Related papers: Flow-Guided Transformer for Video Inpainting

Video motion transfer aims to generate a target video that inherits motion patterns from a source video while rendering new scenes. Existing training-free approaches focus on constructing motion guidance based on the intermediate outputs of…

Forecasting the future states of surrounding traffic participants is a crucial capability for autonomous vehicles. The recently proposed occupancy flow field prediction introduces a scalable and effective representation to jointly predict…

This paper introduces EasyAnimate, an efficient and high quality video generation framework that leverages diffusion transformers to achieve high-quality video production, encompassing data processing, model training, and end-to-end…

Image editing in rectified flow models remains challenging due to the fundamental trade-off between reconstruction fidelity and editing flexibility. While inversion-based methods suffer from trajectory deviation, recent inversion-free…

Motion transfer from the driving to the source portrait remains a key challenge in the portrait animation. Current diffusion-based approaches condition only on the driving motion, which fails to capture source-to-driving correspondences and…

Rectified Flow text-to-image models surpass diffusion models in image quality and text alignment, but adapting ReFlow for real-image editing remains challenging. We propose a new real-image editing method for ReFlow by analyzing the…

Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information across frames. While such approaches have led to significant…

Flow in fractured porous media is modeled frequently by discrete fracture-matrix approaches where fractures are treated as dimensionally reduced manifolds. Generalizing earlier work we focus on two-phase flow in time-dependent fracture…

Planning and acting in 3D environments is a fundamental capability for robotic manipulation in the real world. Although prior work has explored predictive flow planners to guide 3D manipulation, existing approaches often rely on modular…

Perceiving and reconstructing 3D geometry from videos is a fundamental yet challenging computer vision task. To facilitate interactive and low-latency applications, we propose a streaming visual geometry transformer that shares a similar…

Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference…

Event-based vision sensors offer asynchronous, high-temporal-resolution measurements that are attractive for low-latency robotic perception, but many event-based motion estimation methods are computationally intensive and difficult to map…

Video prediction is a challenging computer vision task that has a wide range of applications. In this work, we present a new family of Transformer-based models for video prediction. Firstly, an efficient local spatial-temporal separation…

In this paper, we propose a randomized generalized multiscale finite element method (Randomized GMsFEM) for flow problems with parameterized inputs and high-contrast heterogeneous media. The method employs a data-driven predictor to…

In this paper we present advanced representation learning study on integrating deep learning techniques and sparse approximation, including diffusion models, for advanced flow field analysis and reconstruction. Key applications include…

In this paper, we propose an algorithm to interpolate between a pair of images of a dynamic scene. While in the past years significant progress in frame interpolation has been made, current approaches are not able to handle images with…

Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low…

Scene flow, which provides the 3D motion field of the first frame from two consecutive point clouds, is vital for dynamic scene perception. However, contemporary scene flow methods face three major challenges. Firstly, they lack global flow…

Current optical flow methods exploit the stable appearance of frame (or RGB) data to establish robust correspondences across time. Event cameras, on the other hand, provide high-temporal-resolution motion cues and excel in challenging…

Scalar features in time-dependent fluid flow are traditionally visualized using 3D representation, and their topology changes over time are often conveyed with abstract graphs. Using such techniques, however, the structural details of…