Multi-Space Neural Radiance Fields
- URL: http://arxiv.org/abs/2305.04268v1
- Date: Sun, 7 May 2023 13:11:07 GMT
- Title: Multi-Space Neural Radiance Fields
- Authors: Ze-Xin Yin and Jiaxiong Qiu and Ming-Ming Cheng and Bo Ren
- Abstract summary: Existing Neural Radiance Fields (NeRF) methods suffer from the existence of reflective objects.
We propose a multi-space neural radiance field (MS-NeRF) that represents the scene using a group of feature fields in parallel sub-spaces.
Our approach significantly outperforms the existing single-space NeRF methods for rendering high-quality scenes.
- Score: 74.46513422075438
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Existing Neural Radiance Fields (NeRF) methods suffer from the existence of
reflective objects, often resulting in blurry or distorted rendering. Instead
of calculating a single radiance field, we propose a multi-space neural
radiance field (MS-NeRF) that represents the scene using a group of feature
fields in parallel sub-spaces, which leads to a better understanding of the
neural network toward the existence of reflective and refractive objects. Our
multi-space scheme works as an enhancement to existing NeRF methods, with only
small computational overheads needed for training and inferring the extra-space
outputs. We demonstrate the superiority and compatibility of our approach using
three representative NeRF-based models, i.e., NeRF, Mip-NeRF, and Mip-NeRF 360.
Comparisons are performed on a novelly constructed dataset consisting of 25
synthetic scenes and 7 real captured scenes with complex reflection and
refraction, all having 360-degree viewpoints. Extensive experiments show that
our approach significantly outperforms the existing single-space NeRF methods
for rendering high-quality scenes concerned with complex light paths through
mirror-like objects. Our code and dataset will be publicly available at
https://zx-yin.github.io/msnerf.
Related papers
- NeRF-Casting: Improved View-Dependent Appearance with Consistent Reflections [57.63028964831785]
Recent works have improved NeRF's ability to render detailed specular appearance of distant environment illumination, but are unable to synthesize consistent reflections of closer content.
We address these issues with an approach based on ray tracing.
Instead of querying an expensive neural network for the outgoing view-dependent radiance at points along each camera ray, our model casts rays from these points and traces them through the NeRF representation to render feature vectors.
arXiv Detail & Related papers (2024-05-23T17:59:57Z) - Mesh2NeRF: Direct Mesh Supervision for Neural Radiance Field Representation and Generation [51.346733271166926]
Mesh2NeRF is an approach to derive ground-truth radiance fields from textured meshes for 3D generation tasks.
We validate the effectiveness of Mesh2NeRF across various tasks.
arXiv Detail & Related papers (2024-03-28T11:22:53Z) - Enhance-NeRF: Multiple Performance Evaluation for Neural Radiance Fields [2.5432277893532116]
Neural Radiance Fields (NeRF) can generate realistic images from any viewpoint.
NeRF-based models are susceptible to interference issues caused by colored "fog" noise.
Our approach, coined Enhance-NeRF, adopts joint color to balance low and high reflectivity objects display.
arXiv Detail & Related papers (2023-06-08T15:49:30Z) - Learning Neural Duplex Radiance Fields for Real-Time View Synthesis [33.54507228895688]
We propose a novel approach to distill and bake NeRFs into highly efficient mesh-based neural representations.
We demonstrate the effectiveness and superiority of our approach via extensive experiments on a range of standard datasets.
arXiv Detail & Related papers (2023-04-20T17:59:52Z) - 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) - R2L: Distilling Neural Radiance Field to Neural Light Field for
Efficient Novel View Synthesis [76.07010495581535]
Rendering a single pixel requires querying the Neural Radiance Field network hundreds of times.
NeLF presents a more straightforward representation over NeRF in novel view.
We show the key to successfully learning a deep NeLF network is to have sufficient data.
arXiv Detail & Related papers (2022-03-31T17:57:05Z) - NeRF-SR: High-Quality Neural Radiance Fields using Super-Sampling [82.99453001445478]
We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs.
Our method is built upon Neural Radiance Fields (NeRF) that predicts per-point density and color with a multi-layer perceptron.
arXiv Detail & Related papers (2021-12-03T07:33:47Z)
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.