GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting

• URL: http://arxiv.org/abs/2609.09082v1
• Date: Tue, 08 Sep 2026 17:31:51 GMT
• Title: GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting
• Abstract summary: We use a vision-language model purely as a translator.<n>It produces structured, entity-level descriptions of each posed image.<n>On ScanNet++, our pipeline is competitive with strong annotation free baselines trained on ScanNet.
• Score: 1.2234742322758418
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Open vocabulary 3D semantic segmentation methods typically lift CLIP features into 3D. This embeds points in a joint vision-language space known to behave like a bag-of-words on compositional tasks. Furthermore, even annotation free variants often require a large 3D training corpus and a dedicated 3D encoder per domain. Instead we use a vision-language model purely as a translator. It produces structured, entity-level descriptions of each posed image. These descriptions are grounded, projected, and aggregated directly in a general-purpose, language-only embedding space, with no 3D training corpus or encoder required. On ScanNet++, our pipeline is competitive with strong annotation free baselines trained on ScanNet. On a 5-building cultural heritage benchmark, raw scores initially favor a CLIP-based variant, but a single systematic vocabulary correction reverses this ranking. An effect confirmed by a second, independent correction on a different class, indicating that language-space embeddings track physical content more faithfully. This fidelity extends to genuinely out-of-vocabulary (OOV) objects on ScanNet++ proving that language-space embeddings separate presence from absence objects far more sharply than CLIP-based embeddings do. GoDeep also localize these OOV objects within the scene, all without any 2D-3D annotation. Because every representation remains discrete text, predictions are also explainable at the point level. Finally, exploiting both a heuristic weighting, that favors precise over merely frequent observations and GoDeep's explainability property, we propose an aggregation strategy, as a proof of concept, that favors finer elements localization.

Related papers

• Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis [59.527737790821305]
  We propose a relationship-aware framework that uses 3D scene graphs to enhance open-vocabulary 3D understanding.<n>Our method constructs relational scene graphs from multi-view observations by leveraging vision-language reasoning to infer object relationships.<n>Experiments on ScanNetV2, ScanNet200, ScanNet$++$, and Replica demonstrate strong performance and generalization ability.
  arXiv  Detail & Related papers  (2026-07-06T17:29:49Z)
• 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)
• GALA: Guided Attention with Language Alignment for Open Vocabulary Gaussian Splatting [74.56128224977279]
  We present GALA, a novel framework for open-vocabulary 3D scene understanding with 3D Gaussian Splatting (3DGS)<n>GALA distills a scene-specific 3D instance feature field via self-supervised contrastive learning.<n>It supports seamless 2D and 3D open-vocabulary queries and reduces memory consumption by avoiding per-Gaussian high-dimensional feature learning.
  arXiv  Detail & Related papers  (2025-08-19T21:26:49Z)
• A Neural Representation Framework with LLM-Driven Spatial Reasoning for Open-Vocabulary 3D Visual Grounding [78.99798110890157]
  Open-vocabulary 3D visual grounding aims to localize target objects based on free-form language queries.<n>Existing language field methods struggle to accurately localize instances using spatial relations in language queries.<n>We propose SpatialReasoner, a novel neural representation-based framework with large language model (LLM)-driven spatial reasoning.
  arXiv  Detail & Related papers  (2025-07-09T10:20:38Z)
• PGOV3D: Open-Vocabulary 3D Semantic Segmentation with Partial-to-Global Curriculum [20.206273757144547]
  PGOV3D is a novel framework that introduces a Partial-to-Global curriculum for improving open-vocabulary 3D semantic segmentation.<n>We pre-train the model on partial scenes that provide dense semantic information but relatively simple geometry.<n>In the second stage, we fine-tune the model on complete scene-level point clouds, which are sparser and structurally more complex.
  arXiv  Detail & Related papers  (2025-06-30T08:13:07Z)
• 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.<n>Current methods struggle because they rely heavily on fine-tuning with 3D annotations and mask proposals.<n>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)
• 3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation [20.7179907935644]
  3D-AVS is a method for Auto-Vocabulary of 3D point clouds for which the vocabulary is unknown and auto-generated for each input at runtime.<n>3D-AVS first recognizes semantic entities from image or point cloud data and then segments all points with the automatically generated vocabulary.<n>Our method incorporates both image-based and point-based recognition, enhancing robustness under challenging lighting conditions.
  arXiv  Detail & Related papers  (2024-06-13T13:59:47Z)
• Segment Any 3D Object with Language [58.471327490684295]
  We introduce Segment any 3D Object with LanguagE (SOLE), a semantic geometric and-aware visual-language learning framework with strong generalizability. Specifically, we propose a multimodal fusion network to incorporate multimodal semantics in both backbone and decoder. Our SOLE outperforms previous methods by a large margin on ScanNetv2, ScanNet200, and Replica benchmarks.
  arXiv  Detail & Related papers  (2024-04-02T17:59:10Z)
• 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)
• EDA: Explicit Text-Decoupling and Dense Alignment for 3D Visual Grounding [4.447173454116189]
  3D visual grounding aims to find the object within point clouds mentioned by free-form natural language descriptions with rich semantic cues. We present EDA that Explicitly Decouples the textual attributes in a sentence. We further introduce a new visual grounding task, locating objects without object names, which can thoroughly evaluate the model's dense alignment capacity.
  arXiv  Detail & Related papers  (2022-09-29T17:00:22Z)

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.