Cover Image

Do 3D Large Language Models Really Understand 3D Spatial Relationships?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ma, Xianzheng, Sun, Tao, Chen, Shuai, Bhalgat, Yash, Gu, Jindong, Chang, Angel X, Armeni, Iro, Laina, Iro, Peng, Songyou, Prisacariu, Victor Adrian
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections
by: Wu, Jing, et al.
Published: (2025)

When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models
by: Ma, Xianzheng, et al.
Published: (2024)

Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
by: Smart, Brandon, et al.
Published: (2024)

3D-Aware Instance Segmentation and Tracking in Egocentric Videos
by: Bhalgat, Yash, et al.
Published: (2024)

N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
by: Bhalgat, Yash, et al.
Published: (2024)

ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing
by: Bucher, Martin JJ., et al.
Published: (2025)

DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing
by: Chen, Minghao, et al.
Published: (2024)

SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
by: Singh, Binod, et al.
Published: (2025)

Volumetric Semantically Consistent 3D Panoptic Mapping
by: Miao, Yang, et al.
Published: (2023)

MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps
by: Zheng, Jianhao, et al.
Published: (2024)

Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments
by: Zhu, Liyuan, et al.
Published: (2023)

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting
by: Engstler, Paul, et al.
Published: (2024)

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos
by: Tschernezki, Vadim, et al.
Published: (2025)

GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer
by: Sarkar, Sayan Deb, et al.
Published: (2025)

WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
by: Zheng, Jianhao, et al.
Published: (2025)

Active View Selector: Fast and Accurate Active View Selection with Cross Reference Image Quality Assessment
by: Wang, Zirui, et al.
Published: (2025)

GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting
by: Liu, Changkun, et al.
Published: (2024)

SynCity: Training-Free Generation of 3D Worlds
by: Engstler, Paul, et al.
Published: (2025)

CrossOver: 3D Scene Cross-Modal Alignment
by: Sarkar, Sayan Deb, et al.
Published: (2025)

ReScene4D: Temporally Consistent Semantic Instance Segmentation of Evolving Indoor 3D Scenes
by: Steiner, Emily, et al.
Published: (2026)

GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator
by: Zhu, Liyuan, et al.
Published: (2026)

LoopSplat: Loop Closure by Registering 3D Gaussian Splats
by: Zhu, Liyuan, et al.
Published: (2024)

EPIC Fields: Marrying 3D Geometry and Video Understanding
by: Tschernezki, Vadim, et al.
Published: (2023)

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
by: Jiang, Zeren, et al.
Published: (2025)

Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video
by: Jiang, Zeren, et al.
Published: (2026)

ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
by: Zhu, Liyuan, et al.
Published: (2025)

Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching
by: Pan, Yue, et al.
Published: (2025)

IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation
by: Melas-Kyriazi, Luke, et al.
Published: (2024)

Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change
by: Sun, Tao, et al.
Published: (2023)

Deep Sketch-Based 3D Modeling: A Survey
by: Tono, Alberto, et al.
Published: (2026)

Deep Sketch‐Based 3D Modeling: A Survey
by: Alberto Tono, et al.
Published: (2026)

Multiway Point Cloud Mosaicking with Diffusion and Global Optimization
by: Jin, Shengze, et al.
Published: (2024)

HouseTour: A Virtual Real Estate A(I)gent
by: Çelen, Ata, et al.
Published: (2025)

WildPose: A Unified Framework for Robust Pose Estimation in the Wild
by: Zheng, Jianhao, et al.
Published: (2026)

Neural Refinement for Absolute Pose Regression with Feature Synthesis
by: Chen, Shuai, et al.
Published: (2023)

When Do Diffusion Models learn to Generate Multiple Objects?
by: Jeong, Yujin, et al.
Published: (2026)

Rectified Point Flow: Generic Point Cloud Pose Estimation
by: Sun, Tao, et al.
Published: (2025)

Diffusion Models for Open-Vocabulary Segmentation
by: Karazija, Laurynas, et al.
Published: (2023)

Learning segmentation from point trajectories
by: Karazija, Laurynas, et al.
Published: (2025)

PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models
by: Chen, Minghao, et al.
Published: (2024)