paper-with-me

Papers

Neural-PBIR Reconstruction of Shape, Material, and Illumination

2023-04-26 · ICCV 2023 1 · Cheng Sun, Guangyan Cai, Zhengqin Li, Kai Yan, Cheng Zhang, Carl Marshall, Jia-Bin Huang, Shuang Zhao, Zhao Dong

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision and graphics. In this paper, we introduce an accurate and highly efficient object reconstruction pipeline combining neural based object reconstruction and physics-based inverse rendering (PBIR). Our pipeline firstly leverages a neural SDF based shape reconstruction to produce high-quality but potentially imperfect object shape. Then, we introduce a neural material and lighting distillation stage to achieve high-quality predictions for material and illumination. In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination. Experimental results demonstrate our pipeline significantly outperforms existing methods quality-wise and performance-wise.

📄 PDF Abstract BibTeX arXiv:2304.13445

Code (0)

등록된 구현이 없습니다.

Tasks

Depth PredictionImage RelightingInverse RenderingObjectObject ReconstructionSurface Normals EstimationSurface Reconstruction

Similar Papers 제목 키워드 기반

PBIR-NIE: Glossy Object Capture under Non-Distant Lighting

2024-08-13 · Guangyan Cai, Fujun Luan, Miloš Hašan, Kai Zhang 외

Glossy objects present a significant challenge for 3D reconstruction from multi-view input images under natural lighting. In this paper, we introduce PBIR-NIE, an inverse rendering framework designed to holistically capt…

3D ReconstructionInverse RenderingObject Reconstruction

SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild

2024-01-18 · CVPR 2024 1 · Andreas Engelhardt, Amit Raj, Mark Boss, Yunzhi Zhang 외

We present SHINOBI, an end-to-end framework for the reconstruction of shape, material, and illumination from object images captured with varying lighting, pose, and background. Inverse rendering of an object based on unc…

Inverse RenderingObject

Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects

2025-10-02 · Georgios Kouros, Minye Wu, Tinne Tuytelaars arxiv

Accurate reconstruction and relighting of glossy objects remains a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disentangle. Existing neural rendering approac…

SupeRVol: Super-Resolution Shape and Reflectance Estimation in Inverse Volume Rendering

2022-12-09 · Mohammed Brahimi, Bjoern Haefner, Tarun Yenamandra, Bastian Goldluecke 외

We propose an end-to-end inverse rendering pipeline called SupeRVol that allows us to recover 3D shape and material parameters from a set of color images in a super-resolution manner. To this end, we represent both the b…

Inverse RenderingSuper-Resolution

SGS-Intrinsic: Semantic-Invariant Gaussian Splatting for Sparse-View Indoor Inverse Rendering

2026-03-29 · Jiahao Niu, Rongjia Zheng, Wenju Xu, Wei-Shi Zheng 외 arxiv

We present SGS-Intrinsic, an indoor inverse rendering framework that works well for sparse-view images. Unlike existing 3D Gaussian Splatting (3DGS) based methods that focus on object-centric reconstruction and fail to w…

Inverse Rendering