Progressively Optimized Local Radiance Fields for Robust View Synthesis

03/24/2023
by   Andreas Meuleman, et al.
0

We present an algorithm for reconstructing the radiance field of a large-scale scene from a single casually captured video. The task poses two core challenges. First, most existing radiance field reconstruction approaches rely on accurate pre-estimated camera poses from Structure-from-Motion algorithms, which frequently fail on in-the-wild videos. Second, using a single, global radiance field with finite representational capacity does not scale to longer trajectories in an unbounded scene. For handling unknown poses, we jointly estimate the camera poses with radiance field in a progressive manner. We show that progressive optimization significantly improves the robustness of the reconstruction. For handling large unbounded scenes, we dynamically allocate new local radiance fields trained with frames within a temporal window. This further improves robustness (e.g., performs well even under moderate pose drifts) and allows us to scale to large scenes. Our extensive evaluation on the Tanks and Temples dataset and our collected outdoor dataset, Static Hikes, show that our approach compares favorably with the state-of-the-art.

READ FULL TEXT

page 1

page 4

page 5

page 7

page 8

research
01/05/2023

Robust Dynamic Radiance Fields

Dynamic radiance field reconstruction methods aim to model the time-vary...
research
03/21/2023

Pre-NeRF 360: Enriching Unbounded Appearances for Neural Radiance Fields

Neural radiance fields (NeRF) appeared recently as a powerful tool to ge...
research
03/29/2021

GNeRF: GAN-based Neural Radiance Field without Posed Camera

We introduce GNeRF, a framework to marry Generative Adversarial Networks...
research
06/08/2023

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs

A critical obstacle preventing NeRF models from being deployed broadly i...
research
08/21/2023

CamP: Camera Preconditioning for Neural Radiance Fields

Neural Radiance Fields (NeRF) can be optimized to obtain high-fidelity 3...
research
07/09/2019

Progressive Refinement Imaging

This paper presents a novel technique for progressive online integration...
research
11/23/2021

Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields

Though neural radiance fields (NeRF) have demonstrated impressive view s...

Please sign up or login with your details

Forgot password? Click here to reset