Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention
Efficient-LVSM: 通过解耦共细化注意力实现更高效、更经济、更优质的大型视角合成模型
机构 * Institute of Trustworthy Embodied AI (TEAI)(可信具身人工智能研究院) ; Sch. of Computer Science & Sch. of Artificial Intelligence(计算机科学学院与人工智能学院) ; Shanghai Jiao Tong University(上海交通大学)
AI总结 Efficient-LVSM通过解耦共细化注意力机制,实现了更高效、更经济、更优质的大型视角合成模型,提升了PSNR性能并加快了训练和推理速度。
Comments Accepted at ICLR 2026