CD | Crest | Food | Gaint | Lab | Pasta | Seasoning | Tools |
431 | 601 | 389 | 398 | 394 | 348 | 338 | 335 |
Fern | Flower | Fortress | Horns | Leaves | Orchids | Room | Trex |
393 | 498 | 289 | 554 | 628 | 471 | 435 | 325 |
We present NeX, a new approach to novel view synthesis based on enhancements of multiplane image (MPI) that can reproduce NeXt-level view-dependent effects---in real time. Unlike traditional MPI that uses a set of simple RGBα planes, our technique models view-dependent effects by instead parameterizing each pixel as a linear combination of basis functions learned from a neural network. Moreover, we propose a hybrid implicit-explicit modeling strategy that improves upon fine detail and produces state-of-the-art results. Our method is evaluated on benchmark forward-facing datasets as well as our newly-introduced dataset designed to test the limit of view-dependent modeling with significantly more challenging effects such as the rainbow reflections on a CD. Our method achieves the best overall scores across all major metrics on these datasets with more than 1000× faster rendering time than the state of the art.
*A high-end GPU recommended for High and VR modes.
This table shows the average FPS for the scenes in Shiny and Real Forward-Facing datasets. The rendering was done in real time using Google Chrome’s WebGL on a machine with an NVIDIA RTX3090. (Profiling done without Vertical Synchronization (Vsync) to go beyond the monitor’s frame rate)
CD | Crest | Food | Gaint | Lab | Pasta | Seasoning | Tools |
431 | 601 | 389 | 398 | 394 | 348 | 338 | 335 |
Fern | Flower | Fortress | Horns | Leaves | Orchids | Room | Trex |
393 | 498 | 289 | 554 | 628 | 471 | 435 | 325 |
BibTex
@inproceedings{Wizadwongsa2021NeX, author = {Wizadwongsa, Suttisak and Phongthawee, Pakkapon and Yenphraphai, Jiraphon and Suwajanakorn, Supasorn}, title = {NeX: Real-time View Synthesis with Neural Basis Expansion}, booktitle = {IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, year = {2021}, }
Repurposing GANs for One-shot Semantic Part Segmentation
CVPR 2021 (Oral)