RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF

• URL: http://arxiv.org/abs/2403.11909v2
• Date: Tue, 23 Jul 2024 10:02:52 GMT
• Title: RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF
• Authors: Sibi Catley-Chandar, Richard Shaw, Gregory Slabaugh, Eduardo Perez-Pellitero,
• Abstract summary: 2D enhancers can be pre-trained to recover some detail but are agnostic to scene geometry. Existing 3D enhancers are able to transfer detail from nearby training images in a generalizable manner. We propose a neural rendering enhancer, RoGUENeRF, which exploits the best of both paradigms.
• Score: 1.828790674925926
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in neural rendering have enabled highly photorealistic 3D scene reconstruction and novel view synthesis. Despite this progress, current state-of-the-art methods struggle to reconstruct high frequency detail, due to factors such as a low-frequency bias of radiance fields and inaccurate camera calibration. One approach to mitigate this issue is to enhance images post-rendering. 2D enhancers can be pre-trained to recover some detail but are agnostic to scene geometry and do not easily generalize to new distributions of image degradation. Conversely, existing 3D enhancers are able to transfer detail from nearby training images in a generalizable manner, but suffer from inaccurate camera calibration and can propagate errors from the geometry into rendered images. We propose a neural rendering enhancer, RoGUENeRF, which exploits the best of both paradigms. Our method is pre-trained to learn a general enhancer while also leveraging information from nearby training images via robust 3D alignment and geometry-aware fusion. Our approach restores high-frequency textures while maintaining geometric consistency and is also robust to inaccurate camera calibration. We show that RoGUENeRF substantially enhances the rendering quality of a wide range of neural rendering baselines, e.g. improving the PSNR of MipNeRF360 by 0.63dB and Nerfacto by 1.34dB on the real world 360v2 dataset.

Related papers

• Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernels [51.08794269211701]
  We introduce 3D Linear Splatting (3DLS), which replaces Gaussian kernels with linear kernels to achieve sharper and more precise results. 3DLS demonstrates state-of-the-art fidelity and accuracy, along with a 30% FPS improvement over baseline 3DGS.
  arXiv  Detail & Related papers  (2024-11-19T11:59:54Z)
• Evaluating geometric accuracy of NeRF reconstructions compared to SLAM method [0.0]
  Photogrammetry can perform image-based 3D reconstruction but is computationally expensive and requires extremely dense image representation to recover complex geometry and photorealism. NeRFs perform 3D scene reconstruction by training a neural network on sparse image and pose data, achieving superior results to photogrammetry with less input data. This paper presents an evaluation of two NeRF scene reconstructions for the purpose of estimating the diameter of a vertical PVC cylinder.
  arXiv  Detail & Related papers  (2024-07-15T21:04:11Z)
• 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)
• Bootstrap 3D Reconstructed Scenes from 3D Gaussian Splatting [10.06208115191838]
  We present a bootstrapping method to enhance the rendering of novel views using trained 3D-GS. Our results indicate that bootstrapping effectively reduces artifacts, as well as clear enhancements on the evaluation metrics.
  arXiv  Detail & Related papers  (2024-04-29T12:57:05Z)
• 2D Gaussian Splatting for Geometrically Accurate Radiance Fields [50.056790168812114]
  3D Gaussian Splatting (3DGS) has recently revolutionized radiance field reconstruction, achieving high quality novel view synthesis and fast rendering speed without baking. We present 2D Gaussian Splatting (2DGS), a novel approach to model and reconstruct geometrically accurate radiance fields from multi-view images. We demonstrate that our differentiable terms allows for noise-free and detailed geometry reconstruction while maintaining competitive appearance quality, fast training speed, and real-time rendering.
  arXiv  Detail & Related papers  (2024-03-26T17:21:24Z)
• ReconFusion: 3D Reconstruction with Diffusion Priors [104.73604630145847]
  We present ReconFusion to reconstruct real-world scenes using only a few photos. Our approach leverages a diffusion prior for novel view synthesis, trained on synthetic and multiview datasets. Our method synthesizes realistic geometry and texture in underconstrained regions while preserving the appearance of observed regions.
  arXiv  Detail & Related papers  (2023-12-05T18:59:58Z)
• Enhancing Neural Rendering Methods with Image Augmentations [59.00067936686825]
  We study the use of image augmentations in learning neural rendering methods (NRMs) for 3D scenes. We find that introducing image augmentations during training presents challenges such as geometric and photometric inconsistencies. Our experiments demonstrate the benefits of incorporating augmentations when learning NRMs, including improved photometric quality and surface reconstruction.
  arXiv  Detail & Related papers  (2023-06-15T07:18:27Z)
• GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields [12.92658687936068]
  We take advantage of generative adversarial networks (GANs) to produce realistic images and use them to enhance realism in 3D scene reconstruction with NeRFs. We learn the patch distribution of a scene using an adversarial discriminator, which provides feedback to the radiance field reconstruction. rendering artifacts are repaired directly in the underlying 3D representation by imposing multi-view path rendering constraints.
  arXiv  Detail & Related papers  (2023-06-09T17:12:35Z)
• PlaNeRF: SVD Unsupervised 3D Plane Regularization for NeRF Large-Scale Scene Reconstruction [2.2369578015657954]
  Neural Radiance Fields (NeRF) enable 3D scene reconstruction from 2D images and camera poses for Novel View Synthesis (NVS) NeRF often suffers from overfitting to training views, leading to poor geometry reconstruction. We propose a new method to improve NeRF's 3D structure using only RGB images and semantic maps.
  arXiv  Detail & Related papers  (2023-05-26T13:26:46Z)
• AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training [100.33713282611448]
  We conduct the first pilot study on training NeRF with high-resolution data. We propose the corresponding solutions, including marrying the multilayer perceptron with convolutional layers. Our approach is nearly free without introducing obvious training/testing costs.
  arXiv  Detail & Related papers  (2022-11-17T17:22:28Z)
• NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction [50.54946139497575]
  We propose NeRFusion, a method that combines the advantages of NeRF and TSDF-based fusion techniques to achieve efficient large-scale reconstruction and photo-realistic rendering. We demonstrate that NeRFusion achieves state-of-the-art quality on both large-scale indoor and small-scale object scenes, with substantially faster reconstruction than NeRF and other recent methods.
  arXiv  Detail & Related papers  (2022-03-21T18:56:35Z)

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.