MultiShapeNet

Videos of novel scenes created by LFN, PixelNerf, and SRT on the Multi-ShapeNet dataset. For each new scene, 5 input views are provided to the model and 600 frames are rendered.

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)

Input Views (x5)

LFN

PN

SRT (Ours)