Papers › Neural-PBIR Reconstruction of Shape, Material, and Illumination

Neural-PBIR Reconstruction of Shape, Material, and Illumination

26 Apr 2023ICCV 2023 1arXiv:2304.13445archive 2025-07-28

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.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Depth PredictionImage RelightingInverse RenderingObjectObject ReconstructionSurface Normals EstimationSurface Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Relighting Stanford-ORB Neural-PBIR HDR-PSNR 26.01 #1 of 7 Archive leaderboard report
Image Relighting Stanford-ORB Neural-PBIR LPIPS 0.023 #1 of 7 Archive leaderboard report
Image Relighting Stanford-ORB Neural-PBIR SSIM 0.979 #1 of 7 Archive leaderboard report
Inverse Rendering Stanford-ORB Neural-PBIR HDR-PSNR 26.01 #1 of 7 Archive leaderboard report
Surface Normals Estimation Stanford-ORB Neural-PBIR Cosine Distance 0.06 #4 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections