Here we show rendered views from our method and other baselines on the Neural 3D Video dataset. Note that we show our results and ENeRF at 2048x1536 (2K) and SIMPLI and GPNR at 1024x768 because SIMPLI and GPNR fail to produce high-resolution results at 2K.
Hover over the labels at the left to select which output to view. Hold mouse down anywhere to flip to ground truth for comparison.
coffee_martini/0190
cook_spinach/0190
cut_roasted_beef/0190
flame_salmon_1/0190
flame_steak/0190
sear_steak/0190