Related papers: Novel View Synthesis via Depth-guided Skip Connect…
Zero-shot novel view synthesis (NVS) from a single image is an essential problem in 3D object understanding. While recent approaches that leverage pre-trained generative models can synthesize high-quality novel views from in-the-wild…
3D Gaussian Splatting (3DGS) has demonstrated remarkable real-time performance in novel view synthesis, yet its effectiveness relies heavily on dense multi-view inputs with precisely known camera poses, which are rarely available in…
Synthesizing novel views for urban environments is crucial for tasks like autonomous driving and virtual tours. Compared to object-level or indoor situations, outdoor settings present unique challenges, such as inconsistency across frames…
Novel view synthesis in 360$^\circ$ scenes from extremely sparse input views is essential for applications like virtual reality and augmented reality. This paper presents a novel framework for novel view synthesis in extremely sparse-view…
Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by…
A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints. We apply this representation to single-view view…
We propose UpFusion, a system that can perform novel view synthesis and infer 3D representations for an object given a sparse set of reference images without corresponding pose information. Current sparse-view 3D inference methods typically…
In this study, we propose two novel input processing paradigms for novel view synthesis (NVS) methods based on layered scene representations that significantly improve their runtime without compromising quality. Our approach identifies and…
Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities since their data association usually relies on feature correspondences. Additionally, learning-based SLAM systems often fall short in terms of real-time…
Novel View Synthesis (NVS) aims to generate unseen views of a 3D object given a limited number of known views. Existing methods often struggle to synthesize plausible views for unobserved regions, particularly under single-view input, and…
Novel view synthesis is a task of generating scenes from unseen perspectives; however, synthesizing dynamic scenes from blurry monocular videos remains an unresolved challenge that has yet to be effectively addressed. Existing novel view…
Scene flow estimation is a long-standing problem in computer vision, where the goal is to find the 3D motion of a scene from its consecutive observations. Recently, there have been efforts to compute the scene flow from 3D point clouds. A…
Synthesizing novel views from monocular videos of dynamic scenes remains a challenging problem. Scene-specific methods that optimize 4D representations with explicit motion priors often break down in highly dynamic regions where multi-view…
We introduce a method for using event camera data in novel view synthesis via Gaussian Splatting. Event cameras offer exceptional temporal resolution and a high dynamic range. Leveraging these capabilities allows us to effectively address…
We propose a novel approach for embedding novel views in a single JPEG image while preserving the perceptual fidelity of the modified JPEG image and the restored novel views. We adopt the popular novel view synthesis representation of…
Infrared and visible image fusion aims to generate synthetic images simultaneously containing salient features and rich texture details, which can be used to boost downstream tasks. However, existing fusion methods are suffering from the…
Decompositional reconstruction of 3D scenes, with complete shapes and detailed texture of all objects within, is intriguing for downstream applications but remains challenging, particularly with sparse views as input. Recent approaches…
The virtual viewpoint is perceived as a new technique in virtual navigation, as yet not supported due to the lack of depth information and obscure camera parameters. In this paper, a method for achieving close-up virtual view is proposed…
In medical imaging, there are clinically relevant segmentation tasks where the output mask is a projection to a subset of input image dimensions. In this work, we propose a novel convolutional neural network architecture that can…
Creating flexible 3D scenes from a single image is vital when direct 3D data acquisition is costly or impractical. We introduce NavCrafter, a novel framework that explores 3D scenes from a single image by synthesizing novel-view video…