4K-NeRF: High Fidelity Neural Radiance Fields at Ultra High Resolutions

12/09/2022
by   Zhongshu Wang, et al.
0

In this paper, we present a novel and effective framework, named 4K-NeRF, to pursue high fidelity view synthesis on the challenging scenarios of ultra high resolutions, building on the methodology of neural radiance fields (NeRF). The rendering procedure of NeRF-based methods typically relies on a pixel wise manner in which rays (or pixels) are treated independently on both training and inference phases, limiting its representational ability on describing subtle details especially when lifting to a extremely high resolution. We address the issue by better exploring ray correlation for enhancing high-frequency details benefiting from the use of geometry-aware local context. Particularly, we use the view-consistent encoder to model geometric information effectively in a lower resolution space and recover fine details through the view-consistent decoder, conditioned on ray features and depths estimated by the encoder. Joint training with patch-based sampling further facilitates our method incorporating the supervision from perception oriented regularization beyond pixel wise loss. Quantitative and qualitative comparisons with modern NeRF methods demonstrate that our method can significantly boost rendering quality for retaining high-frequency details, achieving the state-of-the-art visual quality on 4K ultra-high-resolution scenario. Code Available at <https://github.com/frozoul/4K-NeRF>

READ FULL TEXT

page 1

page 6

page 7

page 8

page 11

page 12

research
06/17/2020

XRayGAN: Consistency-preserving Generation of X-ray Images from Radiology Reports

To effectively train medical students to become qualified radiologists, ...
research
11/17/2022

AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training

Neural Radiance Fields (NeRFs) are a powerful representation for modelin...
research
06/07/2021

DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Rendering

We introduce DoubleField, a novel representation combining the merits of...
research
05/31/2022

Novel View Synthesis for High-fidelity Headshot Scenes

Rendering scenes with a high-quality human face from arbitrary viewpoint...
research
06/21/2022

EpiGRAF: Rethinking training of 3D GANs

A very recent trend in generative modeling is building 3D-aware generato...
research
09/27/2022

Im2Oil: Stroke-Based Oil Painting Rendering with Linearly Controllable Fineness Via Adaptive Sampling

This paper proposes a novel stroke-based rendering (SBR) method that tra...
research
03/03/2021

ID-Unet: Iterative Soft and Hard Deformation for View Synthesis

View synthesis is usually done by an autoencoder, in which the encoder m...

Please sign up or login with your details

Forgot password? Click here to reset