ZID-Net decouples diffusion-based priors into a training-only head to create an efficient feed-forward network for single-image dehazing, reporting 40.75 dB PSNR on RESIDE and 19 ms inference.
Udpnet: Unleashing depth-based priors for robust image de- hazing
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.CV 3years
2026 3roles
background 2polarities
background 2representative citing papers
A multi-stage pipeline of restoration, dehazing, MLLM enhancement and 3D Gaussian Splatting with MCMC averaging achieves first place in the NTIRE 2026 smoke-degraded novel view synthesis track.
The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.
citing papers explorer
-
ZID-Net: Zero-Inference Diffusion Prior Decoupling Network for Single Image Dehazing
ZID-Net decouples diffusion-based priors into a training-only head to create an efficient feed-forward network for single-image dehazing, reporting 40.75 dB PSNR on RESIDE and 19 ms inference.
-
GenSmoke-GS: A Multi-Stage Method for Novel View Synthesis from Smoke-Degraded Images Using a Generative Model
A multi-stage pipeline of restoration, dehazing, MLLM enhancement and 3D Gaussian Splatting with MCMC averaging achieves first place in the NTIRE 2026 smoke-degraded novel view synthesis track.
-
NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.