R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis

• URL: http://arxiv.org/abs/2203.17261v1
• Date: Thu, 31 Mar 2022 17:57:05 GMT
• Title: R2L: Distilling Neural Radiance Field to Neural Light Field for Efficient Novel View Synthesis
• Authors: Huan Wang, Jian Ren, Zeng Huang, Kyle Olszewski, Menglei Chai, Yun Fu, Sergey Tulyakov
• Abstract summary: 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.
• Score: 76.07010495581535
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent research explosion on Neural Radiance Field (NeRF) shows the encouraging potential to represent complex scenes with neural networks. One major drawback of NeRF is its prohibitive inference time: Rendering a single pixel requires querying the NeRF network hundreds of times. To resolve it, existing efforts mainly attempt to reduce the number of required sampled points. However, the problem of iterative sampling still exists. On the other hand, Neural Light Field (NeLF) presents a more straightforward representation over NeRF in novel view synthesis -- the rendering of a pixel amounts to one single forward pass without ray-marching. In this work, we present a deep residual MLP network (88 layers) to effectively learn the light field. We show the key to successfully learning such a deep NeLF network is to have sufficient data, for which we transfer the knowledge from a pre-trained NeRF model via data distillation. Extensive experiments on both synthetic and real-world scenes show the merits of our method over other counterpart algorithms. On the synthetic scenes, we achieve 26-35x FLOPs reduction (per camera ray) and 28-31x runtime speedup, meanwhile delivering significantly better (1.4-2.8 dB average PSNR improvement) rendering quality than NeRF without any customized implementation tricks.

Related papers

• NeRF-VPT: Learning Novel View Representations with Neural Radiance Fields via View Prompt Tuning [63.39461847093663]
  We propose NeRF-VPT, an innovative method for novel view synthesis to address these challenges. Our proposed NeRF-VPT employs a cascading view prompt tuning paradigm, wherein RGB information gained from preceding rendering outcomes serves as instructive visual prompts for subsequent rendering stages. NeRF-VPT only requires sampling RGB data from previous stage renderings as priors at each training stage, without relying on extra guidance or complex techniques.
  arXiv  Detail & Related papers  (2024-03-02T22:08:10Z)
• ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields [27.008124938806944]
  We propose ProNeRF, which provides an optimal trade-off between memory footprint (similar to NeRF), speed (faster than HyperReel), and quality (better than K-Planes) Our ProNeRF yields state-of-the-art metrics, being 15-23x faster with 0.65dB higher PSNR than NeRF and yielding 0.95dB higher PSNR than the best published sampler-based method, HyperReel.
  arXiv  Detail & Related papers  (2023-12-13T13:37:32Z)
• Efficient View Synthesis with Neural Radiance Distribution Field [61.22920276806721]
  We propose a new representation called Neural Radiance Distribution Field (NeRDF) that targets efficient view synthesis in real-time. We use a small network similar to NeRF while preserving the rendering speed with a single network forwarding per pixel as in NeLF. Experiments show that our proposed method offers a better trade-off among speed, quality, and network size than existing methods.
  arXiv  Detail & Related papers  (2023-08-22T02:23:28Z)
• Multi-Space Neural Radiance Fields [74.46513422075438]
  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.
  arXiv  Detail & Related papers  (2023-05-07T13:11:07Z)
• 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)
• DONeRF: Towards Real-Time Rendering of Neural Radiance Fields using Depth Oracle Networks [6.2444658061424665]
  DONeRF is a dual network design with a depth oracle network as a first step and a locally sampled shading network for ray accumulation. We are the first to render raymarching-based neural representations at interactive frame rates (15 frames per second at 800x800) on a single GPU.
  arXiv  Detail & Related papers  (2021-03-04T18:55:09Z)
• iNeRF: Inverting Neural Radiance Fields for Pose Estimation [68.91325516370013]
  We present iNeRF, a framework that performs mesh-free pose estimation by "inverting" a Neural RadianceField (NeRF) NeRFs have been shown to be remarkably effective for the task of view synthesis.
  arXiv  Detail & Related papers  (2020-12-10T18:36:40Z)

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.