Related papers: S-VolSDF: Sparse Multi-View Stereo Regularization …

A commonly observed failure mode of Neural Radiance Field (NeRF) is fitting incorrect geometries when given an insufficient number of input views. One potential reason is that standard volumetric rendering does not enforce the constraint…

Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled…

Neural Radiance Field (NeRF) has recently emerged as a powerful representation to synthesize photorealistic novel views. While showing impressive performance, it relies on the availability of dense input views with highly accurate camera…

NeRF-based techniques fit wide and deep multi-layer perceptrons (MLPs) to a continuous radiance field that can be rendered from any unseen viewpoint. However, the lack of surface and normals definition and high rendering times limit their…

Remote sensing images (RSIs) in real scenes may be disturbed by multiple factors such as optical blur, undersampling, and additional noise, resulting in complex and diverse degradation models. At present, the mainstream SR algorithms only…

We present a framework, called MVG-NeRF, that combines classical Multi-View Geometry algorithms and Neural Radiance Fields (NeRF) for image-based 3D reconstruction. NeRF has revolutionized the field of implicit 3D representations, mainly…

In this paper, we study the problem of continuous 3D shape representations. The majority of existing successful methods are coordinate-based implicit neural representations. However, they are inefficient to render novel views or recover…

This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…

We present MS-Splatting -- a multi-spectral 3D Gaussian Splatting (3DGS) framework that is able to generate multi-view consistent novel views from images of multiple, independent cameras with different spectral domains. In contrast to…

Neural volumetric representations have become a widely adopted model for radiance fields in 3D scenes. These representations are fully implicit or hybrid function approximators of the instantaneous volumetric radiance in a scene, which are…

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…

Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facilitates the training of visual and audio-visual speech…

Neural radiance fields (NeRFs) have enabled high fidelity 3D reconstruction from multiple 2D input views. However, a well-known drawback of NeRFs is the less-than-ideal performance under a small number of views, due to insufficient…

Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image.…

Novel view synthesis is a long-standing problem that revolves around rendering frames of scenes from novel camera viewpoints. Volumetric approaches provide a solution for modeling occlusions through the explicit 3D representation of the…

Neural implicit surfaces have become an important technique for multi-view 3D reconstruction but their accuracy remains limited. In this paper, we argue that this comes from the difficulty to learn and render high frequency textures with…

Recently, Gaussian Splatting has sparked a new trend in the field of computer vision. Apart from novel view synthesis, it has also been extended to the area of multi-view reconstruction. The latest methods facilitate complete, detailed…

This paper proposes Sparse View Synthesis. This is a view synthesis problem where the number of reference views is limited, and the baseline between target and reference view is significant. Under these conditions, current radiance field…

With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D)…

Neural Radiance Fields (NeRF) has shown great success in novel view synthesis due to its state-of-the-art quality and flexibility. However, NeRF requires dense input views (tens to hundreds) and a long training time (hours to days) for a…