Related papers: FG-DFPN: Flow Guided Deformable Frame Prediction N…
The great success of Deep Neural Networks (DNNs) has inspired the algorithmic development of DNN-based Fixed-Point (DNN-FP) for computer vision tasks. DNN-FP methods, trained by Back-Propagation Through Time or computing the inaccurate…
Predicting future frames of a video sequence has been a problem of high interest in the field of Computer Vision as it caters to a multitude of applications. The ability to predict, anticipate and reason about future events is the essence…
FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classification, while other fundamental vision problems, including…
Future Frame Synthesis (FFS), the task of generating subsequent video frames from context, represents a core challenge in machine intelligence and a cornerstone for developing predictive world models. This survey provides a comprehensive…
Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots. While recent scene flow estimation approaches achieve a reasonable accuracy,…
Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a…
Traffic prediction is a critical component of intelligent transportation systems, enabling applications such as congestion mitigation and accident risk prediction. While recent research has explored both graph-based and grid-based…
Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneously, these applications are often not restricted to…
Feature pyramid network (FPN) is a critical component in modern object detection frameworks. The performance gain in most of the existing FPN variants is mainly attributed to the increase of computational burden. An attempt to enhance the…
A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data…
Diffusion models have made significant strides in image generation, mastering tasks such as unconditional image synthesis, text-image translation, and image-to-image conversions. However, their capability falls short in the realm of video…
Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…
Motion estimation is one of the core challenges in computer vision. With traditional dual-frame approaches, occlusions and out-of-view motions are a limiting factor, especially in the context of environmental perception for vehicles due to…
We propose a neural network model to estimate the current frame from two reference frames, using affine transformation and adaptive spatially-varying filters. The estimated affine transformation allows for using shorter filters compared to…
In this paper, we propose a deformable convolution-based generative adversarial network (DCNGAN) for perceptual quality enhancement of compressed videos. DCNGAN is also adaptive to the quantization parameters (QPs). Compared with optical…
This paper considers the challenging task of long-term video interpolation. Unlike most existing methods that only generate few intermediate frames between existing adjacent ones, we attempt to speculate or imagine the procedure of an…
This paper describes a study based on computational fluid dynamics (CFD) and deep neural networks that focusing on predicting the flow field in differently distorted U-shaped pipes. The main motivation of this work was to get an insight…
Learning reliable motion representation between consecutive frames, such as optical flow, has proven to have great promotion to video understanding. However, the TV-L1 method, an effective optical flow solver, is time-consuming and…
Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and…
We introduce FLAG-4D, a novel framework for generating novel views of dynamic scenes by reconstructing how 3D Gaussian primitives evolve through space and time. Existing methods typically rely on a single Multilayer Perceptron (MLP) to…