Copertina

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Qiu, Haiyi, Pan, Kaihang, Li, Jiacheng, Li, Juncheng, Tang, Siliang, Zhuang, Yueting
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
di: Yu, Qifan, et al.
Pubblicazione: (2024)

STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training
di: Qiu, Haiyi, et al.
Pubblicazione: (2024)

WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing
di: Pan, Kaihang, et al.
Pubblicazione: (2025)

FocusDiff: Advancing Fine-Grained Text-Image Alignment for Autoregressive Visual Generation through RL
di: Pan, Kaihang, et al.
Pubblicazione: (2025)

OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
di: Bu, Wendong, et al.
Pubblicazione: (2025)

Auto-Encoding Morph-Tokens for Multimodal LLM
di: Pan, Kaihang, et al.
Pubblicazione: (2024)

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning
di: Pan, Kaihang, et al.
Pubblicazione: (2025)

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
di: Li, Juncheng, et al.
Pubblicazione: (2023)

InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
di: Qin, Bosheng, et al.
Pubblicazione: (2023)

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
di: Ge, Zhiqi, et al.
Pubblicazione: (2024)

Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
di: Fan, Zhaoyu, et al.
Pubblicazione: (2025)

Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
di: Pan, Kaihang, et al.
Pubblicazione: (2024)

Unified Generative and Discriminative Training for Multi-modal Large Language Models
di: Chow, Wei, et al.
Pubblicazione: (2024)

What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
di: Bu, Wendong, et al.
Pubblicazione: (2025)

OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
di: Pan, Kaihang, et al.
Pubblicazione: (2026)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
di: Pan, Kaihang, et al.
Pubblicazione: (2025)

GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection
di: Dai, Guangyu, et al.
Pubblicazione: (2025)

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation
di: Zheng, Haoyu, et al.
Pubblicazione: (2024)

SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models
di: Zheng, Haoyu, et al.
Pubblicazione: (2025)

InstructSAM: Segment Any Instance with Any Instructions
di: Yuan, Yuqian, et al.
Pubblicazione: (2026)

T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text
di: Yin, Aoxiong, et al.
Pubblicazione: (2024)

Momentor: Advancing Video Large Language Model with Fine-Grained Temporal Reasoning
di: Qian, Long, et al.
Pubblicazione: (2024)

Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark
di: Miao, Bingchen, et al.
Pubblicazione: (2024)

Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness
di: Yu, Qifan, et al.
Pubblicazione: (2024)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
di: Wang, Wei, et al.
Pubblicazione: (2026)

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
di: Yu, Qifan, et al.
Pubblicazione: (2023)

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
di: Gao, Minghe, et al.
Pubblicazione: (2023)

Benchmarking Multimodal CoT Reward Model Stepwise by Visual Program
di: Gao, Minghe, et al.
Pubblicazione: (2025)

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
di: Gao, Minghe, et al.
Pubblicazione: (2024)

MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation
di: Zheng, Haoyu, et al.
Pubblicazione: (2024)

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
di: Wang, Keyu, et al.
Pubblicazione: (2026)

Ask Questions with Double Hints: Visual Question Generation with Answer-awareness and Region-reference
di: Shen, Kai, et al.
Pubblicazione: (2024)

SpatialFusion additional data
di: Yates, Josephine
Pubblicazione: (2026)

3D Dynamics-Aware Manipulation: Endowing Manipulation Policies with 3D Foresight
di: He, Yuxin, et al.
Pubblicazione: (2025)

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
di: Lin, Tianwei, et al.
Pubblicazione: (2025)

Towards Physically Executable 3D Gaussian for Embodied Navigation
di: Miao, Bingchen, et al.
Pubblicazione: (2025)

Unified Multimodal Coherent Field: Synchronous Semantic-Spatial-Vision Fusion for Brain Tumor Segmentation
di: Zhang, Mingda, et al.
Pubblicazione: (2025)

UniFS: Unified Multi-Contrast MRI Reconstruction via Frequency-Spatial Fusion
di: Li, Jialin, et al.
Pubblicazione: (2025)

MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation
di: Li, Baicheng, et al.
Pubblicazione: (2026)

Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models
di: Pan, Jiadong, et al.
Pubblicazione: (2026)