Casual Indoor HDR Radiance Capture from Omnidirectional Images

08/16/2022
by   Pulkit Gera, et al.
0

We present PanoHDR-NeRF, a novel pipeline to casually capture a plausible full HDR radiance field of a large indoor scene without elaborate setups or complex capture protocols. First, a user captures a low dynamic range (LDR) omnidirectional video of the scene by freely waving an off-the-shelf camera around the scene. Then, an LDR2HDR network uplifts the captured LDR frames to HDR, subsequently used to train a tailored NeRF++ model. The resulting PanoHDR-NeRF pipeline can estimate full HDR panoramas from any location of the scene. Through experiments on a novel test dataset of a variety of real scenes with the ground truth HDR radiance captured at locations not seen during training, we show that PanoHDR-NeRF predicts plausible radiance from any scene point. We also show that the HDR images produced by PanoHDR-NeRF can synthesize correct lighting effects, enabling the augmentation of indoor scenes with synthetic objects that are lit correctly.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 8

research
08/22/2023

ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes

We present ScanNet++, a large-scale dataset that couples together captur...
research
07/24/2018

GRAINS: Generative Recursive Autoencoders for INdoor Scenes

We present a generative neural network which enables us to generate plau...
research
11/04/2020

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

For many fundamental scene understanding tasks, it is difficult or impos...
research
06/29/2017

Analysis and Modeling of 3D Indoor Scenes

We live in a 3D world, performing activities and interacting with object...
research
09/26/2016

Swipe Mosaics from Video

A panoramic image mosaic is an attractive visualization for viewing many...
research
05/05/2022

BlobGAN: Spatially Disentangled Scene Representations

We propose an unsupervised, mid-level representation for a generative mo...
research
11/11/2018

Improved Visual Relocalization by Discovering Anchor Points

We address the visual relocalization problem of predicting the location ...

Please sign up or login with your details

Forgot password? Click here to reset