DeblurNVS restores geometric representations via latent diffusion to enable high-fidelity novel view synthesis directly from sparse motion-blurred inputs.
Repurposing geometric foundation models for multi-view diffusion,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
GARD performs diffusion-based multi-view restoration in the feature space of a feed-forward 3D reconstructor to recover scene geometry and RGB images under degraded conditions, shown effective on the DA3 benchmark.
citing papers explorer
-
DeblurNVS: Geometric Latent Diffusion for Novel View Synthesis from Sparse Motion-Blurred Images
DeblurNVS restores geometric representations via latent diffusion to enable high-fidelity novel view synthesis directly from sparse motion-blurred inputs.
-
Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction
GARD performs diffusion-based multi-view restoration in the feature space of a feed-forward 3D reconstructor to recover scene geometry and RGB images under degraded conditions, shown effective on the DA3 benchmark.