Progressively-connected Light Field Network for Efficient View Synthesis

07/10/2022
by   Peng Wang, et al.
0

This paper presents a Progressively-connected Light Field network (ProLiF), for the novel view synthesis of complex forward-facing scenes. ProLiF encodes a 4D light field, which allows rendering a large batch of rays in one training step for image- or patch-level losses. Directly learning a neural light field from images has difficulty in rendering multi-view consistent images due to its unawareness of the underlying 3D geometry. To address this problem, we propose a progressive training scheme and regularization losses to infer the underlying geometry during training, both of which enforce the multi-view consistency and thus greatly improves the rendering quality. Experiments demonstrate that our method is able to achieve significantly better rendering quality than the vanilla neural light fields and comparable results to NeRF-like rendering methods on the challenging LLFF dataset and Shiny Object dataset. Moreover, we demonstrate better compatibility with LPIPS loss to achieve robustness to varying light conditions and CLIP loss to control the rendering style of the scene. Project page: https://totoro97.github.io/projects/prolif.

READ FULL TEXT

page 1

page 2

page 4

page 6

page 7

page 8

page 9

page 12

research
03/10/2023

Aleth-NeRF: Low-light Condition View Synthesis with Concealing Fields

Common capture low-light scenes are challenging for most computer vision...
research
08/09/2020

Neural Reflectance Fields for Appearance Acquisition

We present Neural Reflectance Fields, a novel deep scene representation ...
research
06/09/2023

GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields

Neural Radiance Fields (NeRF) have shown impressive novel view synthesis...
research
05/07/2023

Multi-Space Neural Radiance Fields

Existing Neural Radiance Fields (NeRF) methods suffer from the existence...
research
04/22/2023

Dehazing-NeRF: Neural Radiance Fields from Hazy Images

Neural Radiance Field (NeRF) has received much attention in recent years...
research
07/11/2022

A Learned Radiance-Field Representation for Complex Luminaires

We propose an efficient method for rendering complex luminaires using a ...
research
04/20/2023

ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects

In this paper, we focus on the problem of rendering novel views from a N...

Please sign up or login with your details

Forgot password? Click here to reset