# Unifying 3D Vision-Language Understanding via Promptable Queries

arXiv: https://arxiv.org/abs/2405.11442 · HTML: https://mlsanity.com/paper/2405.11442/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- Builds on 70 of its 81 references that are in the map.
- First posted on arXiv 19 May 2024.

## Builds on (most cited first, 30 of 70)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (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 Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [Perceiver IO: A General Architecture for Structured Inputs & Outputs](https://mlsanity.com/paper/2107.14795/) (2021)
- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [OpenScene: 3D Scene Understanding with Open Vocabularies](https://mlsanity.com/paper/2211.15654/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Scaling Open-Vocabulary Image Segmentation with Image-Level Labels](https://mlsanity.com/paper/2112.12143/) (2021)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [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)
- [PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation](https://mlsanity.com/paper/2004.01658/) (2020)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [Generalized Decoding for Pixel, Image, and Language](https://mlsanity.com/paper/2212.11270/) (2022)

## Built on by (most cited first, 30 of 70)

- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding](https://mlsanity.com/paper/2412.00493/) (2024)
- [GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models](https://mlsanity.com/paper/2501.01428/) (2025)
- [3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding](https://mlsanity.com/paper/2506.01946/) (2025)
- [SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding](https://mlsanity.com/paper/2412.04383/) (2024)
- [ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting](https://mlsanity.com/paper/2502.19459/) (2025)
- [Multi-modal Situated Reasoning in 3D Scenes](https://mlsanity.com/paper/2409.02389/) (2024)
- [Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation](https://mlsanity.com/paper/2507.04047/) (2025)
- [Detect Anything 3D in the Wild](https://mlsanity.com/paper/2504.07958/) (2025)
- [3DGraphLLM: Combining Semantic Graphs and Large Language Models for 3D Scene Understanding](https://mlsanity.com/paper/2412.18450/) (2024)
- [Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning](https://mlsanity.com/paper/2410.00255/) (2024)
- [A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions](https://mlsanity.com/paper/2406.05785/) (2024)
- [Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding](https://mlsanity.com/paper/2501.00358/) (2024)
- [Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis](https://mlsanity.com/paper/2503.22420/) (2025)
- [Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D](https://mlsanity.com/paper/2504.14151/) (2025)
- [Reasoning in Space via Grounding in the World](https://mlsanity.com/paper/2510.13800/) (2025)
- [LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding](https://mlsanity.com/paper/2505.12253/) (2025)
- [Unifying 2D and 3D Vision-Language Understanding](https://mlsanity.com/paper/2503.10745/) (2025)
- [Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding](https://mlsanity.com/paper/2504.19500/) (2025)
- [3D Question Answering via only 2D Vision-Language Models](https://mlsanity.com/paper/2505.22143/) (2025)
- [Uni4D-LLM: A Unified SpatioTemporal-Aware VLM for 4D Understanding and Generation](https://mlsanity.com/paper/2509.23828/) (2025)
- [Task-oriented Sequential Grounding and Navigation in 3D Scenes](https://mlsanity.com/paper/2408.04034/) (2024)
- [DSPNet: Dual-vision Scene Perception for Robust 3D Question Answering](https://mlsanity.com/paper/2503.03190/) (2025)
- [ASHiTA: Automatic Scene-grounded HIerarchical Task Analysis](https://mlsanity.com/paper/2504.06553/) (2025)
- [ViewSRD: 3D Visual Grounding via Structured Multi-View Decomposition](https://mlsanity.com/paper/2507.11261/) (2025)
- [SceneCOT: Eliciting Grounded Chain-of-Thought Reasoning in 3D Scenes](https://mlsanity.com/paper/2510.16714/) (2025)
- [CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting](https://mlsanity.com/paper/2412.19142/) (2024)
- [ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding](https://mlsanity.com/paper/2501.01366/) (2025)
- [From Thousands to Billions: 3D Visual Language Grounding via Render-Supervised Distillation from 2D VLMs](https://mlsanity.com/paper/2502.20389/) (2025)
- [Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding](https://mlsanity.com/paper/2603.19235/) (2026)

## Abstract (arXiv)

A unified model for 3D vision-language (3D-VL) understanding is expected to take various scene representations and perform a wide range of tasks in a 3D scene. However, a considerable gap exists between existing methods and such a unified model, due to the independent application of representation and insufficient exploration of 3D multi-task training. In this paper, we introduce PQ3D, a unified model capable of using Promptable Queries to tackle a wide range of 3D-VL tasks, from low-level instance segmentation to high-level reasoning and planning. This is achieved through three key innovations: (1) unifying various 3D scene representations (i.e., voxels, point clouds, multi-view images) into a shared 3D coordinate space by segment-level grouping, (2) an attention-based query decoder for task-specific information retrieval guided by prompts, and (3) universal output heads for different tasks to support multi-task training. Tested across ten diverse 3D-VL datasets, PQ3D demonstrates impressive performance on these tasks, setting new records on most benchmarks. Particularly, PQ3D improves the state-of-the-art on ScanNet200 by 4.9% (AP25), ScanRefer by 5.4% (acc@0.5), Multi3DRefer by 11.7% (F1@0.5), and Scan2Cap by 13.4% (CIDEr@0.5). Moreover, PQ3D supports flexible inference with individual or combined forms of available 3D representations, e.g., solely voxel input.