LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding

• URL: http://arxiv.org/abs/2412.17635v2
• Date: Tue, 24 Dec 2024 02:48:55 GMT
• Title: LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding
• Authors: Hao Li, Roy Qin, Zhengyu Zou, Diqi He, Bohan Li, Bingquan Dai, Dingewn Zhang, Junwei Han,
• Abstract summary: LangSurf is a language-Embedded Surface Field that aligns 3D language fields with the surface of objects.<n>Our method is capable of segmenting objects in 3D space, thus boosting the effectiveness of our approach in instance recognition, removal, and editing.
• Score: 42.750252190275546
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Applying Gaussian Splatting to perception tasks for 3D scene understanding is becoming increasingly popular. Most existing works primarily focus on rendering 2D feature maps from novel viewpoints, which leads to an imprecise 3D language field with outlier languages, ultimately failing to align objects in 3D space. By utilizing masked images for feature extraction, these approaches also lack essential contextual information, leading to inaccurate feature representation. To this end, we propose a Language-Embedded Surface Field (LangSurf), which accurately aligns the 3D language fields with the surface of objects, facilitating precise 2D and 3D segmentation with text query, widely expanding the downstream tasks such as removal and editing. The core of LangSurf is a joint training strategy that flattens the language Gaussian on the object surfaces using geometry supervision and contrastive losses to assign accurate language features to the Gaussians of objects. In addition, we also introduce the Hierarchical-Context Awareness Module to extract features at the image level for contextual information then perform hierarchical mask pooling using masks segmented by SAM to obtain fine-grained language features in different hierarchies. Extensive experiments on open-vocabulary 2D and 3D semantic segmentation demonstrate that LangSurf outperforms the previous state-of-the-art method LangSplat by a large margin. As shown in Fig. 1, our method is capable of segmenting objects in 3D space, thus boosting the effectiveness of our approach in instance recognition, removal, and editing, which is also supported by comprehensive experiments. \url{https://langsurf.github.io}.

Related papers

• ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning [68.4209681278336]
  Open-vocabulary 3D visual grounding and reasoning aim to localize objects in a scene based on implicit language descriptions. Current methods struggle because they rely heavily on fine-tuning with 3D annotations and mask proposals. We propose ReasonGrounder, an LVLM-guided framework that uses hierarchical 3D feature Gaussian fields for adaptive grouping.
  arXiv  Detail & Related papers  (2025-03-30T03:40:35Z)
• MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation [87.30919771444117]
  Reasoning segmentation aims to segment target objects in complex scenes based on human intent and spatial reasoning. Recent multimodal large language models (MLLMs) have demonstrated impressive 2D image reasoning segmentation. We introduce MLLM-For3D, a framework that transfers knowledge from 2D MLLMs to 3D scene understanding.
  arXiv  Detail & Related papers  (2025-03-23T16:40:20Z)
• Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration [41.046653227409564]
  Dr. Splat is a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Our method associates language-aligned CLIP embeddings with 3D Gaussians for holistic 3D scene understanding. Experiments demonstrate that our approach significantly outperforms existing approaches in 3D perception benchmarks.
  arXiv  Detail & Related papers  (2025-02-23T17:01:14Z)
• SuperGSeg: Open-Vocabulary 3D Segmentation with Structured Super-Gaussians [77.77265204740037]
  3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. We introduce SuperGSeg, a novel approach that fosters cohesive, context-aware scene representation. SuperGSeg outperforms prior works on both open-vocabulary object localization and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2024-12-13T16:01:19Z)
• Occam's LGS: A Simple Approach for Language Gaussian Splatting [57.00354758206751]
  We show that sophisticated techniques for language-grounded 3D Gaussian Splatting are simply unnecessary.<n>We apply Occam's razor to the task at hand and perform weighted multi-view feature aggregation.<n>Our results offer us state-of-the-art results with a speed-up of two orders of magnitude.
  arXiv  Detail & Related papers  (2024-12-02T18:50:37Z)
• XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation [72.12250272218792]
  We propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. We integrate 3D global features as implicit conditions into the pre-trained 2D denoising UNet, enabling the generation of segmentation masks. The generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings.
  arXiv  Detail & Related papers  (2024-11-20T12:02:12Z)
• Enforcing View-Consistency in Class-Agnostic 3D Segmentation Fields [46.711276257688326]
  Radiance Fields have become a powerful tool for modeling 3D scenes from multiple images. Some methods work well using 2D semantic masks, but they generalize poorly to class-agnostic segmentations. More recent methods circumvent this issue by using contrastive learning to optimize a high-dimensional 3D feature field instead.
  arXiv  Detail & Related papers  (2024-08-19T12:07:24Z)
• RefMask3D: Language-Guided Transformer for 3D Referring Segmentation [32.11635464720755]
  RefMask3D aims to explore the comprehensive multi-modal feature interaction and understanding. RefMask3D outperforms previous state-of-the-art method by a large margin of 3.16% mIoU on the challenging ScanRefer dataset.
  arXiv  Detail & Related papers  (2024-07-25T17:58:03Z)
• Grounded 3D-LLM with Referent Tokens [58.890058568493096]
  We propose Grounded 3D-LLM to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision tasks into language formats.
  arXiv  Detail & Related papers  (2024-05-16T18:03:41Z)
• Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting [27.974762304763694]
  We introduce Semantic Gaussians, a novel open-vocabulary scene understanding approach based on 3D Gaussian Splatting. Unlike existing methods, we design a versatile projection approach that maps various 2D semantic features into a novel semantic component of 3D Gaussians. We build a 3D semantic network that directly predicts the semantic component from raw 3D Gaussians for fast inference.
  arXiv  Detail & Related papers  (2024-03-22T21:28:19Z)
• LangSplat: 3D Language Gaussian Splatting [42.16849512832556]
  LangSplat constructs a 3D language field that enables precise and efficient open-vocabulary querying within 3D spaces. LangSplat significantly outperforms the previous state-of-the-art method LERF by a large margin.
  arXiv  Detail & Related papers  (2023-12-26T15:14:37Z)
• Language Embedded 3D Gaussians for Open-Vocabulary Scene Understanding [2.517953665531978]
  We introduce Language Embedded 3D Gaussians, a novel scene representation for open-vocabulary query tasks. Our representation achieves the best visual quality and language querying accuracy across current language-embedded representations.
  arXiv  Detail & Related papers  (2023-11-30T11:50:07Z)
• 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)

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.