pixelNeRF: Neural Radiance Fields from One or Few Images

12/03/2020
by   Alex Yu, et al.
3

We propose pixelNeRF, a learning framework that predicts a continuous neural scene representation conditioned on one or few input images. The existing approach for constructing neural radiance fields involves optimizing the representation to every scene independently, requiring many calibrated views and significant compute time. We take a step towards resolving these shortcomings by introducing an architecture that conditions a NeRF on image inputs in a fully convolutional manner. This allows the network to be trained across multiple scenes to learn a scene prior, enabling it to perform novel view synthesis in a feed-forward manner from a sparse set of views (as few as one). Leveraging the volume rendering approach of NeRF, our model can be trained directly from images with no explicit 3D supervision. We conduct extensive experiments on ShapeNet benchmarks for single image novel view synthesis tasks with held-out objects as well as entire unseen categories. We further demonstrate the flexibility of pixelNeRF by demonstrating it on multi-object ShapeNet scenes and real scenes from the DTU dataset. In all cases, pixelNeRF outperforms current state-of-the-art baselines for novel view synthesis and single image 3D reconstruction. For the video and code, please visit the project website: https://alexyu.net/pixelnerf

READ FULL TEXT

page 2

page 3

page 4

page 9

page 10

page 11

page 15

page 19

research
03/19/2020

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

We present a method that achieves state-of-the-art results for synthesiz...
research
01/18/2023

Behind the Scenes: Density Fields for Single View Reconstruction

Inferring a meaningful geometric scene representation from a single imag...
research
09/08/2022

im2nerf: Image to Neural Radiance Field in the Wild

We propose im2nerf, a learning framework that predicts a continuous neur...
research
08/24/2023

NeO 360: Neural Fields for Sparse View Synthesis of Outdoor Scenes

Recent implicit neural representations have shown great results for nove...
research
04/02/2021

Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation

We present ObSuRF, a method which turns a single image of a scene into a...
research
04/02/2022

SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image

Despite the rapid development of Neural Radiance Field (NeRF), the neces...
research
04/01/2022

SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Tasks

Real-world autonomous driving datasets comprise of images aggregated fro...

Please sign up or login with your details

Forgot password? Click here to reset