Vision Transformer for NeRF-Based View Synthesis from a Single Input Image Supplementary Material

Vision Transformer for NeRF-Based View
Synthesis from a Single Input Image
Supplementary Material

arxiv preprint

Back

Cars Dataset (128 x 128, 24 FPS)

shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif



Chairs Dataset (128 x 128, 24 FPS)

shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif shapenet results gif



NMR Dataset (64 x 64, 6 FPS)

Images are bilinearly upsampled 2x

Plane

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Bench

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Cabinet

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Car

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Chair

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Display

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Lamp

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Rifle

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Sofa

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Table

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Phone

shapenet results gif shapenet results gif shapenet results gif shapenet results gif

Boat

shapenet results gif shapenet results gif shapenet results gif shapenet results gif