Hedman, P;
Philip, J;
Price, T;
Frahm, J-M;
Drettakis, G;
Brostow, G;
(2018)
Deep Blending for Free-Viewpoint Image-Based Rendering.
ACM Transactions on Graphics
, 37
, Article 6. 10.1145/3272127.3275084.
Preview |
Text
Deep_IBR_draft_fromOverleaf.pdf - Accepted Version Download (90MB) | Preview |
Abstract
Free-viewpoint image-based rendering (IBR) is a standing challenge. IBR methods combine warped versions of input photos to synthesize a novel view. The image quality of this combination is directly afected by geometric inaccuracies of multi-view stereo (MVS) reconstruction and by view-and image-dependent efects that produce artifacts when contributions from different input views are blended. We present a new deep learning approach to blending for IBR, in which we use held-out real image data to learn blending weights to combine input photo contributions. Our Deep Blending method requires us to address several challenges to achieve our goal of interactive free-viewpoint IBR navigation.We irst need to provide suiciently accurate geometry so the Convolutional Neural Network (CNN) can succeed in inding correct blending weights. We do this by combining two diferent MVS reconstructions with complementary accuracy vs. completeness tradeofs. To tightly integrate learning in an interactive IBR system, we need to adapt our rendering algorithm to produce a ixed number of input layers that can then be blended by the CNN. We generate training data with a variety of captured scenes, using each input photo as ground truth in a held-out approach. We also design the network architecture and the training loss to provide high quality novel view synthesis, while reducing temporal lickering artifacts. Our results demonstrate free-viewpoint IBR in a wide variety of scenes, clearly surpassing previous methods in visual quality, especially when moving far from the input cameras.
| Type: | Article |
|---|---|
| Title: | Deep Blending for Free-Viewpoint Image-Based Rendering |
| Location: | Tokyo, JAPAN |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1145/3272127.3275084 |
| Publisher version: | http://doi.org/10.1145/3272127.3275084 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Deep learning, free-viewpoint, image-based rendering |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10117776 |
Archive Staff Only
 |
View Item |
