EYE3: Turn Anything into Naked-Eye 3D
Yingde Song, Zongyuan Yang, Baolin Liu, Yongping Xiong, Sai Chen, Lan Yi, Zhaohe Zhang, Xunbo Yu
摘要
Light Field Displays (LFDs), despite significant advances in hardware technology supporting larger fields of view and multiple viewpoints, still face a critical challenge of limited content availability. Producing autostereoscopic 3D content on these displays requires refracting multi-perspective images into different spatial angles, with strict demands for spatial consistency across views, which is technically challenging for non-experts. Existing image/video generation models and radiance field-based methods cannot directly generate display content that meets the strict requirements of light field display hardware from a single 2D resource.We introduces the first generative framework EYE ^ 3 specifically designed for 3D light field displays, capable of converting any 2D images, videos, or texts into high-quality display content tailored for these screens. The framework employs a point-based representation rendered through off-axis perspective, ensuring precise light refraction and alignment with the hardware's optical requirements. To maintain consistent 3D coherence across multiple viewpoints, we finetune a video diffusion model to fill occluded regions based on the rendered masks.Experimental results demonstrate that our approach outperforms state-of-the-art methods, significantly simplifying content creation for LFDs. With broad potential in industries such as entertainment, advertising, and immersive display technologies, our method offers a robust solution to content scarcity and greatly enhances the visual experience on LFDs.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper14
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Directly Denoising Diffusion ModelsDan Zhang, Jingjing Wang, Feng LuoICML 2024 · 被引用 11,724 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Depth Anything V2Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao 等NeurIPS 2024 · 被引用 2,305 次
相关 Paper
- CoherentRaster: Efficient 3D Gaussian Splatting for Light Field DisplaysGyujin Sim, Seungjoo Shin, Hosung Jeon, Gwangsoon Lee 等SIGGRAPH 2026
- Bootstrap3D: Improving Multi-View Diffusion Model with Synthetic DataZeyi Sun, Tong Wu, Pan Zhang, Yuhang Zang 等ICCV 2025 · 被引用 1 次
- S2D-LFE: Sparse-to-Dense Light Field Event GenerationYutong Liu, Wenming Weng, Yueyi Zhang, Zhiwei XiongCVPR 2025
- Real-Time Light-Field Path Tracing for 3D Displays via Sparse Spatial-Angular-Temporal ReconstructionZongyuan Yang, Liulei Zou, Ling Zhu, Yongping Xiong 等SIGGRAPH 2026
- A Comprehensive Model for Visual Fatigue Assessment in 3D Light Field Displays Based on Eye Movement Data AnalysisYu Chen, Binbin Yan, Shuo Chen, Xinzhu SangACM MM 2025
