资源分类
》 资源 》论文》Shadow Removal from Single RGB-D Images

Shadow Removal from Single RGB-D Images

2019-12-16 | |  64 |   51 |   0

Abstract

We present the fifirst automatic method to remove shadows from single RGB-D images. Using normal cues directly derived from depth, we can remove hard and soft shadows while preserving surface texture and shading. Our key assumption is: pixels with similar normals, spatial locations and chromaticity should have similar colors. A modifified nonlocal matching is used to compute a shadow confifidence map that localizes well hard shadow boundary, thus handling hard and soft shadows within the same framework. We compare our results produced using state-of-the-art shadow removal on single RGB images, and intrinsic image decomposition on standard RGB-D datasets

上一篇：Joint Summarization of Large-scale Collections of Web Images and Videos for Storyline Reconstruction

下一篇：Image Pre-compensation: Balancing Contrast and Ringing

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Learning to learn...

    The move from hand-designed features to learned...