Skip to content
Hot eventLive

3DTexMOR:纹理空间修复的3D高斯多物体移除

1 reports1 sources3 hr ago updated

Get the story

AI overview

2026年10月9日,arXiv(Computer Vision)发布3DTexMOR方法,针对3D场景多物体移除任务,提出在多视角共享的统一纹理空间中进行修复。该方法先将多视角观测聚合为纹理图并修复缺失区域,再重投影回相机视角以监督Gaussian场景补全;同时分解外观、聚合视角无关的内在属性,以避免高光与反射干扰,并引入几何正则化约束补全区域的几何,从而提升几何与外观补全效果。目前公开信息仅涉及该方法的设计思路与流程,尚无实验数据、代码或第三方验证结果。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 9, 2026
  1. arXiv · Computer Vision
    3DTexMOR:通过纹理空间修复实现 3D Gaussian 多物体移除

    3DTexMOR 提出在多视角共享的统一纹理空间中进行修复,以提升 3D 场景多物体移除的几何与外观补全效果。该方法将多视角观测聚合为纹理图并修复缺失区域,再重投影回相机视角监督 Gaussian 场景补全,同时分解外观、聚合视角无关的内在属性以避免高光与反射干扰,并引入几何正则化约束补全区域几何。

Heat trend

Current heat 9·Comparable peak 10(Oct 9)·Comparable change over 24 hours –

02.557.510Oct9Oct9Oct9Oct9

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.