Results 11 to 20 of about 24,246 (264)
SatGeo-NeRF: Geometrically Regularized NeRF for Satellite Imagery [PDF]
ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information SciencesWe present SatGeo-NeRF, a geometrically regularized NeRF for satellite imagery that mitigates overfitting-induced geometric artifacts observed in current state-of-the-art models using three model-agnostic regularizers.
V. Wagner +3 more
doaj +6 more sources
VM-NeRF: Tackling Sparsity in NeRF with View Morphing [PDF]
, 2023 NeRF aims to learn a continuous neural scene representation by using a finite set of input images taken from various viewpoints. A well-known limitation of NeRF methods is their reliance on data: the fewer the viewpoints, the higher the likelihood of overfitting.
Matteo Bortolon +2 more
core +7 more sources
HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork [PDF]
Advances in Neural Information Processing Systems 36, 2023 Project Page: https://hyp-nerf.github ...
Bipasha Sen +5 more
core +6 more sources
Specularity in NeRFs: A Comparative Study of Ref-NeRF and NRFF
Image Processing On LineNeural Radiance Fields (NeRF) have emerged as a leading technology for 3D digitization, especially for their high accuracy and intricate detailing. Despite their advancements, early NeRF models struggle to handle reflections on specular surfaces effectively.
Albert Barreiro +5 more
openaire +2 more sources
NeRF-In: Free-Form NeRF Inpainting with RGB-D Priors [PDF]
CoRR, 2022 Though Neural Radiance Field (NeRF) demonstrates compelling novel view synthesis results, it is still unintuitive to edit a pre-trained NeRF because the neural network's parameters and the scene geometry/appearance are often not explicitly associated.
Hao-Kang Liu +2 more
core +5 more sources
NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild [PDF]
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Neural Radiance Fields (NeRFs) have shown remarkable success in synthesizing photorealistic views from multi-view images of static scenes, but face challenges in dynamic, real-world environments with distractors like moving objects, shadows, and lighting
Weining Ren +5 more
semanticscholar +3 more sources
Clean-NeRF: Reformulating NeRF to account for View-Dependent Observations
CoRR, 2023 While Neural Radiance Fields (NeRFs) had achieved unprecedented novel view synthesis results, they have been struggling in dealing with large-scale cluttered scenes with sparse input views and highly view-dependent appearances. Specifically, existing NeRF-based models tend to produce blurry rendering with the volumetric reconstruction often inaccurate,
Xinhang Liu, Yu-Wing Tai, Chi-Keung Tang
openaire +4 more sources
DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF [PDF]
Computer Vision and Pattern RecognitionWe present DiSR-NeRF, a diffusion-guided framework for view-consistent super-resolution (SR) NeRF. Unlike prior works, we circumvent the requirement for high-resolution (HR) reference images by leveraging existing powerful 2D super-resolution models ...
Jie-Long Lee, Chen Li, Gim Hee Lee
semanticscholar +4 more sources
VF-NeRF: Viewshed Fields for Rigid NeRF Registration
3D scene registration is a fundamental problem in computer vision that seeks the best 6-DoF alignment between two scenes. This problem was extensively investigated in the case of point clouds and meshes, but there has been relatively limited work regarding Neural Radiance Fields (NeRF).
Leo Segre, Shai Avidan
openaire +4 more sources