GOR-IS：本征空间中的三维高斯物体移除
GOR-IS: 3D Gaussian Object Removal In the Intrinsic Space
把场景分解为材质与光照等本征分量，并在本征空间中做图像修复，为 3DGS/NeRF 场景编辑提供了一条处理全局光照一致性与视角相关非朗伯表面的可复用思路。
原文依据 we introduce an intrinsic-space inpainting module that operates directly in the material and lighting domains
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论神经辐射场（NeRF）与三维高斯泼溅（3DGS）的最新进展，使得从多视角图像重建三维场景成为常规做法。从此类三维表示中移除物体是一项基础编辑任务，要求对被遮挡区域进行完整且无缝的图像修复，并保证几何与外观的一致性。尽管现有方法在提升修复一致性方面取得了显著进展，但它们往往忽略全局光照效果，导致结果在物理上不合理。此外，这些方法难以处理视角相关的非朗伯表面——其外观随视点变化，从而导致修复不可靠。本文提出本征空间中的三维高斯物体移除（GOR-IS），一个用于物理一致且视觉连贯的三维物体移除的新框架。该方法将场景分解为本征分量，并显式建模光照传输，以保持全局光照效果的一致性。进一步地，我们引入一个本征空间修复模块，直接在材质与光照域中操作，有效应对非朗伯表面带来的挑战。在合成与真实数据集上的大量实验表明，该框架显著提升了物体移除的物理一致性与视觉连贯性，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/
英文原文摘要 1578 字符
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/