Related papers: Temporal View Synthesis of Dynamic Scenes through …

Temporal modeling is crucial for multi-frame human pose estimation. Most existing methods directly employ optical flow or deformable convolution to predict full-spectrum motion fields, which might incur numerous irrelevant cues, such as a…

We present a data-driven approach for 4D space-time visualization of dynamic events from videos captured by hand-held multiple cameras. Key to our approach is the use of self-supervised neural networks specific to the scene to compose…

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…

A long-standing goal in computer vision is to capture, model, and realistically synthesize human behavior. Specifically, by learning from data, our goal is to enable virtual humans to navigate within cluttered indoor scenes and naturally…

Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…

Detecting salient objects from a video requires exploiting both spatial and temporal knowledge included in the video. We propose a novel region-based multiscale spatiotemporal saliency detection method for videos, where static features and…

This paper presents WALDO (WArping Layer-Decomposed Objects), a novel approach to the prediction of future video frames from past ones. Individual images are decomposed into multiple layers combining object masks and a small set of control…

This paper addresses the challenge of learning semantically and functionally meaningful 3D motion priors from real-world videos, in order to enable prediction of future 3D scene motion from a single input image. We propose a novel…

Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…

Predicting the future in real-world settings, particularly from raw sensory observations such as images, is exceptionally challenging. Real-world events can be stochastic and unpredictable, and the high dimensionality and complexity of…

We present an approach for pixel-level future prediction given an input image of a scene. We observe that a scene is comprised of distinct entities that undergo motion and present an approach that operationalizes this insight. We implicitly…

Editing faces in videos is a popular yet challenging aspect of computer vision and graphics, which encompasses several applications including facial attractiveness enhancement, makeup transfer, face replacement, and expression manipulation.…

Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other scene changes. While recent methods can predict specific…

A recent frontier in computer vision has been the task of 3D video generation, which consists of generating a time-varying 3D representation of a scene. To generate dynamic 3D scenes, current methods explicitly model 3D temporal dynamics by…

Rendering photo-realistic novel-view images of complex scenes has been a long-standing challenge in computer graphics. In recent years, great research progress has been made on enhancing rendering quality and accelerating rendering speed in…

Stochastic video prediction models take in a sequence of image frames, and generate a sequence of consecutive future image frames. These models typically generate future frames in an autoregressive fashion, which is slow and requires the…

Estimating accurate camera poses, 3D scene geometry, and object motion from in-the-wild videos is a long-standing challenge for classical structure from motion pipelines due to the presence of dynamic objects. Recent learning-based methods…

Novel view synthesis (NVS) and video prediction (VP) are typically considered disjoint tasks in computer vision. However, they can both be seen as ways to observe the spatial-temporal world: NVS aims to synthesize a scene from a new point…

Learning to predict the long-term future of video frames is notoriously challenging due to inherent ambiguities in the distant future and dramatic amplifications of prediction error through time. Despite the recent advances in the…

We study the problem of synthesizing a number of likely future frames from a single input image. In contrast to traditional methods, which have tackled this problem in a deterministic or non-parametric way, we propose a novel approach that…