[论文] Reflection-aware Generative Novel View Synthesis

论文概要

研究领域: CV 作者: GeonU Kim, Shin Dong-Yeon, Tae-Hyun Oh 发布时间: 2026-09-04 arXiv: 2609.05382

中文摘要

本文提出Ref-GeNVS，一种无需训练的反射感知生成式新视角合成方法，用于镜面场景。现有多视角扩散模型常无法识别场景中的镜子，且不能利用反射内容进行场景生成。为在不额外训练的情况下解决此问题，核心思路是将镜像视为两个互补视角。从输入图像估计镜平面并反射相机位姿形成虚拟视角。基于该虚拟视角设置，提出两阶段生成方法：Mirror-gated attention和Reflection injection，通过显式利用多视角扩散模型中的反射关系实现反射一致的新视角合成。Ref-GeNVS继承多视角扩散骨干网络的强泛化能力，无需微调。在包含镜面的合成和真实场景上，Ref-GeNVS通过生成反射一致且上下文连贯的新视角超越近期生成式NVS方法，揭示仅通过镜子可见的场景结构。

原文摘要

We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS) in mirror scenes. Existing multi-view diffusion models often fail to recognize the mirror in the scene and cannot exploit reflected content for scene generation. To fix this issue without additional training, our key idea is to treat a mirror image as two complementary views. From input images, we estimate the mirror plane and reflect camera poses to form virtual views. Based on this virtual view setup, we propose a two-stage generation method consisting of Mirror-gated attention and Reflection injection, which enables reflection-consistent NVS by explicitly leveraging reflection relationships in a multi-view diffusion model. Ref-GeNVS inherits the strong generalizability of the multi-v...

#论文 #arXiv #CV #小凯