相关论文: Self-supervised Light Field View Synthesis Using C…

While deep-learning based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training. To eliminate expensive and exhaustive annotation, we study self-supervised…

Generated video scenes for action-centric sequence descriptions, such as recipe instructions and do-it-yourself projects, often include non-linear patterns, where the next video may need to be visually consistent not with the immediately…

Despite significant progress on current state-of-the-art image generation models, synthesis of document images containing multiple and complex object layouts is a challenging task. This paper presents a novel approach, called DocSynth, to…

The rapid development of inexpensive commodity depth sensors has made keypoint detection and matching in the depth image modality an important problem in computer vision. Despite great improvements in recent RGB local feature learning…

Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining both synthesis-based and warping networks. However, few of…

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…

View synthesis aims to generate novel views from one or more given source views. Although existing methods have achieved promising performance, they usually require paired views of different poses to learn a pixel transformation. This paper…

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…

Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors. Existing video interpolation methods usually assume uniform motion between consecutive frames and use linear…

3D Gaussian Splatting (3DGS) has demonstrated impressive performance in synthesizing novel views after training on a given set of viewpoints. However, its rendering quality deteriorates when the synthesized view deviates significantly from…

We propose VISION-SLS, a method for nonlinear output-feedback control from high-resolution RGB images which provides robust constraint satisfaction guarantees under calibrated uncertainty bounds despite partial observability, sensor noise,…

Light field (LF) technology is considered as a promising way for providing a high-quality virtual reality (VR) content. However, such an imaging technology produces a large amount of data requiring efficient LF image compression solutions.…

We present a large-scale synthetic dataset for novel view synthesis consisting of ~300k images rendered from nearly 2000 complex scenes using high-quality ray tracing at high resolution (1600 x 1600 pixels). The dataset is orders of…

Information retrieval techniques have demonstrated exceptional capabilities in identifying semantic similarities across diverse domains through robust feature representations. However, their potential in guiding synthesis tasks,…

We present a novel approach to view synthesis using multiplane images (MPIs). Building on recent advances in learned gradient descent, our algorithm generates an MPI from a set of sparse camera viewpoints. The resulting method incorporates…

In this work, we propose a method to address the challenge of rendering a 3D human from a single image in a free-view manner. Some existing approaches could achieve this by using generalizable pixel-aligned implicit fields to reconstruct a…

Cross-view localization and synthesis are two fundamental tasks in cross-view visual understanding, which deals with cross-view datasets: overhead (satellite or aerial) and ground-level imagery. These tasks have gained increasing attention…

View synthesis is usually done by an autoencoder, in which the encoder maps a source view image into a latent content code, and the decoder transforms it into a target view image according to the condition. However, the source contents are…

Currently almost all state-of-the-art novel view synthesis and reconstruction models rely on calibrated cameras or additional geometric priors for training. These prerequisites significantly limit their applicability to massive uncalibrated…

Video frame interpolation aims to synthesize nonexistent frames in-between the original frames. While significant advances have been made from the recent deep convolutional neural networks, the quality of interpolation is often reduced due…