paper-with-me

홈 › Papers

BathyFacto: Refraction-Aware Two-Media Neural Radiance Fields for Bathymetry

2026-05-11 · Markus Brezovsky, Anatol Günthner, Frederik Schulte, Lukas Winiwarter, Boris Jutzi, Gottfried Mandlburger arxiv

Through-water photogrammetry based on UAV imagery enables shallow-water bathymetry, but refraction at the air-water interface violates the straight-ray assumption of Structure-from-Motion and causes systematic depth bias. We present BathyFacto, a refraction-aware two-media extension of Nerfacto integrated into Nerfstudio that targets metrically precise underwater point clouds. BathyFacto uses a shared hash-grid-based density field with a medium-conditioned color head that receives a one-bit medium flag (air or water) and traces each camera ray as two segments: a straight segment in air up to a planar water surface and a refracted segment in water computed via Snell's law with known refractive indices. To allocate samples efficiently across the air-water boundary, we employ a single proposal-network sampler that operates on a virtual straight ray spanning both media, combined with a kinked density wrapper that transparently corrects water-segment positions along the refracted direction before density evaluation. A data adaptation pipeline converts photogrammetric reconstructions to a Nerfstudio-compatible format, estimates the water plane from boundary markers, and provides per-pixel medium masks to gate refraction. We also extend the point cloud export with refraction-corrected backprojection and reversible coordinate transforms to world and global frames. On a simulated two-media scene with known ground truth, BathyFacto with refraction achieves a Cloud-to-Mesh mean distance of 0.06 m and 87 % completeness, compared to 0.52 m / 29 % for the Nerfacto baseline and 0.36 m / 21% for conventional MVS without refraction correction.

📄 PDF Abstract BibTeX arXiv:2605.10174

Code (0)

등록된 구현이 없습니다.

Tasks

Point Clouds

Similar Papers 제목 키워드 기반

REF$^2$-NeRF: Reflection and Refraction aware Neural Radiance Field

2023-11-28 · Wooseok Kim, Taiki Fukiage, Takeshi Oishi

Recently, significant progress has been made in the study of methods for 3D reconstruction from multiple images using implicit neural representations, exemplified by the neural radiance field (NeRF) method. Such methods,…

3D ReconstructionNeRF

TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians

2025-04-26 · Letian Huang, Dongwei Ye, Jialin Dan, Chengzhi Tao 외

The emergence of neural and Gaussian-based radiance field methods has led to considerable advancements in novel view synthesis and 3D object reconstruction. Nonetheless, specular reflection and refraction continue to pos…

3D Object ReconstructionInverse RenderingNovel View SynthesisObject Reconstruction+1

Multi-Space Neural Radiance Fields

2023-05-07 · CVPR 2023 1 · Ze-Xin Yin, Jiaxiong Qiu, Ming-Ming Cheng, Bo Ren

Existing Neural Radiance Fields (NeRF) methods suffer from the existence of reflective objects, often resulting in blurry or distorted rendering. Instead of calculating a single radiance field, we propose a multi-space n…

NeRF

Learning Neural Light Fields With Ray-Space Embedding

2022-01-01 · CVPR 2022 1 · Benjamin Attal, Jia-Bin Huang, Michael Zollhöfer, Johannes Kopf 외

Neural radiance fields (NeRFs) produce state-of-the-art view synthesis results, but are slow to render, requiring hundreds of network evaluations per pixel to approximate a volume rendering integral. Baking NeRFs int…

NeRF

NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields

2023-09-22 · Xiaoxue Chen, Junchen Liu, Hao Zhao, Guyue Zhou 외

Neural radiance fields (NeRF) have revolutionized the field of image-based view synthesis. However, NeRF uses straight rays and fails to deal with complicated light path changes caused by refraction and reflection. This …

3D ReconstructionNeRFObject