| CARVIEW |
Select Language
HTTP/2 301
server: GitHub.com
content-type: text/html
location: https://lvsn.github.io/PanoHDR-NeRF/
access-control-allow-origin: *
expires: Sun, 28 Dec 2025 16:22:29 GMT
cache-control: max-age=600
x-proxy-cache: MISS
x-github-request-id: EDF1:2B0FD4:7D4B0D:8C64EF:695156EC
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 16:12:29 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210049-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766938349.362895,VS0,VE204
vary: Accept-Encoding
x-fastly-request-id: 6867bf08a71d14b6d3a0a015a63f6b8608064ee7
content-length: 162
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
x-origin-cache: HIT
last-modified: Thu, 11 Dec 2025 15:41:18 GMT
access-control-allow-origin: *
etag: W/"693ae61e-2e60"
expires: Sun, 28 Dec 2025 16:22:29 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: A32E:2BC55:7CE8FB:8C04F5:695156ED
accept-ranges: bytes
age: 0
date: Sun, 28 Dec 2025 16:12:29 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210049-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1766938350.580991,VS0,VE205
vary: Accept-Encoding
x-fastly-request-id: ae355d904f0f7bdbfc0d9e874084d2332a16a139
content-length: 3455
Casual Indoor HDR Radiance Capture from Omnidirectional Images
|
Charles Renaud P J Narayanan Jean-François Lalonde 
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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. |
 |
Pulkit Gera, Mohammed Reza Karimi Dastjerdi, Charles Renaud,P.J Narayanan, Jean-François Lalonde Casual Indoor HDR Radiance Capture from Omnidirectional Images (hosted on ArXiv) |
Video
Presentation @ OmniCV-2022, CVPR-W
Dataset
| Scene 001 | Scene 002 | Scene 003 | Scene 004 |