MrNeRF (@janusch_patas)
2025-12-23 | โค๏ธ 30 | ๐ 4
WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion
Contributions:
-
WorldWarp: A novel framework for long-range novel view extrapolation that generates video chunk-by-chunk using an autoregressive inference pipeline.
-
Spatio-Temporal Diffusion (ST-Diff): A non-causal diffusion model that leverages bidirectional attention conditioned on forward-warped images as a dense geometric prior.
-
An online 3D geometric cache mechanism: Uses test-time optimized 3DGS [25] to provide high-fidelity warped priors while preventing the irreversible error propagation of static 3D representations.
-
State-of-the-art performance on challenging view extrapolation benchmarks, demonstrating significantly improved geometric consistency and image quality over existing methods.
๐ Related
- objsplat-geometry-aware-gaussian-surfels-for-active-object
- gen3r-3d-scene-generation-meets-feed-forward-reconstruction
- gaussianfluent-explicit-gaussian-simulation-for-dynamic
- video-generation-but-4d-dynamic-scene-consistent-and-very
- gamo-geometry-aware-multi-view-diffusion-outpainting-for