SOTAVerified

Perpetual View Generation

Perpetual View Generation is the task of generating long-range novel views by flying into a given image.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–7 of 7 papers

TitleStatusHype
DreamJourney: Perpetual View Generation with Video Diffusion Models—0
StarGen: A Spatiotemporal Autoregression Framework with Video Diffusion Model for Scalable and Controllable Scene Generation—0
DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators—0
SceneScape: Text-Driven Consistent Scene Generation—0
DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models—0
InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single ImagesCode0
Infinite Nature: Perpetual View Generation of Natural Scenes from a Single ImageCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InfNat-ZeroFID (first 20 steps)39.45—Unverified
2DiffDreamerFID (first 20 steps)34.49—Unverified