Scaling Diverse Language Generation for 3D Visual Grounding

• URL: http://arxiv.org/abs/2606.20946v1
• Date: Thu, 18 Jun 2026 21:20:20 GMT
• Title: Scaling Diverse Language Generation for 3D Visual Grounding
• Abstract summary: ViGiL3D++ is a scalable, scene-agnostic method that generates diverse visual grounding queries.<n>We show that it has greater diversity over existing scaled datasets and improves model performance over several 3DVG benchmarks.
• Score: 14.535096337338544
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Developing robust models for 3D visual grounding (3DVG), the localization of entities in a 3D scene described in natural language, is important for enabling agents to correspond spatial language with objects in the physical world. However, the lack of diverse descriptions at scale prevents models from generalizing beyond simple linguistic patterns. Recent such attempts lack diversity in the constraint types and language used to ground objects. Captioning methods cannot precisely contrast objects, which is important for visual grounding. We therefore propose ViGiL3D++, a scalable, scene-agnostic method that generates diverse visual grounding queries by combining constraint sampling in scene graphs with the language generation of LLMs. We show that it has greater diversity over existing scaled datasets and improves model performance over several 3DVG benchmarks but also illuminates outstanding limitations of VLMs.

Related papers

• PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding [45.510721162264666]
  3D Visual Grounding aims to localize target objects in 3D scenes given natural language descriptions.<n>Existing approaches typically perform reasoning over the entire scene, leading to ambiguous predictions and high computational cost.<n>We propose PruneGround, an effective plug-and-play framework for 3DVG built upon three key components.
  arXiv  Detail & Related papers  (2026-06-30T05:21:11Z)
• Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM [71.01178857331969]
  Chat-Scene++ is an MLLM framework that represents 3D scenes as context-rich object sequences.<n>By structuring scenes as sequences of objects with contextual semantics, Chat-Scene++ enables object-centric representation and interaction.<n>Chat-Scene++ achieves state-of-the-art performance on five major 3D vision-language benchmarks.
  arXiv  Detail & Related papers  (2026-03-29T04:16:04Z)
• GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond [56.677984098204696]
  multimodal language models are driving the development of 3D Vision-Language Models (VLMs)<n>We propose a scene-centric 3D VLM for 3D Gaussian splat scenes that employs language- and task-aware scene representations.<n>We present the first Gaussian splatting-based VLM, leveraging photorealistic 3D representations derived from standard RGB images.
  arXiv  Detail & Related papers  (2025-07-01T15:52:59Z)
• AugRefer: Advancing 3D Visual Grounding via Cross-Modal Augmentation and Spatial Relation-based Referring [49.78120051062641]
  3D visual grounding aims to correlate a natural language description with the target object within a 3D scene.<n>Existing approaches commonly encounter a shortage of text3D pairs available for training.<n>We propose AugRefer, a novel approach for advancing 3D visual grounding.
  arXiv  Detail & Related papers  (2025-01-16T09:57:40Z)
• ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding [9.289977174410824]
  3D visual grounding involves localizing entities in a 3D scene referred to by natural language text.<n>We introduce Visual Grounding with Diverse Language in 3D (ViGiL3D), a diagnostic dataset for evaluating visual grounding methods against a diverse set of language patterns.
  arXiv  Detail & Related papers  (2025-01-02T17:20:41Z)
• g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks [62.74304008688472]
  Generalizable 3D-Language Feature Fields (g3D-LF) is a 3D representation model pre-trained on large-scale 3D-language dataset for embodied tasks.
  arXiv  Detail & Related papers  (2024-11-26T01:54:52Z)
• 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)
• SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding [37.47195477043883]
  3D vision-language grounding, which focuses on aligning language with the 3D physical environment, stands as a cornerstone in the development of embodied agents. We introduce the first million-scale 3D vision-language dataset, SceneVerse, encompassing about 68K 3D indoor scenes. We demonstrate this scaling allows for a unified pre-training framework, Grounded Pre-training for Scenes (GPS) for 3D vision-language learning.
  arXiv  Detail & Related papers  (2024-01-17T17:04:35Z)
• LanguageRefer: Spatial-Language Model for 3D Visual Grounding [72.7618059299306]
  We develop a spatial-language model for a 3D visual grounding problem. We show that our model performs competitively on visio-linguistic datasets proposed by ReferIt3D.
  arXiv  Detail & Related papers  (2021-07-07T18:55:03Z)

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.