PulseAugur
EN
LIVE 21:42:06

GOR-IS framework improves 3D object removal with intrinsic space inpainting

Researchers have developed GOR-IS, a new framework for removing objects from 3D scene reconstructions generated by methods like 3D Gaussian Splatting. This approach addresses limitations in existing techniques by explicitly modeling light transport for global consistency and handling non-Lambertian surfaces. GOR-IS decomposes scenes into intrinsic components and uses an intrinsic-space inpainting module to improve physical consistency and visual coherence. Experiments show a 13% improvement in perceptual similarity and a 2dB increase in PSNR compared to prior methods. AI

IMPACT Improves 3D scene editing by enabling more physically consistent object removal, potentially aiding in content creation and virtual environment manipulation.

RANK_REASON Academic paper introducing a novel framework for 3D scene editing.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

GOR-IS framework improves 3D object removal with intrinsic space inpainting

COVERAGE [2]

  1. arXiv cs.CV TIER_1 English(EN) · Yonghao Zhao, Yupeng Gao, Jian Yang, Jin Xie, Beibei Wang ·

    GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space

    arXiv:2605.00498v1 Announce Type: new Abstract: 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…

  2. arXiv cs.CV TIER_1 English(EN) · Beibei Wang ·

    GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space

    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 inpain…