression, introducing a costly, per-scene optimization bottleneck that hinders deployment scalability. In this work, we introduce Gen-LangSplat, that eliminates this requirement by replacing the scene-wise autoencoder with a generalized autoencoder, pre-trained extensively on the large-scale ScanNet dataset. This architectural shift enables the use of a fixed, compact latent space for language features across any new scene without any scene-specific training. By removing this dependency, our entire language field construction process achieves a efficiency boost while delivering querying performance comparable to, or exceeding, the original LangSplat method. To validate our design choice, we perform a thorough ablation study empirically determining the optimal latent embedding dimension and quantifying representational fidelity using Mean Squared Error and cosine similarity between the original and reprojected 512-dimensional CLIP embeddings. Our results demonstrate that generalized embeddings can efficiently and accurately support open-vocabulary querying in novel 3D scenes, paving the way for scalable, real-time interactive 3D AI applications.

Related papers

• MonoVoc: Decoupling Geometry and Semantics for Lightweight Monocular Open-Vocabulary 3D Gaussians [10.451279636801301]
  Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language.<n>We present a novel, training-free pipeline that fundamentally reimagines this paradigm by explicitly decoupling 3D geometric reconstruction from semantic integration.
  arXiv  Detail & Related papers  (2026-07-30T14:41:02Z)
• Ilov3Splat: Instance-Level Open-Vocabulary 3D Scene Understanding in Gaussian Splatting [32.46353940664006]
  Ilov3Splat is a framework for instance-level open-vocabulary 3D scene understanding built on 3D Gaussian Splatting (3D-GS)<n>We leverage multi-resolution hash embedding to efficiently encode language-aligned CLIP features.<n>At inference time, CLIP-encoded queries are matched against the learned features, followed by two-stage 3D clustering to retrieve relevant Gaussian groups.
  arXiv  Detail & Related papers  (2026-05-06T05:23:41Z)
• Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction [50.5449251266956]
  This paper addresses the task of large-scale 3D scene reconstruction from long video sequences.<n>Recent feed-forward reconstruction models have shown promising results by directly regressing 3D geometry from RGB images without explicit 3D priors or geometric constraints.<n>We propose a novel neural global context representation that efficiently compresses and retains long-range scene information.
  arXiv  Detail & Related papers  (2026-04-09T17:59:50Z)
• Point Cloud as a Foreign Language for Multi-modal Large Language Model [22.63554774942836]
  SAGE is the first end-to-end 3D MLLM that directly processes raw point clouds without relying on a pre-trained 3D encoder.<n>Our approach introduces a lightweight 3D tokenizer that combines geometric sampling and neighbourhood aggregation with vector quantization to convert point clouds into discrete tokens.
  arXiv  Detail & Related papers  (2026-03-10T04:22:40Z)
• Joint Semantic and Rendering Enhancements in 3D Gaussian Modeling with Anisotropic Local Encoding [86.55824709875598]
  We propose a joint enhancement framework for 3D semantic Gaussian modeling that synergizes both semantic and rendering branches.<n>Unlike conventional point cloud shape encoding, we introduce an anisotropic 3D Gaussian Chebyshev descriptor to capture fine-grained 3D shape details.<n>We employ a cross-scene knowledge transfer module to continuously update learned shape patterns, enabling faster convergence and robust representations.
  arXiv  Detail & Related papers  (2026-01-05T18:33:50Z)
• Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding [80.66591664266744]
  Lemon is a unified transformer architecture that processes 3D point cloud patches and language tokens as a single sequence.<n>To handle the complexity of 3D data, we develop a structured patchification and tokenization scheme that preserves spatial context.<n>Lemon establishes new state-of-the-art performance across comprehensive 3D understanding and reasoning tasks.
  arXiv  Detail & Related papers  (2025-12-14T20:02:43Z)
• Lang3D-XL: Language Embedded 3D Gaussians for Large-scale Scenes [23.445409551683213]
  Embedding a language field in a 3D representation enables richer semantic understanding of spatial environments.<n>We propose a novel approach to address challenges in semantic feature misalignment and inefficiency in memory and runtime.<n>We evaluate our method on the in-the-wild HolyScenes dataset and demonstrate that it surpasses existing approaches in both performance and efficiency.
  arXiv  Detail & Related papers  (2025-12-08T18:39:58Z)
• LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM [2.0524609401792397]
  We propose LEGO-SLAM, a framework to achieve real-time, open-vocabulary mapping within a 3DGS-based SLAM system.<n>At the core of our method is a scene-adaptive encoder-decoder that distills high-dimensional language embeddings into a compact 16-dimensional feature space.<n>Experiments demonstrate that LEGO-SLAM achieves competitive mapping quality and tracking accuracy, all while providing open-vocabulary capabilities at 15 FPS.
  arXiv  Detail & Related papers  (2025-11-20T08:31:34Z)
• OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting [52.40697058096931]
  3D Gaussian Splatting (3DGS) has emerged as a powerful representation for neural scene reconstruction.<n>We introduce an approach for open-vocabulary 3D instance segmentation without requiring manual labeling, termed OpenSplat3D.<n>We show results on LERF-mask and LERF-OVS as well as the full ScanNet++ validation set, demonstrating the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-06-09T12:37:15Z)
• On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation [52.96632954620623]
  We introduce a novel geometry-aware PEFT module specifically designed for 3D point cloud transformers.<n>Our approach sets a new benchmark for efficient, scalable, and geometry-aware fine-tuning of large-scale 3D point cloud models.
  arXiv  Detail & Related papers  (2025-05-28T15:08:36Z)
• Online Language Splatting [28.066910888210973]
  We introduce Online Language Splatting, the first framework to achieve online, near real-time, open-vocabulary language mapping within a 3DGS-SLAM system.<n>We show that our online method surpasses the state-of-the-art offline methods in accuracy and achieves more than 40x efficiency boost.
  arXiv  Detail & Related papers  (2025-03-12T14:49:24Z)
• Large Spatial Model: End-to-end Unposed Images to Semantic 3D [79.94479633598102]
  Large Spatial Model (LSM) processes unposed RGB images directly into semantic radiance fields. LSM simultaneously estimates geometry, appearance, and semantics in a single feed-forward operation. It can generate versatile label maps by interacting with language at novel viewpoints.
  arXiv  Detail & Related papers  (2024-10-24T17:54:42Z)
• GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane [53.388937705785025]
  3D open-vocabulary scene understanding is crucial for advancing augmented reality and robotic applications. We introduce GOI, a framework that integrates semantic features from 2D vision-language foundation models into 3D Gaussian Splatting (3DGS) Our method treats the feature selection process as a hyperplane division within the feature space, retaining only features that are highly relevant to the query.
  arXiv  Detail & Related papers  (2024-05-27T18:57:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.