Cover Image

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zheng, Xu, Dongfang, Zihao, Jiang, Lutao, Zheng, Boyuan, Guo, Yulong, Zhang, Zhenquan, Albanese, Giuliano, Yang, Runyi, Ma, Mengjiao, Zhang, Zixin, Liao, Chenfei, Zhen, Dingcheng, Lyu, Yuanhuiyi, Fu, Yuqian, Ren, Bin, Zhang, Linfeng, Paudel, Danda Pani, Sebe, Nicu, Van Gool, Luc, Hu, Xuming
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reducing Unimodal Bias in Multi-Modal Semantic Segmentation with Multi-Scale Functional Entropy Regularization
by: Zheng, Xu, et al.
Published: (2025)

PANORAMA: The Rise of Omnidirectional Vision in the Embodied AI Era
by: Zheng, Xu, et al.
Published: (2025)

Retrieval Augmented Generation and Understanding in Vision: A Survey and New Outlook
by: Zheng, Xu, et al.
Published: (2025)

CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representation
by: Ma, Qi, et al.
Published: (2025)

MLLMs are Deeply Affected by Modality Bias
by: Zheng, Xu, et al.
Published: (2025)

Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?
by: Dongfang, Zihao, et al.
Published: (2025)

Understanding-in-Generation: Reinforcing Generative Capability of Unified Model via Infusing Understanding into Generation
by: Lyu, Yuanhuiyi, et al.
Published: (2025)

Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization
by: Ren, Bin, et al.
Published: (2025)

Vision encoders should be image size agnostic and task driven
by: Prisadnikov, Nedyalko, et al.
Published: (2025)

Self-supervised pretraining for an iterative image size agnostic vision transformer
by: Prisadnikov, Nedyalko, et al.
Published: (2026)

Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
by: Li, Yue, et al.
Published: (2025)

Benchmarking Multi-modal Semantic Segmentation under Sensor Failures: Missing and Noisy Modality Robustness
by: Liao, Chenfei, et al.
Published: (2025)

Cross-View Multi-Modal Segmentation @ Ego-Exo4D Challenges 2025
by: Fu, Yuqian, et al.
Published: (2025)

Lego: Learning to Disentangle and Invert Personalized Concepts Beyond Object Appearance in Text-to-Image Diffusion Models
by: Motamed, Saman, et al.
Published: (2023)

Autonomous Vehicle Controllers From End-to-End Differentiable Simulation
by: Nachkov, Asen, et al.
Published: (2024)

EvenNICER-SLAM: Event-based Neural Implicit Encoding SLAM
by: Chen, Shi, et al.
Published: (2024)

SPEAR-1: Scaling Beyond Robot Demonstrations via 3D Understanding
by: Nikolov, Nikolay, et al.
Published: (2025)

ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining
by: Ma, Qi, et al.
Published: (2024)

EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM
by: Shu, Yan, et al.
Published: (2025)

SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
by: Li, Yue, et al.
Published: (2025)

SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting
by: Ma, Mengjiao, et al.
Published: (2025)

RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
by: Lyu, Yuanhuiyi, et al.
Published: (2025)

Are We Using the Right Benchmark: An Evaluation Framework for Visual Token Compression Methods
by: Liao, Chenfei, et al.
Published: (2025)

Bringing Masked Autoencoders Explicit Contrastive Properties for Point Cloud Self-Supervised Learning
by: Ren, Bin, et al.
Published: (2024)

Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis
by: Mahdi, Mohammad, et al.
Published: (2025)

OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation
by: Zhong, Ding, et al.
Published: (2025)

SeasonScapes: Learning Large-scale Re-lightable 3D Landscapes with Seasonal Variation from Sparse Webcams
by: Kleger, Timo, et al.
Published: (2026)

Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
by: Ma, Qi, et al.
Published: (2024)

Continuous Pose for Monocular Cameras in Neural Implicit Representation
by: Ma, Qi, et al.
Published: (2023)

From Synchrony to Sequence: Exo-to-Ego Generation via Interpolation
by: Mahdi, Mohammad, et al.
Published: (2026)

EgoSpot:Egocentric Multimodal Control for Hands-Free Mobile Manipulation
by: Zhang, Ganlin, et al.
Published: (2023)

Learning Robust Anymodal Segmentor with Unimodal and Cross-modal Distillation
by: Zheng, Xu, et al.
Published: (2024)

EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
by: Zhang, Deheng, et al.
Published: (2025)

MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selection
by: Zheng, Xu, et al.
Published: (2024)

Partial CLIP is Enough: Chimera-Seg for Zero-shot Semantic Segmentation
by: Chen, Jialei, et al.
Published: (2025)

BiXFormer: A Robust Framework for Maximizing Modality Effectiveness in Multi-Modal Semantic Segmentation
by: Chen, Jialei, et al.
Published: (2025)

Inferring Compositional 4D Scenes without Ever Seeing One
by: Gokmen, Ahmet Berke, et al.
Published: (2025)

A Simple and Generalist Approach for Panoptic Segmentation
by: Prisadnikov, Nedyalko, et al.
Published: (2024)

Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits
by: Balauca, Ada-Astrid, et al.
Published: (2024)

RICO: Two Realistic Benchmarks and an In-Depth Analysis for Incremental Learning in Object Detection
by: Neuwirth-Trapp, Matthias, et al.
Published: (2025)