通过分解场景内在属性，实现物理真实且视觉连贯的3D物体移除。
GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space
- 在材质与光照域中直接进行补全，避免视点依赖性失真。
- 在真实与合成数据上提升13%感知相似度（LPIPS）和2dB PSNR。
- 适合需要高保真3D编辑与光照一致性的科研与工业应用。
NeRF与3D高斯溅射（3DGS）的进展使多视角图像重建3D场景成为标准方法。从这些3D表示中移除物体是基础编辑任务，需对遮挡区域实现完整且无缝的补全，确保几何与外观一致性。尽管现有方法在补全一致性方面取得进展，但常忽略全局光照效应，导致物理上不合理的结果。此外，这些方法在视点依赖的非朗伯表面（appearance随视角变化）上表现不佳，造成不可靠的补全。本文提出3D高斯物体移除内在空间方法（GOR-IS），一种物理一致且视觉连贯的3D物体移除新框架。该方法将场景分解为内在成分，并显式建模光传输以保持全局光照一致性。同时引入内在空间补全模块，直接在材质与光照域操作，有效应对非朗伯表面挑战。在合成与真实世界数据集上的大量实验表明，本框架显著提升物体移除的物理一致性和视觉连贯性，在感知相似度（LPIPS）上优于现有方法13%，峰值信噪比（PSNR）提升2dB。代码已公开于 https://applezyh.github.io/GOR-IS-project-page/
原文摘要 · Abstract (English)
Recent advances in Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have made it standard practice to reconstruct 3D scenes from multi-view images. Removing objects from such 3D representations is a fundamental editing task that requires complete and seamless inpainting of occluded regions, ensuring consistency in geometry and appearance. Although existing methods have made notable progress in improving inpainting consistency, they often neglect global lighting effects, leading to physically implausible results. Moreover, these methods struggle with view-dependent non-Lambertian surfaces, where appearance varies across viewpoints, leading to unreliable inpainting. In this paper, we present 3D Gaussian Object Removal in the Intrinsic Space (GOR-IS), a novel framework for physically consistent and visually coherent 3D object removal. Our approach decomposes the scene into intrinsic components and explicitly models light transport to maintain global lighting effects consistency. Furthermore, we introduce an intrinsic-space inpainting module that operates directly in the material and lighting domains, effectively addressing the challenges posed by non-Lambertian surfaces. Extensive experiments on both synthetic and real-world datasets demonstrate that our framework substantially improves the physical consistency and visual coherence of object removal, outperforming existing methods by 13% in perceptual similarity (LPIPS) and 2dB in peak signal-to-noise ratio (PSNR). Code is publicly available at https://applezyh.github.io/GOR-IS-project-page/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。