Results 51 to 60 of about 4,408 (223)

NIRGB‐GS: Near‐Infrared Assisted Low‐Light Scene Reconstruction and Enhancement via Gaussian Splatting

Advanced Intelligent Systems, EarlyView.
This article proposes NIRGB‐GS, a multimodal 3DGS variant that enables reliable 3D reconstruction and normal‐light novel‐view synthesis for extremely low‐light scenes by fusing paired near‐infrared and noisy RGB captures. High‐SNR near‐infrared modality and modality‐specific appearance encoding together resolve the issues of unstable pose/geometry ...
Chengyun Yang, Yi Zhang, Yu Lei, Qiaofeng Li   +3 more
wiley   +1 more source

BRDF-NeRF: Neural radiance fields with optical satellite images and BRDF modelling

International Journal of Applied Earth Observations and Geoinformation
Neural radiance fields (NeRF) have gained prominence as a machine learning technique for representing 3D scenes and estimating the bidirectional reflectance distribution function (BRDF) from multiple images. However, most existing research has focused on
Lulin Zhang, Ewelina Rupnik, Tri Dung Nguyen, Stéphane Jacquemoud, Yann Klinger   +4 more
doaj   +1 more source

NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
This research aims to assess the adaptability of Neural Radiance Fields (NeRF) for the digital documentation of cultural heritage objects of varying size and complexity.
V. Croce, G. Forleo, D. Billi, M. G. Bevilacqua, A. Piemonte, G. Caroti   +5 more
doaj   +1 more source

Splatshop: Efficiently Editing Large Gaussian Splat Models

Computer Graphics Forum, EarlyView.
Abstract We present Splatshop, a highly optimized toolbox for interactive editing (selection, deletion, painting, transformation, …) of 3D Gaussian Splatting models. Utilizing a comprehensive collection of heuristic approaches, we carefully balance between exact and fast rendering to enable precise editing without sacrificing real‐time performance. Our
Markus Schütz, Christoph Peters, Florian Hahlbohm, Elmar Eisemann, Marcus Magnor, Michael Wimmer   +5 more
wiley   +1 more source

IW-NeRF: Using Implicit Watermarks to Protect the Copyright of Neural Radiation Fields

Applied Sciences
The neural radiance field (NeRF) has demonstrated significant advancements in computer vision. However, the training process for NeRF models necessitates extensive computational resources and ample training data.
Lifeng Chen, Chaoyue Song, Jia Liu, Wenquan Sun, Weina Dong, Fuqiang Di   +5 more
doaj   +1 more source

PSHead: 3D Head Reconstruction from a Single Image with Diffusion Prior and Self‐Enhancement

Computer Graphics Forum, EarlyView.
We introduce PSHead, a coarse‐to‐fine framework guided by both object and face priors, to produce a Gaussian‐based 3D avatar for a single frontal‐view reference image. In the coarse stage, we create an initial 3D representation by applying diffusion models trained for general object generation, using Score Distillation Sampling losses over novel views.
Jing Yang, Tianhan Wu, Kyle Fogarty, Fangcheng Zhong, Cengiz Oztireli   +4 more
wiley   +1 more source

Neural Radiance Fields (NeRFs): A Review and Some Recent Developments

CoRR, 2023
Neural Radiance Field (NeRF) is a framework that represents a 3D scene in the weights of a fully connected neural network, known as the Multi-Layer Perception(MLP). The method was introduced for the task of novel view synthesis and is able to achieve state-of-the-art photorealistic image renderings from a given continuous viewpoint. NeRFs have become a
openaire   +2 more sources

NeRF--: Neural Radiance Fields Without Known Camera Parameters

CoRR, 2021
Project page see https://nerfmm.active.vision.
Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, Victor Adrian Prisacariu   +4 more
openaire   +2 more sources

NePO: Neural Point Octrees for Large‐Scale Novel View Synthesis

Computer Graphics Forum, EarlyView.
We introduce Neural Point Octrees (NePOs), a scalable radiance field representation that organises point clouds hierarchically for efficient optimisation and rendering of large scale scenes. NePOs enable level of detail selection, joint refinement of appearance and camera poses, and real‐time rendering of hundreds of millions of points.
Noah Lewis, Darius Rückert, Marc Stamminger, Linus Franke   +3 more
wiley   +1 more source

Hyperspectral Neural Radiance Field Method Based on Reference Spectrum

IEEE Access
The Neural Radiance Field (NeRF) method for datasets is gaining attention for its wide applications and research value. Hyperspectral images have also gained many applications in recent years.
Runchuan Ma, Sailing He
doaj   +1 more source