paper-with-me

홈 › Papers

Pano Popups: Indoor 3D Reconstruction with a Plane-Aware Network

2019-07-01 · Marc Eder, Pierre Moulon, Li Guan

In this work we present a method to train a plane-aware convolutional neural network for dense depth and surface normal estimation as well as plane boundaries from a single indoor $360^\circ$ image. Using our proposed loss function, our network outperforms existing methods for single-view, indoor, omnidirectional depth estimation and provides an initial benchmark for surface normal prediction from $360^\circ$ images. Our improvements are due to the use of a novel plane-aware loss that leverages principal curvature as an indicator of planar boundaries. We also show that including geodesic coordinate maps as network priors provides a significant boost in surface normal prediction accuracy. Finally, we demonstrate how we can combine our network's outputs to generate high quality 3D "pop-up" models of indoor scenes.

📄 PDF Abstract BibTeX arXiv:1907.00939

Code (0)

등록된 구현이 없습니다.

Tasks

3D ReconstructionDepth EstimationSurface Normal Estimation

Similar Papers 제목 키워드 기반

Indoor Panorama Planar 3D Reconstruction via Divide and Conquer

2021-06-27 · CVPR 2021 1 · Cheng Sun, Chi-Wei Hsiao, Ning-Hsu Wang, Min Sun 외

Indoor panorama typically consists of human-made structures parallel or perpendicular to gravity. We leverage this phenomenon to approximate the scene in a 360-degree image with (H)orizontal-planes and (V)ertical-planes.…

3D ReconstructionInstance SegmentationSemantic SegmentationTranslation

Layout-guided Indoor Panorama Inpainting with Plane-aware Normalization

2023-01-13 · Chao-Chen Gao, Cheng-Hsiu Chen, Jheng-Wei Su, Hung-Kuo Chu

We present an end-to-end deep learning framework for indoor panoramic image inpainting. Although previous inpainting methods have shown impressive performance on natural perspective images, most fail to handle panoramic …

Image Inpainting

PanoPlane: Plane-Aware Panoramic Completion for Sparse-View Indoor 3D Gaussian Splatting

2026-05-13 · Adil Qureshi, Dongki Jung, Jaehoon Choi, Dinesh Manocha arxiv

We present PanoPlane, an approach for high-fidelity sparse-view indoor novel view synthesis that reconstructs closed room geometry via panoramic scene completion. Unlike perspective-based methods that generate training v…

Novel View Synthesis

OmniIndoor3D: Comprehensive Indoor 3D Reconstruction

2025-05-27 · Xiaobao Wei, Xiaoan Zhang, Hao Wang, Qingpo Wuwu 외

We propose a novel framework for comprehensive indoor 3D reconstruction using Gaussian representations, called OmniIndoor3D. This framework enables accurate appearance, geometry, and panoptic reconstruction of diverse in…

3DGS3D ReconstructionScene Understanding

Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction

2023-03-18 · Jiayang Bai, Zhen He, Shan Yang, Jie Guo 외

Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robust prediction, this problem can be decom…

HDR Reconstruction