SlimDiffSR uses uncertainty-guided timestep assignment and structured pruning with frequency- and direction-separable convolutions plus MMD distillation to create a 200x faster, 20x smaller diffusion SR model for remote sensing while retaining competitive quality.
High-resolution image synthesis with latent diffusion models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3verdicts
UNVERDICTED 3representative citing papers
Seen-to-Scene unifies propagation-based and generation-based approaches for video outpainting via fine-tuned flow completion and reference-guided latent propagation to deliver superior temporal coherence and efficiency.
SPAGS reconstructs articulated objects from sparse single-state RGB images by constraining Gaussians to planar primitives, optimizing with depth and diffusion priors, and using a VLM for part segmentation and joint estimation.
citing papers explorer
-
SlimDiffSR: Toward Lightweight and Efficient Remote Sensing Image Super-Resolution via Diffusion Model Distillation
SlimDiffSR uses uncertainty-guided timestep assignment and structured pruning with frequency- and direction-separable convolutions plus MMD distillation to create a 200x faster, 20x smaller diffusion SR model for remote sensing while retaining competitive quality.
-
Seen-to-Scene: Keep the Seen, Generate the Unseen for Video Outpainting
Seen-to-Scene unifies propagation-based and generation-based approaches for video outpainting via fine-tuned flow completion and reference-guided latent propagation to deliver superior temporal coherence and efficiency.
-
SPAGS: Sparse-View Articulated Object Reconstruction from Single State via Planar Gaussian Splatting
SPAGS reconstructs articulated objects from sparse single-state RGB images by constraining Gaussians to planar primitives, optimizing with depth and diffusion priors, and using a VLM for part segmentation and joint estimation.