Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement

• URL: http://arxiv.org/abs/2309.07640v3
• Date: Tue, 13 Aug 2024 05:01:28 GMT
• Title: Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement
• Authors: Sheng Ye, Yubin Hu, Matthieu Lin, Yu-Hui Wen, Wang Zhao, Yong-Jin Liu, Wenping Wang,
• Abstract summary: The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations.
• Score: 50.56517624931987
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The reconstruction of indoor scenes from multi-view RGB images is challenging due to the coexistence of flat and texture-less regions alongside delicate and fine-grained regions. Recent methods leverage neural radiance fields aided by predicted surface normal priors to recover the scene geometry. These methods excel in producing complete and smooth results for floor and wall areas. However, they struggle to capture complex surfaces with high-frequency structures due to the inadequate neural representation and the inaccurately predicted normal priors. This work aims to reconstruct high-fidelity surfaces with fine-grained details by addressing the above limitations. To improve the capacity of the implicit representation, we propose a hybrid architecture to represent low-frequency and high-frequency regions separately. To enhance the normal priors, we introduce a simple yet effective image sharpening and denoising technique, coupled with a network that estimates the pixel-wise uncertainty of the predicted surface normal vectors. Identifying such uncertainty can prevent our model from being misled by unreliable surface normal supervisions that hinder the accurate reconstruction of intricate geometries. Experiments on the benchmark datasets show that our method outperforms existing methods in terms of reconstruction quality. Furthermore, the proposed method also generalizes well to real-world indoor scenarios captured by our hand-held mobile phones. Our code is publicly available at: https://github.com/yec22/Fine-Grained-Indoor-Recon.

Related papers

• ND-SDF: Learning Normal Deflection Fields for High-Fidelity Indoor Reconstruction [50.07671826433922]
  It is non-trivial to simultaneously recover meticulous geometry and preserve smoothness across regions with differing characteristics. We propose ND-SDF, which learns a Normal Deflection field to represent the angular deviation between the scene normal and the prior normal. Our method not only obtains smooth weakly textured regions such as walls and floors but also preserves the geometric details of complex structures.
  arXiv  Detail & Related papers  (2024-08-22T17:59:01Z)
• PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction [37.14913599050765]
  We propose a fast planar-based Gaussian splatting reconstruction representation (PGSR) to achieve high-fidelity surface reconstruction. We then introduce single-view geometric, multi-view photometric, and geometric regularization to preserve global geometric accuracy. Our method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods.
  arXiv  Detail & Related papers  (2024-06-10T17:59:01Z)
• GeoGaussian: Geometry-aware Gaussian Splatting for Scene Rendering [83.19049705653072]
  During the Gaussian Splatting optimization process, the scene's geometry can gradually deteriorate if its structure is not deliberately preserved. We propose a novel approach called GeoGaussian to mitigate this issue. Our proposed pipeline achieves state-of-the-art performance in novel view synthesis and geometric reconstruction.
  arXiv  Detail & Related papers  (2024-03-17T20:06:41Z)
• PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction [31.768161784030923]
  The framework PSDF is proposed which resorts to external geometric priors from a pretrained MVS network and internal geometric priors inherent in the NISR model. Experiments on the Tanks and Temples dataset show that PSDF achieves state-of-the-art performance on complex uncontrolled scenes.
  arXiv  Detail & Related papers  (2024-01-23T13:30:43Z)
• Fast Monocular Scene Reconstruction with Global-Sparse Local-Dense Grids [84.90863397388776]
  We propose to directly use signed distance function (SDF) in sparse voxel block grids for fast and accurate scene reconstruction without distances. Our globally sparse and locally dense data structure exploits surfaces' spatial sparsity, enables cache-friendly queries, and allows direct extensions to multi-modal data. Experiments show that our approach is 10x faster in training and 100x faster in rendering while achieving comparable accuracy to state-of-the-art neural implicit methods.
  arXiv  Detail & Related papers  (2023-05-22T16:50:19Z)
• NeuRIS: Neural Reconstruction of Indoor Scenes Using Normal Priors [84.66706400428303]
  We propose a new method, named NeuRIS, for high quality reconstruction of indoor scenes. NeuRIS integrates estimated normal of indoor scenes as a prior in a neural rendering framework. Experiments show that NeuRIS significantly outperforms the state-of-the-art methods in terms of reconstruction quality.
  arXiv  Detail & Related papers  (2022-06-27T19:22:03Z)
• SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse views [40.7986573030214]
  We introduce SparseNeuS, a novel neural rendering based method for the task of surface reconstruction from multi-view images. SparseNeuS can generalize to new scenes and work well with sparse images (as few as 2 or 3)
  arXiv  Detail & Related papers  (2022-06-12T13:34:03Z)
• NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction [88.02850205432763]
  We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs. Existing neural surface reconstruction approaches, such as DVR and IDR, require foreground mask as supervision. We observe that the conventional volume rendering method causes inherent geometric errors for surface reconstruction. We propose a new formulation that is free of bias in the first order of approximation, thus leading to more accurate surface reconstruction even without the mask supervision.
  arXiv  Detail & Related papers  (2021-06-20T12:59:42Z)
• Sign-Agnostic CONet: Learning Implicit Surface Reconstructions by Sign-Agnostic Optimization of Convolutional Occupancy Networks [39.65056638604885]
  We learn implicit surface reconstruction by sign-agnostic optimization of convolutional occupancy networks. We show this goal can be effectively achieved by a simple yet effective design.
  arXiv  Detail & Related papers  (2021-05-08T03:35:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.