paper-with-me

Papers

Robust Reflection Removal with Flash-only Cues in the Wild

2022-11-05 · Chenyang Lei, Xudong Jiang, Qifeng Chen

We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambient image from the corresponding flash image in raw data space. The flash-only image is equivalent to an image taken in a dark environment with only a flash on. This flash-only image is visually reflection-free and thus can provide robust cues to infer the reflection in the ambient image. Since the flash-only image usually has artifacts, we further propose a dedicated model that not only utilizes the reflection-free cue but also avoids introducing artifacts, which helps accurately estimate reflection and transmission. Our experiments on real-world images with various types of reflection demonstrate the effectiveness of our model with reflection-free flash-only cues: our model outperforms state-of-the-art reflection removal approaches by more than 5.23dB in PSNR. We extend our approach to handheld photography to address the misalignment between the flash and no-flash pair. With misaligned training data and the alignment module, our aligned model outperforms our previous version by more than 3.19dB in PSNR on a misaligned dataset. We also study using linear RGB images as training data. Our source code and dataset are publicly available at https://github.com/ChenyangLEI/flash-reflection-removal.

📄 PDF Abstract BibTeX arXiv:2211.02914

Code (1)

ChenyangLEI/flash-reflection-removal 공식 구현 tf

Tasks

Reflection Removal

Similar Papers 제목 키워드 기반

Robust Reflection Removal with Reflection-free Flash-only Cues

2021-03-07 · CVPR 2021 1 · Chenyang Lei, Qifeng Chen

We propose a simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient (no-flash) images. The reflection-free cue exploits a flash-only image obtained by subtracting the ambi…

Reflection RemovalSSIM

Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation

2024-12-31 · CVPR 2025 1 · Tianfu Wang, Mingyang Xie, Haoming Cai, Sachin Shah 외

Transparent surfaces, such as glass, create complex reflections that obscure images and challenge downstream computer vision applications. We introduce Flash-Split, a robust framework for separating transmitted and refle…

Reflection Removal

Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats

2024-10-03 · Mingyang Xie, Haoming Cai, Sachin Shah, Yiran Xu 외

We introduce a simple yet effective approach for separating transmitted and reflected light. Our key insight is that the powerful novel view synthesis capabilities provided by modern inverse rendering methods (e.g.,~3D G…

Inverse RenderingNovel View SynthesisReflection Removal

WildLight: In-the-wild Inverse Rendering with a Flashlight

2023-03-24 · CVPR 2023 1 · Ziang Cheng, Junxuan Li, Hongdong Li

This paper proposes a practical photometric solution for the challenging problem of in-the-wild inverse rendering under unknown ambient lighting. Our system recovers scene geometry and reflectance using only multi-view i…

3D ReconstructionInverse Rendering

Polarized Reflection Removal with Perfect Alignment in the Wild

2020-03-28 · CVPR 2020 6 · Chenyang Lei, Xuhua Huang, Mengdi Zhang, Qiong Yan 외

We present a novel formulation to removing reflection from polarized images in the wild. We first identify the misalignment issues of existing reflection removal datasets where the collected reflection-free images are no…

Image EnhancementReflection Removal