arXiv Computer Vision By Kui Jiang, Yang Gu, Jiacheng Liu, Shiyu Liu, Youyu Chen, Hui Liu

Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware Optimization

Read the original on arXiv Computer Vision →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Hugging Face Trending Papers
Sep 10

Tri-DehazeGS: Scene--Medium Decoupled Gaussian Splatting with Transmittance-Aware Optimization

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 Computer Vision
Sep 11

FujinSplat: Seeing Through Smoke with RAW-Domain Gaussian Splatting

FujinSplat is a method for reconstructing clean 3D scenes from images captured through smoke by operating in the RAW image domain, where the camera’s ISP and the medium’s scattering effects remain separable. It first learns a per‑scene base ISP from hazy RAW captures, then uses a low‑dimensional correction space to fit per‑view corrections at training poses, and finally trains a scene‑agnostic controller to predict these corrections from RAW input. The corrected views supervise a single static 3D Gaussian representation, with a bounded per‑view residual to reconcile cross‑view inconsistencies, achieving superior performance on the RealX3D smoke benchmark compared to physics‑based and restoration‑then‑3DGS baselines.

By Gengjia Chang, Ziteng Cui, Shuhong Liu
arXiv AI
Sep 10

DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image Dehazing

DPSF-Net is a dual‑prior spatial‑frequency network designed for real‑world remote sensing image dehazing. It combines hazy RGB images with dark channel prior maps as joint inputs, and incorporates a spatial‑frequency residual interaction block, a prior‑guided feature attention module, and a selective kernel complementary fusion module to reduce colour shift, structural distortion, and large‑scale haze. Experiments show that DPSF-Net achieves state‑of‑the‑art performance on the RRSHID benchmark while maintaining a favorable balance of restoration quality, parameter count, and computational complexity.

By Mei Lu, Shangliang Shao, Shanliang Yao