Taking Language Embedded 3D Gaussian Splatting into the Wild

• URL: http://arxiv.org/abs/2507.19830v2
• Date: Tue, 05 Aug 2025 01:40:57 GMT
• Title: Taking Language Embedded 3D Gaussian Splatting into the Wild
• Authors: Yuze Wang, Yue Qi,
• Abstract summary: We propose a novel framework for open-vocabulary scene understanding from unconstrained photo collections.<n>Specifically, we first render multiple appearance images from the same viewpoint, then extract multi-appearance CLIP features.<n>We then propose a transient uncertainty-aware autoencoder, a multi-appearance language field 3DGS representation, and a post-ensemble strategy to effectively compress, learn, and fuse language features.
• Score: 6.550474097747006
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in leveraging large-scale Internet photo collections for 3D reconstruction have enabled immersive virtual exploration of landmarks and historic sites worldwide. However, little attention has been given to the immersive understanding of architectural styles and structural knowledge, which remains largely confined to browsing static text-image pairs. Therefore, can we draw inspiration from 3D in-the-wild reconstruction techniques and use unconstrained photo collections to create an immersive approach for understanding the 3D structure of architectural components? To this end, we extend language embedded 3D Gaussian splatting (3DGS) and propose a novel framework for open-vocabulary scene understanding from unconstrained photo collections. Specifically, we first render multiple appearance images from the same viewpoint as the unconstrained image with the reconstructed radiance field, then extract multi-appearance CLIP features and two types of language feature uncertainty maps-transient and appearance uncertainty-derived from the multi-appearance features to guide the subsequent optimization process. Next, we propose a transient uncertainty-aware autoencoder, a multi-appearance language field 3DGS representation, and a post-ensemble strategy to effectively compress, learn, and fuse language features from multiple appearances. Finally, to quantitatively evaluate our method, we introduce PT-OVS, a new benchmark dataset for assessing open-vocabulary segmentation performance on unconstrained photo collections. Experimental results show that our method outperforms existing methods, delivering accurate open-vocabulary segmentation and enabling applications such as interactive roaming with open-vocabulary queries, architectural style pattern recognition, and 3D scene editing.

Related papers

• LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion [21.828264119753502]
  LangScene-X is a novel generative framework to unify and generate 3D consistent multi-modality information.<n>Powered by the generative capability of creating more consistent novel observations, we can build generalizable 3D language-embedded scenes from only sparse views.
  arXiv  Detail & Related papers  (2025-07-03T17:21:23Z)
• CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image [18.445769892372528]
  We introduce CATSplat, a novel generalizable transformer-based framework for single-view 3D scene reconstruction.<n>By incorporating scene-specific contextual details from text embeddings through cross-attention, we pave the way for context-aware reconstruction.<n>Experiments on large-scale datasets demonstrate the state-of-the-art performance of CATSplat in single-view 3D scene reconstruction.
  arXiv  Detail & Related papers  (2024-12-17T13:32:04Z)
• 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)
• Open-Vocabulary 3D Semantic Segmentation with Text-to-Image Diffusion Models [57.37244894146089]
  We propose Diff2Scene, which leverages frozen representations from text-image generative models, along with salient-aware and geometric-aware masks, for open-vocabulary 3D semantic segmentation and visual grounding tasks. We show that it outperforms competitive baselines and achieves significant improvements over state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-18T16:20:56Z)
• Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding [39.55810156545949]
  We propose a Multimodal Alignment (DMA) framework to densely co-embed different modalities into a common space. Our DMA method produces highly competitive open-vocabulary segmentation performance on various indoor and outdoor tasks.
  arXiv  Detail & Related papers  (2024-07-13T05:39:17Z)
• TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes [67.5351491691866]
  We present a novel framework, dubbed TeMO, to parse multi-object 3D scenes and edit their styles. Our method can synthesize high-quality stylized content and outperform the existing methods over a wide range of multi-object 3D meshes.
  arXiv  Detail & Related papers  (2023-12-07T12:10:05Z)
• Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding [57.47315482494805]
  Open-world instance-level scene understanding aims to locate and recognize unseen object categories that are not present in the annotated dataset. This task is challenging because the model needs to both localize novel 3D objects and infer their semantic categories. We propose to harness pre-trained vision-language (VL) foundation models that encode extensive knowledge from image-text pairs to generate captions for 3D scenes.
  arXiv  Detail & Related papers  (2023-08-01T07:50:14Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision [50.07532560364523]
  We present a new, large-scale dataset of landmark photo collections that contains descriptive text in the form of captions and hierarchical category names. WikiScenes forms a new testbed for multimodal reasoning involving images, text, and 3D geometry.
  arXiv  Detail & Related papers  (2021-08-12T17:16:49Z)

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.