CORTEXA
← Browse
arxivcs.CV2026-07-03

Holo-Captioning: Toward the Text Equivalent of 3D Scenes

Kun-Yu Lin, Chengke Bu, Zhenguo Li, Kai Han

This work introduces holo-captioning, a novel task that strives to seek the text equivalent of 3D scenes. As the initial step, we formulate holo-captioning as generating a structured textual description that comprehensively depicts all entities within a 3D scene -- including their semantic tags, spatial locations, attributes, and inter-entity relations. To tackle this challenging task, we first develop an effective captioning engine to produce detailed descriptions of individual entity instances and instance pairs, and contribute a large-scale benchmark comprising over 15K scenes for training and evaluation. Building upon this foundation, we propose HoloScribe, a novel model that features an instance-aware decoupled pipeline for generating structured holo-captions, and further incorporates anchor-aware instance linking to identify relational instance pairs. Additionally, we propose a comprehensive evaluation metric named HoloScore, and provide a human-curated test set to ensure reliable model assessment. Experimental results demonstrate that HoloScribe significantly outperforms state-of-the-art 3D dense captioners and 3D LLM generalists, underscoring the effectiveness of our approach. Project page: https://visual-ai.github.io/holocap/

View free PDFSource page

Related papers

arxivcs.CVcs.AI2026-07-07

PVCap: Towards Accurate 3D Dense Captioning via PseudoCap and VoxelCapNet

Xiaopei Wu, Chenshu Hou, Liang Peng, Dan Xu, Binbin Lin, Xiaoshui Huang, et al.

3D dense captioning, an emerging vision-language task, aims to generate descriptive sentences for each object in the 3D scene. Despite the impressive results achieved by previous methods, they suffer from two limitations. First, current research often employs global rigid transfo…

View free PDFSource page
arxivcs.CVcs.RO2026-07-06

Beyond Isolated Objects: Relationship-aware Open Vocabulary Scene Understanding via 3D Scene Graph Analysis

Xianhao Chen, Jiarui Hu, Yuanbo Yang, Xiyu Zhang, Tengyue Wang, Hujun Bao, et al.

Open-vocabulary 3D scene understanding aims to segment 3D scenes beyond predefined categories by transferring semantic knowledge from vision-language models. Existing methods have advanced this task by lifting language-aligned 2D features into 3D, yet they often rely on context-i…

View free PDFSource page
arxivcs.AIcs.CV2026-07-02

Text-Driven 3D Indoor Scene Synthesis in Non-Manhattan Environments

Xianhui Meng, Zirui Song, Yuchen Zhang, Li Zhang, Yongxuan Lv, Xiuying Chen, et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in 3D indoor synthesis for Manhattan environments. However, existing methods often fail to capture plausible object layout patterns in non-Manhattan settings, primarily because they struggle to model non-ortho…

View free PDFSource page
arxivcs.CV2026-06-28

NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation

Cheng Wan, Yongsen Mao, Wenzheng Wu, Yuxuan Xie, Chucheng Xiang, Runze Wang, et al.

Recently, Large Language Models (LLMs) have emerged as promising layout agents for 3D scene generation. Existing layout agents still suffer from implausible layout generation because most of them convert 3D assets and 3D layouts into textual descriptions as inputs and outputs, wh…

View free PDFSource page
arxivcs.CV2026-07-07

CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models

He Liang, Chenyang Ma, Yiming Zhang, Sangyun Shin, Andrew Markham, Niki Trigoni, et al.

Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world household environments containing multiple interconnected rooms and diverse object categories. We in…

View free PDFSource page
arxivcs.CVcs.AIcs.GReess.IV2026-06-25

From Scene-Centric to Observer-Centric: Modeling Observer-Aware Relations for 3D Scene Graph Generation

Jingjun Sun, Chaowei Wang, Zhirui Liu, Jiaxu Tian, Ming Yang, Yaoxing Wang, et al.

3D Scene Graph Generation (3DSGG) represents 3D scenes as structured object--relation--object graphs for spatial understanding. In observer-centric spatial perception, the same scene may be expressed under different local observer frames while its structure remains unchanged. How…

View free PDFSource page