3 papers
cs.CV2026
Registration-Free Hyperspectral Reconstruction from RGB via a Permutation-Invariant Gram-Matrix Principle
Jiangsan Zhao, Masayuki Hirafuji, Seishi Ninomiya +2
Reconstructing a spatially and spectrally high-resolution hyperspectral image (HR-HSI) from a low-resolution HSI (LR-HSI) and a high-resolution RGB image (HR-RGB) usually assumes p…
cs.CV2026
From Implicit Ambiguity to Explicit Solidity: Diagnosing Interior Geometric Degradation in Neural Radiance Fields for Dense 3D Scene Understanding
Jiangsan Zhao, Jakob Geipel, Kryzysztof Kusnierek
Neural Radiance Fields (NeRFs) have emerged as a powerful paradigm for multi-view reconstruction, complementing classical photogrammetric pipelines based on Structure-from-Motion (…
cs.CV2025
InvNeRF-Seg: Fine-Tuning a Pre-Trained NeRF for 3D Object Segmentation
Jiangsan Zhao, Jakob Geipel, Krzysztof Kusnierek +1
Neural Radiance Fields (NeRF) have been widely adopted for reconstructing high quality 3D point clouds from 2D RGB images. However, the segmentation of these reconstructed 3D scene…