Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

UW-GS: Distractor-Aware 3D Gaussian Splatting for Enhanced Underwater Scene Reconstruction

About

3D Gaussian splatting (3DGS) offers the capability to achieve real-time high quality 3D scene rendering. However, 3DGS assumes that the scene is in a clear medium environment and struggles to generate satisfactory representations in underwater scenes, where light absorption and scattering are prevalent and moving objects are involved. To overcome these, we introduce a novel Gaussian Splatting-based method, UW-GS, designed specifically for underwater applications. It introduces a color appearance that models distance-dependent color variation, employs a new physics-based density control strategy to enhance clarity for distant objects, and uses a binary motion mask to handle dynamic content. Optimized with a well-designed loss function supporting for scattering media and strengthened by pseudo-depth maps, UW-GS outperforms existing methods with PSNR gains up to 1.26dB. To fully verify the effectiveness of the model, we also developed a new underwater dataset, S-UW, with dynamic object masks.

Haoran Wang, Nantheera Anantrasirichai, Fan Zhang, David Bull• 2024

Related benchmarks

TaskDatasetResultRank
Underwater 3D ReconstructionSubmerged3D (test)
PSNR28.4065
35
Underwater 3D ReconstructionSeaThru-NeRF (val)
PSNR31.0023
35
Underwater 3D ReconstructionS-UW
PSNR26.9103
35
Novel View SynthesisOmniUW synthetic (deepsea)
PSNR26.6
16
Novel View SynthesisOmniUW synthetic (rocks)
PSNR35.09
16
Novel View SynthesisOmniUW synthetic (pool)
PSNR26.47
16
Novel View SynthesisOmniUW synthetic (building)
PSNR31.59
16
Novel View SynthesisOmniUW ship synthetic
PSNR32.84
15
Novel View SynthesisInsta360 scene1
PSNR23.27
15
Novel View SynthesisInsta360 scene3
PSNR23.52
15
Showing 10 of 17 rows

Other info

Follow for update