Recursive-NeRF: An Efficient and Dynamically Growing NeRF

• URL: http://arxiv.org/abs/2105.09103v1
• Date: Wed, 19 May 2021 12:51:54 GMT
• Title: Recursive-NeRF: An Efficient and Dynamically Growing NeRF
• Authors: Guo-Wei Yang, Wen-Yang Zhou, Hao-Yang Peng, Dun Liang, Tai-Jiang Mu, Shi-Min Hu
• Abstract summary: Recursive-NeRF is an efficient rendering and training approach for the Neural Radiance Field (NeRF) method. Recursive-NeRF learns uncertainties for query coordinates, representing the quality of the predicted color and volumetric intensity at each level. Our evaluation on three public datasets shows that Recursive-NeRF is more efficient than NeRF while providing state-of-the-art quality.
• Score: 34.768382663711705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: View synthesis methods using implicit continuous shape representations learned from a set of images, such as the Neural Radiance Field (NeRF) method, have gained increasing attention due to their high quality imagery and scalability to high resolution. However, the heavy computation required by its volumetric approach prevents NeRF from being useful in practice; minutes are taken to render a single image of a few megapixels. Now, an image of a scene can be rendered in a level-of-detail manner, so we posit that a complicated region of the scene should be represented by a large neural network while a small neural network is capable of encoding a simple region, enabling a balance between efficiency and quality. Recursive-NeRF is our embodiment of this idea, providing an efficient and adaptive rendering and training approach for NeRF. The core of Recursive-NeRF learns uncertainties for query coordinates, representing the quality of the predicted color and volumetric intensity at each level. Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability. The final rendered image is a composition of results from neural networks of all levels. Our evaluation on three public datasets shows that Recursive-NeRF is more efficient than NeRF while providing state-of-the-art quality. The code will be available at https://github.com/Gword/Recursive-NeRF.

Related papers

• Evaluation of strategies for efficient rate-distortion NeRF streaming [4.117347527143616]
  Neural Radiance Fields (NeRF) have revolutionized the field of 3D visual representation by enabling highly realistic and detailed scene reconstructions from a sparse set of images. Despite its advancements, the efficient streaming of NeRF content remains a significant challenge due to the large amount of data involved. This paper investigates the rate-distortion performance of two NeRF streaming strategies: pixel-based and neural network (NN) parameter-based streaming.
  arXiv  Detail & Related papers  (2024-10-25T10:40:03Z)
• 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)
• MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields [49.68916478541697]
  We develop a Memory-Efficient Incremental Learning algorithm for NeRF (MEIL-NeRF) MEIL-NeRF takes inspiration from NeRF itself in that a neural network can serve as a memory that provides the pixel RGB values, given rays as queries. As a result, MEIL-NeRF demonstrates constant memory consumption and competitive performance.
  arXiv  Detail & Related papers  (2022-12-16T08:04:56Z)
• SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction [147.9379707578091]
  NeRFmm is the Neural Radiance Fields (NeRF) that deal with Joint Optimization tasks. Despite NeRFmm producing precise scene synthesis and pose estimations, it still struggles to outperform the full-annotated baseline on challenging scenes. We propose Sinusoidal Neural Radiance Fields (SiNeRF) that leverage sinusoidal activations for radiance mapping and a novel Mixed Region Sampling (MRS) for selecting ray batch efficiently.
  arXiv  Detail & Related papers  (2022-10-10T10:47:51Z)
• Aug-NeRF: Training Stronger Neural Radiance Fields with Triple-Level Physically-Grounded Augmentations [111.08941206369508]
  We propose Augmented NeRF (Aug-NeRF), which for the first time brings the power of robust data augmentations into regularizing the NeRF training. Our proposal learns to seamlessly blend worst-case perturbations into three distinct levels of the NeRF pipeline. Aug-NeRF effectively boosts NeRF performance in both novel view synthesis and underlying geometry reconstruction.
  arXiv  Detail & Related papers  (2022-07-04T02:27:07Z)
• 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)
• pixelNeRF: Neural Radiance Fields from One or Few Images [20.607712035278315]
  pixelNeRF is a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. We conduct experiments on ShapeNet benchmarks for single image novel view synthesis tasks with held-out objects. In all cases, pixelNeRF outperforms current state-of-the-art baselines for novel view synthesis and single image 3D reconstruction.
  arXiv  Detail & Related papers  (2020-12-03T18:59:54Z)

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.