arXiv:2605.21440v2 Announce Type: replace Abstract: Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing...
arXiv:2610.19274v1 Announce Type: cross Abstract: Atmospheric turbulence creates complex spatial and temporal distortions that significantly reduce image quality. This work compares two deep learning...
Tri‑DehazeGS is a Gaussian Splatting framework that decouples clean scene reconstruction from atmospheric haze by representing the scene with Gaussian primitives and the haze medium with an independent view‑shared tri‑plane field. It uses a physical scattering model to compose hazy observations and introduces Medium‑Decoupled Transmittance Gradient Compensation (MD‑TGC) to re‑balance gradients in low‑transmittance regions without altering forward rendering. Experiments on real and synthetic haze benchmarks demonstrate that this approach improves clean novel‑view reconstruction.
arXiv:2607. 20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction.
Tri-DehazeGS tackles the problem of reconstructing clean 3D scenes from hazy multi‑view images by decoupling the scene and the haze medium. It represents the scene with Gaussian primitives while modeling the haze as an independent view‑shared tri‑plane field, and composes hazy observations through a physical scattering model. The method introduces Medium‑Decoupled Transmittance Gradient Compensation (MD‑TGC) to balance gradients in low‑transmittance regions, leading to improved novel‑view reconstruction on real and synthetic haze benchmarks.
arXiv:2506.19445v5 Announce Type: replace Abstract: Motion blur remains one of the most common and visually disruptive degradations in real-world smartphone imaging, yet existing deblurring benchmark...
arXiv:2506. 19445v4 Announce Type: cross Abstract: We introduce the largest real-world image deblurring dataset constructed from smartphone slow-motion videos.
arXiv:2609.21391v1 Announce Type: cross Abstract: Neural Radiance Fields (NeRF) have attracted extensive attention in recent years due to their strong capability for high-quality 3D reconstruction an...
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.
ASTRA-SR is a blind single‑frame restoration framework designed for ground‑based planetary imaging, addressing atmospheric turbulence, sensor noise, and limited sampling. It is trained on a physics‑grounded synthetic dataset that uses high‑dynamic‑range spacecraft RAW observations as clean sources and synthesizes low‑resolution inputs with realistic turbulence, PSFs, and noise. The method first produces a noise‑suppressed but blur‑retaining low‑resolution image, then restores spatial structure via multiscale processing and refines high‑resolution detail with serial spatial‑amplitude refinement, achieving a 0.49 dB PSNR gain over the strongest baseline approaches.
arXiv:2609.38438v1 Announce Type: cross Abstract: Machine learning surrogate models offer a promising path toward accelerating plasma turbulence simulations. We present PreVAE-Turb, a surrogate model...
Existing diffusion-based methods have recently made significant progress in image dehazing. However, they typically neglect the physics of haze formation and reconstruct clean images from pure Gaussian noise, thereby limiting their restoration potential.