Enhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views

• URL: http://arxiv.org/abs/2407.05666v1
• Date: Mon, 8 Jul 2024 07:03:22 GMT
• Title: Enhancing Neural Radiance Fields with Depth and Normal Completion Priors from Sparse Views
• Authors: Jiawei Guo, HungChyun Chou, Ning Ding,
• Abstract summary: Neural Radiance Fields (NeRF) create highly realistic images by learning about scenes through a neural network model. NeRF often encounters issues when there are not enough images to work with, leading to problems in accurately rendering views. This framework enhances view rendering by adding depth and normal dense completion priors to the NeRF optimization process.
• Score: 8.533926962066305
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural Radiance Fields (NeRF) are an advanced technology that creates highly realistic images by learning about scenes through a neural network model. However, NeRF often encounters issues when there are not enough images to work with, leading to problems in accurately rendering views. The main issue is that NeRF lacks sufficient structural details to guide the rendering process accurately. To address this, we proposed a Depth and Normal Dense Completion Priors for NeRF (CP\_NeRF) framework. This framework enhances view rendering by adding depth and normal dense completion priors to the NeRF optimization process. Before optimizing NeRF, we obtain sparse depth maps using the Structure from Motion (SfM) technique used to get camera poses. Based on the sparse depth maps and a normal estimator, we generate sparse normal maps for training a normal completion prior with precise standard deviations. During optimization, we apply depth and normal completion priors to transform sparse data into dense depth and normal maps with their standard deviations. We use these dense maps to guide ray sampling, assist distance sampling and construct a normal loss function for better training accuracy. To improve the rendering of NeRF's normal outputs, we incorporate an optical centre position embedder that helps synthesize more accurate normals through volume rendering. Additionally, we employ a normal patch matching technique to choose accurate rendered normal maps, ensuring more precise supervision for the model. Our method is superior to leading techniques in rendering detailed indoor scenes, even with limited input views.

Related papers

• Scale Propagation Network for Generalizable Depth Completion [16.733495588009184]
  We propose a novel scale propagation normalization (SP-Norm) method to propagate scales from input to output. We also develop a new network architecture based on SP-Norm and the ConvNeXt V2 backbone. Our model consistently achieves the best accuracy with faster speed and lower memory when compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-10-24T03:53:06Z)
• Simple-RF: Regularizing Sparse Input Radiance Fields with Simpler Solutions [5.699788926464751]
  Neural Radiance Fields (NeRF) show impressive performance in photo-realistic free-view rendering of scenes. Recent improvements on the NeRF such as TensoRF and ZipNeRF employ explicit models for faster optimization and rendering. We show that supervising the depth estimated by a radiance field helps train it effectively with fewer views.
  arXiv  Detail & Related papers  (2024-04-29T18:00:25Z)
• Indoor Scene Reconstruction with Fine-Grained Details Using Hybrid Representation and Normal Prior Enhancement [50.56517624931987]
  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.
  arXiv  Detail & Related papers  (2023-09-14T12:05:29Z)
• SimpleNeRF: Regularizing Sparse Input Neural Radiance Fields with Simpler Solutions [6.9980855647933655]
  supervising the depth estimated by the NeRF helps train it effectively with fewer views. We design augmented models that encourage simpler solutions by exploring the role of positional encoding and view-dependent radiance. We achieve state-of-the-art view-synthesis performance on two popular datasets by employing the above regularizations.
  arXiv  Detail & Related papers  (2023-09-07T18:02:57Z)
• ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields [9.67057831710618]
  Training neural radiance fields (NeRFs) on sparse input views leads to overfitting and incorrect scene depth estimation. We reformulate the NeRF to also directly output the visibility of a 3D point from a given viewpoint to reduce the training time with the visibility constraint. Our model outperforms the competing sparse input NeRF models including those that use learned priors.
  arXiv  Detail & Related papers  (2023-04-28T18:26:23Z)
• SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis [93.46963803030935]
  We present a new Sparse-view NeRF (SparseNeRF) framework that exploits depth priors from real-world inaccurate observations. We propose a simple yet effective constraint, a local depth ranking method, on NeRFs such that the expected depth ranking of the NeRF is consistent with that of the coarse depth maps in local patches. We also collect a new dataset NVS-RGBD that contains real-world depth maps from Azure Kinect, ZED 2, and iPhone 13 Pro.
  arXiv  Detail & Related papers  (2023-03-28T17:58:05Z)
• DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields [75.35416391705503]
  Recent works such as BARF and GARF can adjust camera poses with neural radiance fields (NeRF) which is based on coordinate-MLPs. Despite the impressive results, these methods cannot be applied to Generalizable NeRFs (GeNeRFs) which require image feature extractions. In this work, we first analyze the difficulties of jointly optimizing camera poses with GeNeRFs, and then further propose our DBARF to tackle these issues.
  arXiv  Detail & Related papers  (2023-03-25T14:18:30Z)
• Dense Depth Priors for Neural Radiance Fields from Sparse Input Views [37.92064060160628]
  We propose a method to synthesize novel views of whole rooms from an order of magnitude fewer images. Our method enables data-efficient novel view synthesis on challenging indoor scenes, using as few as 18 images for an entire scene.
  arXiv  Detail & Related papers  (2021-12-06T19:00:02Z)
• NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo [97.07453889070574]
  We present a new multi-view depth estimation method that utilizes both conventional SfM reconstruction and learning-based priors. We show that our proposed framework significantly outperforms state-of-the-art methods on indoor scenes.
  arXiv  Detail & Related papers  (2021-09-02T17:54:31Z)
• Depth-supervised NeRF: Fewer Views and Faster Training for Free [69.34556647743285]
  DS-NeRF (Depth-supervised Neural Radiance Fields) is a loss for learning fields that takes advantage of readily-available depth supervision. We show that our loss is compatible with other recently proposed NeRF methods, demonstrating that depth is a cheap and easily digestible supervisory signal.
  arXiv  Detail & Related papers  (2021-07-06T17:58:35Z)
• Depth Completion Using a View-constrained Deep Prior [73.21559000917554]
  Recent work has shown that the structure of convolutional neural networks (CNNs) induces a strong prior that favors natural images. This prior, known as a deep image prior (DIP), is an effective regularizer in inverse problems such as image denoising and inpainting. We extend the concept of the DIP to depth images. Given color images and noisy and incomplete target depth maps, we reconstruct a depth map restored by virtue of using the CNN network structure as a prior.
  arXiv  Detail & Related papers  (2020-01-21T21:56:01Z)

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.