Image de couverture de livre

WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Yifan, Min, Zhiyuan, Wang, Zhenwei, Wu, Junta, Wang, Tengfei, Yuan, Yixuan, Luo, Yawei, Guo, Chunchao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories
par: Zhang, Yisu, et autres
Publié: (2026)

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
par: Sun, Wenqiang, et autres
Publié: (2025)

WorldCompass: Reinforcement Learning for Long-Horizon World Models
par: Wang, Zehan, et autres
Publié: (2026)

Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
par: Huang, Tianyu, et autres
Publié: (2025)

FlashWorld: High-quality 3D Scene Generation within Seconds
par: Li, Xinyang, et autres
Publié: (2025)

MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
par: Li, Zhiqi, et autres
Publié: (2025)

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
par: HY-World, Team, et autres
Publié: (2026)

HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
par: HunyuanWorld Team, et autres
Publié: (2025)

Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
par: Min, Zhiyuan, et autres
Publié: (2024)

Animate Any Character in Any World
par: Wang, Yitong, et autres
Publié: (2025)

Material Anything: Generating Materials for Any 3D Object via Diffusion
par: Huang, Xin, et autres
Publié: (2024)

Pathwise Test-Time Correction for Autoregressive Long Video Generation
par: Xiang, Xunzhi, et autres
Publié: (2026)

HuPrior3R: Incorporating Human Priors for Better 3D Dynamic Reconstruction from Monocular Videos
par: Xiong, Weitao, et autres
Publié: (2025)

MirrorGaussian: Reflecting 3D Gaussians for Reconstructing Mirror Reflections
par: Liu, Jiayue, et autres
Publié: (2024)

Part-X-MLLM: Part-aware 3D Multimodal Large Language Model
par: Wang, Chunshi, et autres
Publié: (2025)

PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
par: Yang, Yunhan, et autres
Publié: (2026)

Shape-for-Motion: Precise and Consistent Video Editing with 3D Proxy
par: Liu, Yuhao, et autres
Publié: (2025)

Depth Anything with Any Prior
par: Wang, Zehan, et autres
Publié: (2025)

Seeing Through Reflections: Advancing 3D Scene Reconstruction in Mirror-Containing Environments with Gaussian Splatting
par: Guo, Zijing, et autres
Publié: (2025)

Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields
par: Min, Zhiyuan, et autres
Publié: (2023)

SAS: Segment Any 3D Scene with Integrated 2D Priors
par: Li, Zhuoyuan, et autres
Publié: (2025)

Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections
par: Wu, Jing, et autres
Publié: (2025)

WorldTree: Towards 4D Dynamic Worlds from Monocular Video using Tree-Chains
par: Wang, Qisen, et autres
Publié: (2026)

AIR: Amortized Image Reconstruction Framework for Self-Supervised Feed-Forward 2D Gaussian Splatting
par: Zeng, Zhaojie, et autres
Publié: (2026)

ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars
par: Wang, Zhenwei, et autres
Publié: (2024)

MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis
par: Luo, Di, et autres
Publié: (2025)

AnyRecon: Arbitrary-View 3D Reconstruction with Video Diffusion Model
par: Chen, Yutian, et autres
Publié: (2026)

ArtiWorld: LLM-Driven Articulation of 3D Objects in Scenes
par: Yang, Yixuan, et autres
Publié: (2025)

Phidias: A Generative Model for Creating 3D Content from Text, Image, and 3D Conditions with Reference-Augmented Diffusion
par: Wang, Zhenwei, et autres
Publié: (2024)

MaGS: Reconstructing and Simulating Dynamic 3D Objects with Mesh-adsorbed Gaussian Splatting
par: Ma, Shaojie, et autres
Publié: (2024)

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
par: Zheng, Duo, et autres
Publié: (2025)

Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising
par: Guo, Jun, et autres
Publié: (2026)

Any to Full: Prompting Depth Anything for Depth Completion in One Stage
par: Zhou, Zhiyuan, et autres
Publié: (2026)

3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
par: Hong, Fangzhou, et autres
Publié: (2024)

Grounding Creativity in Physics: A Brief Survey of Physical Priors in AIGC
par: Meng, Siwei, et autres
Publié: (2025)

Towards Real-World Blind Face Restoration with Generative Diffusion Prior
par: Chen, Xiaoxu, et autres
Publié: (2023)

World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
par: Wang, Weijie, et autres
Publié: (2026)

TSD-SR: One-Step Diffusion with Target Score Distillation for Real-World Image Super-Resolution
par: Dong, Linwei, et autres
Publié: (2024)

AHAP: Reconstructing Arbitrary Humans from Arbitrary Perspectives with Geometric Priors
par: Qiao, Xiaozhen, et autres
Publié: (2026)

DA$^{2}$: Depth Anything in Any Direction
par: Li, Haodong, et autres
Publié: (2025)