paper-with-me

홈 › Papers

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

2021-03-25 · ICCV 2021 10 · Christian Reiser, Songyou Peng, Yiyi Liao, Andreas Geiger

NeRF synthesizes novel views of a scene with unprecedented quality by fitting a neural radiance field to RGB images. However, NeRF requires querying a deep Multi-Layer Perceptron (MLP) millions of times, leading to slow rendering times, even on modern GPUs. In this paper, we demonstrate that real-time rendering is possible by utilizing thousands of tiny MLPs instead of one single large MLP. In our setting, each individual MLP only needs to represent parts of the scene, thus smaller and faster-to-evaluate MLPs can be used. By combining this divide-and-conquer strategy with further optimizations, rendering is accelerated by three orders of magnitude compared to the original NeRF model without incurring high storage costs. Further, using teacher-student distillation for training, we show that this speed-up can be achieved without sacrificing visual quality.

📄 PDF Abstract BibTeX arXiv:2103.13744

Code (4)

creiser/kilonerf 공식 구현 pytorch
MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/KiloNeRF_Speeding_up_Neural_Radiance_Fields_with_Thousands_of_Tiny_MLPs pytorch
nitthilan/kilonerf_modified pytorch
openxrlab/xrnerf pytorch

Tasks

NeRF

Methods 이 논문이 사용한 방법론

Robinhood Customer Care Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Tiny-DroNeRF: Tiny Neural Radiance Fields aboard Federated Learning-enabled Nano-drones

2026-03-02 · Ilenia Carboni, Elia Cereda, Lorenzo Lamberti, Daniele Malpetti 외 arxiv

Sub-30g nano-sized aerial robots can leverage their agility and form factor to autonomously explore cluttered and narrow environments, like in industrial inspection and search and rescue missions. However, the price for …

Federated Learning3D ReconstructionMotion Planning

Fast Dynamic Radiance Fields with Time-Aware Neural Voxels

2022-05-30 · Jiemin Fang, Taoran Yi, Xinggang Wang, Lingxi Xie 외

Neural radiance fields (NeRF) have shown great success in modeling 3D scenes and synthesizing novel-view images. However, most previous NeRF methods take much time to optimize one single scene. Explicit data structures, …

NeRF

Differentiable Rendering with Reparameterized Volume Sampling

2023-02-21 · Nikita Morozov, Denis Rakitin, Oleg Desheulin, Dmitry Vetrov 외

In view synthesis, a neural radiance field approximates underlying density and radiance fields based on a sparse set of scene pictures. To generate a pixel of a novel view, it marches a ray through the pixel and computes…

NeRFNovel View Synthesis

PaletteNeRF: Palette-based Color Editing for NeRFs

2022-12-25 · Qiling Wu, Jianchao Tan, Kun Xu

Neural Radiance Field (NeRF) is a powerful tool to faithfully generate novel views for scenes with only sparse captured images. Despite its strong capability for representing 3D scenes and their appearance, its editing a…

NeRF

AdaNeRF: Adaptive Sampling for Real-time Rendering of Neural Radiance Fields

2022-07-21 · Andreas Kurz, Thomas Neff, Zhaoyang Lv, Michael Zollhöfer 외

Novel view synthesis has recently been revolutionized by learning neural radiance fields directly from sparse observations. However, rendering images with this new paradigm is slow due to the fact that an accurate quadra…

Novel View Synthesis