# LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual Preferences

arXiv: https://arxiv.org/abs/2412.01292 · HTML: https://mlsanity.com/paper/2412.01292/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 35 of its 49 references that are in the map.
- First posted on arXiv 2 Dec 2024.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 35)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model](https://mlsanity.com/paper/2304.15010/) (2023)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments](https://mlsanity.com/paper/2004.02857/) (2020)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario](https://mlsanity.com/paper/2305.14836/) (2023)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following](https://mlsanity.com/paper/2309.00615/) (2023)
- [RIO: 3D Object Instance Re-Localization in Changing Indoor Environments](https://mlsanity.com/paper/1908.06109/) (2019)
- [Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers](https://mlsanity.com/paper/2312.08168/) (2023)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding](https://mlsanity.com/paper/2401.09340/) (2024)
- [Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes](https://mlsanity.com/paper/2308.08769/) (2023)
- [LiDAR-LLM: Exploring the Potential of Large Language Models for 3D LiDAR Understanding](https://mlsanity.com/paper/2312.14074/) (2023)
- [OccLLaMA: An Occupancy-Language-Action Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2409.03272/) (2024)
- [End-to-End 3D Dense Captioning with Vote2Cap-DETR](https://mlsanity.com/paper/2301.02508/) (2023)

## Built on by (most cited first, 30 of 38)

- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [SpatialLM: Training Large Language Models for Structured Indoor Modeling](https://mlsanity.com/paper/2506.07491/) (2025)
- [3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding](https://mlsanity.com/paper/2507.23478/) (2025)
- [LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding](https://mlsanity.com/paper/2505.12253/) (2025)
- [Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation](https://mlsanity.com/paper/2506.03583/) (2025)
- [GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond](https://mlsanity.com/paper/2507.00886/) (2025)
- [Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs](https://mlsanity.com/paper/2506.05318/) (2025)
- [SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models](https://mlsanity.com/paper/2505.04911/) (2025)
- [Understanding Dynamic Scenes in Ego Centric 4D Point Clouds](https://mlsanity.com/paper/2508.07251/) (2025)
- [LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning](https://mlsanity.com/paper/2506.09935/) (2025)
- [SpatialMosaic: A Multiview VLM Dataset for Partial Visibility](https://mlsanity.com/paper/2512.23365/) (2025)
- [Zoo3D: Zero-Shot 3D Object Detection at Scene Level](https://mlsanity.com/paper/2511.20253/) (2025)
- [3D Instruction Ambiguity Detection](https://mlsanity.com/paper/2601.05991/) (2026)
- [Open-Vocabulary Functional 3D Human-Scene Interaction Generation](https://mlsanity.com/paper/2601.20835/) (2026)
- [Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model](https://mlsanity.com/paper/2510.11509/) (2025)
- [MosaicThinker: On-Device Visual Spatial Reasoning for Embodied AI via Iterative Construction of Space Representation](https://mlsanity.com/paper/2602.07082/) (2026)
- [C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning](https://mlsanity.com/paper/2602.10551/) (2026)
- [SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs](https://mlsanity.com/paper/2602.22716/) (2026)
- [Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models](https://mlsanity.com/paper/2603.18002/) (2026)
- [Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM](https://mlsanity.com/paper/2603.27507/) (2026)
- [TUN3D: Towards Real-World Scene Understanding from Unposed Images](https://mlsanity.com/paper/2509.21388/) (2025)
- [Error-Driven Scene Editing for 3D Grounding in Large Language Models](https://mlsanity.com/paper/2511.14086/) (2025)
- [Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding](https://mlsanity.com/paper/2512.12822/) (2025)
- [Temporal Visual Semantics-Induced Human Motion Understanding with Large Language Models](https://mlsanity.com/paper/2512.22249/) (2025)
- [Efficient Encoder-Free Fourier-based 3D Large Multimodal Model](https://mlsanity.com/paper/2602.23153/) (2026)
- [VistaGEN: Consistent Driving Video Generation with Fine-Grained Control Using Multiview Visual-Language Reasoning](https://mlsanity.com/paper/2603.28353/) (2026)
- [ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning](https://mlsanity.com/paper/2607.17599/) (2026)
- [D3VL: Understanding Driving Scenes from 3D Time Series Data and Video with Language Models](https://mlsanity.com/paper/2607.19528/) (2026)
- [VoxRep: Enhancing 3D Spatial Understanding in 2D Vision-Language Models via Voxel Representation](https://mlsanity.com/paper/2503.21214/) (2025)
- [Scenes as Tokens: Multi-Scale Normal Distributions Transform Tokenizer for General 3D Vision-Language Understanding](https://mlsanity.com/paper/2511.21191/) (2025)

## Abstract (arXiv)

Research on 3D Vision-Language Models (3D-VLMs) is gaining increasing attention, which is crucial for developing embodied AI within 3D scenes, such as visual navigation and embodied question answering. Due to the high density of visual features, especially in large 3D scenes, accurately locating task-relevant visual information is challenging. Existing works attempt to segment all objects and consider their features as scene representations. However, these task-agnostic object features include much redundant information and missing details for the task-relevant area. To tackle these problems, we propose LSceneLLM, an adaptive framework that automatically identifies task-relevant areas by leveraging LLM's visual preference for different tasks, followed by a plug-and-play scene magnifier module to capture fine-grained details in focused areas. Specifically, a dense token selector examines the attention map of LLM to identify visual preferences for the instruction input. It then magnifies fine-grained details of the focusing area. An adaptive self-attention module is leveraged to fuse the coarse-grained and selected fine-grained visual information. To comprehensively evaluate the large scene understanding ability of 3D-VLMs, we further introduce a cross-room understanding benchmark, XR-Scene, which contains a series of large scene understanding tasks including XR-QA, XR-EmbodiedPlanning, and XR-SceneCaption. Experiments show that our method surpasses existing methods on both large scene understanding and existing scene understanding benchmarks. Plunging our scene magnifier module into the existing 3D-VLMs also brings significant improvement.