Imagen de Portada

GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Jiaxin, Jiang, Junjun, Li, Haijie, Chen, Youyu, Jiang, Kui, Chen, Dave Zhenyu
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting
por: Zhang, Jiaxin, et al.
Publicado: (2025)

Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations
por: Chen, Youyu, et al.
Publicado: (2026)

DashGaussian: Optimizing 3D Gaussian Splatting in 200 Seconds
por: Chen, Youyu, et al.
Publicado: (2025)

FUSE: Label-Free Image-Event Joint Monocular Depth Estimation via Frequency-Decoupled Alignment and Degradation-Robust Fusion
por: Sun, Pihai, et al.
Publicado: (2025)

MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
por: Huang, Jiaxin, et al.
Publicado: (2025)

LLV-FSR: Exploiting Large Language-Vision Prior for Face Super-resolution
por: Wang, Chenyang, et al.
Publicado: (2024)

Vision to Geometry: 3D Spatial Memory for Sequential Embodied MLLM Reasoning and Exploration
por: Cai, Zhongyi, et al.
Publicado: (2025)

Large-Scale 3D Medical Image Pre-training with Geometric Context Priors
por: Wu, Linshan, et al.
Publicado: (2024)

GeoAlign: Geometric Feature Realignment for MLLM Spatial Reasoning
por: Liu, Zhaochen, et al.
Publicado: (2026)

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
por: Wang, Chunshi, et al.
Publicado: (2025)

Spatial Annealing for Efficient Few-shot Neural Rendering
por: Xiao, Yuru, et al.
Publicado: (2024)

MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields
por: Xiao, Yuru, et al.
Publicado: (2024)

CoMP: Continual Multimodal Pre-training for Vision Foundation Models
por: Chen, Yitong, et al.
Publicado: (2025)

Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration
por: Wu, Gang, et al.
Publicado: (2023)

Boosting All-in-One Image Restoration via Self-Improved Privilege Learning
por: Wu, Gang, et al.
Publicado: (2025)

Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence
por: Zheng, Yufei, et al.
Publicado: (2026)

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models
por: Miao, Yanting, et al.
Publicado: (2026)

ControlMLLM: Training-Free Visual Prompt Learning for Multimodal Large Language Models
por: Wu, Mingrui, et al.
Publicado: (2024)

E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training
por: Zhao, Qitao, et al.
Publicado: (2025)

MG-3D: Multi-Grained Knowledge-Enhanced 3D Medical Vision-Language Pre-training
por: Ni, Xuefeng, et al.
Publicado: (2024)

RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training
por: Nie, Yunshuang, et al.
Publicado: (2026)

Fully $1\times1$ Convolutional Network for Lightweight Image Super-Resolution
por: Wu, Gang, et al.
Publicado: (2023)

Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
por: Xu, Runsen, et al.
Publicado: (2025)

VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection
por: Cao, Yang, et al.
Publicado: (2026)

MR-MLLM: Mutual Reinforcement of Multimodal Comprehension and Vision Perception
por: Wang, Guanqun, et al.
Publicado: (2024)

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
por: Fu, Jiyuan, et al.
Publicado: (2024)

Exploiting Self-Supervised Constraints in Image Super-Resolution
por: Wu, Gang, et al.
Publicado: (2024)

DSwinIR: Rethinking Window-based Attention for Image Restoration
por: Wu, Gang, et al.
Publicado: (2025)

M2DAO-Talker: Harmonizing Multi-granular Motion Decoupling and Alternating Optimization for Talking-head Generation
por: Jiang, Kui, et al.
Publicado: (2025)

Fast and Accurate Gigapixel Pathological Image Classification with Hierarchical Distillation Multi-Instance Learning
por: Dong, Jiuyang, et al.
Publicado: (2025)

AHDMIL: Asymmetric Hierarchical Distillation Multi-Instance Learning for Fast and Accurate Whole-Slide Image Classification
por: Dong, Jiuyang, et al.
Publicado: (2025)

Beyond Degradation Redundancy: Contrastive Prompt Learning for All-in-One Image Restoration
por: Wu, Gang, et al.
Publicado: (2025)

Primitive Geometry Segment Pre-training for 3D Medical Image Segmentation
por: Tadokoro, Ryu, et al.
Publicado: (2024)

Face-MLLM: A Large Face Perception Model
por: Sun, Haomiao, et al.
Publicado: (2024)

Are Large Pre-trained Vision Language Models Effective Construction Safety Inspectors?
por: Chen, Xuezheng, et al.
Publicado: (2025)

Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection
por: Tang, Lv, et al.
Publicado: (2023)

Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning
por: Chen, Jiahua, et al.
Publicado: (2026)

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models
por: Huang, Junming, et al.
Publicado: (2026)

SafeVid: Toward Safety Aligned Video Large Multimodal Models
por: Wang, Yixu, et al.
Publicado: (2025)

LLMI3D: MLLM-based 3D Perception from a Single 2D Image
por: Yang, Fan, et al.
Publicado: (2024)