A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance
Xianmin Xu, Yuxin Lin, Haoyang Zhou, Chong Zeng, Yaxin Yu, Kun Zhou, Hongzhi Wu
摘要
We propose a unified structured light, consisting of an LED array and an LCD mask, for high-quality acquisition of both shape and reflectance from a single view. For geometry, one LED projects a set of learned mask patterns to accurately encode spatial information; the decoded results from multiple LEDs are then aggregated to produce a final depth map. For appearance, learned light patterns are cast through a transparent mask to efficiently probe angularlyvarying reflectance. Per-point BRDF parameters are differentiably optimized with respect to corresponding measurements, and stored in texture maps as the final reflectance. We establish a differentiable pipeline for the joint capture to automatically optimize both the mask and light patterns towards optimal acquisition quality. The effectiveness of our light is demonstrated with a wide variety of physical objects. Our results compare favorably with state-of-the-art techniques.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper5
- TurboSL: Dense, Accurate and Fast 3D by Neural Inverse Structured LightParsa Mirdehghan, Maxx Wu, Wenzheng Chen, David B. Lindell 等CVPR 2024 · 被引用 5 次
- Real-Time Acquisition and Reconstruction of Dynamic Volumes with Neural Structured IlluminationYixin Zeng, Zoubin Bi, Mingrui Yin, Xiang Feng 等CVPR 2024 · 被引用 2 次
- GUSLO: General and Unified Structured Light OptimizationTinglei Wan, Zhongjie Wang, Tonghua SuAAAI 2026
- Differentiable Adaptive 4D Structured Illumination for Joint Capture of Shape and ReflectanceHuakeng Ding, Yaowen Chen, Kun Zhou, Hongzhi WuCVPR 2026
- SPIDeRS: Structured Polarization for Invisible Depth and Reflectance SensingTomoki Ichikawa, Shohei Nobuhara, Ko NishinoCVPR 2024
它引用的顶会 Paper2
- Free-form scanning of non-planar appearance with neural trace photographyXiaohe Ma, Kaizhang Kang, Ruisheng Zhu, Hongzhi Wu 等SIGGRAPH 2021 · 被引用 22 次
- Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D SupervisionMichael Niemeyer, Lars M. Mescheder, Michael Oechsle, Andreas GeigerCVPR 2020
相关 Paper
- Deep SVBRDF Estimation from Single Image under Learned Planar LightingLianghao Zhang, Fangzhou Gao, Li Wang, Minjing Yu 等SIGGRAPH 2023 · 被引用 13 次
- Deep Polarization Imaging for 3D Shape and SVBRDF AcquisitionValentin Deschaintre, Yiming Lin, Abhijeet GhoshCVPR 2021
- Polka Lines: Learning Structured Illumination and Reconstruction for Active StereoSeung-Hwan Baek, Felix HeideCVPR 2021
- Deep 3D Capture: Geometry and Reflectance From Sparse Multi-View ImagesSai Bi, Zexiang Xu, Kalyan Sunkavalli, David J. Kriegman 等CVPR 2020
- Learning Efficient Photometric Feature Transform for Multi-view StereoKaizhang Kang, Cihui Xie, Ruisheng Zhu, Xiaohe Ma 等ICCV 2021 · 被引用 3 次
