相关论文: Lie Flow: Video Dynamic Fields Modeling and Predic…

Estimating 2D camera motion is a fundamental computer vision task that models the projection of 3D camera movements onto the 2D image plane. Current methods rely on either homography-based approaches, limited to planar scenes, or meshflow…

Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. These challenges degrade the performance of the existing methods in…

Talking head generation based on the neural radiation fields model has shown promising visual effects. However, the slow rendering speed of NeRF seriously limits its application, due to the burdensome calculation process over hundreds of…

Neural radiance fields (NeRFs) are a powerful tool for implicit scene representations, allowing for differentiable rendering and the ability to make predictions about unseen viewpoints. There has been growing interest in object and…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the…

This paper focuses on a novel approach for detecting moving objects during camera motion. We present an optical-flow-based transformation that yields a consistent 2D invariant image output regardless of time instants, range of points in 3D,…

Modeling and forecasting subsurface multiphase fluid flow fields underpin applications ranging from geological CO2 sequestration (GCS) operations to geothermal production. This is essential for ensuring both operational performance and…

Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under…

We present a survey on 4D generation and reconstruction, a fast-evolving subfield of computer graphics whose developments have been propelled by recent advances in neural fields, geometric and motion deep learning, as well as 3D generative…

Estimation of 3D motion in a dynamic scene from a temporal pair of images is a core task in many scene understanding problems. In real world applications, a dynamic scene is commonly captured by a moving camera (i.e., panning, tilting or…

In this work, we aim to detect the changes caused by object variations in a scene represented by the neural radiance fields (NeRFs). Given an arbitrary view and two sets of scene images captured at different timestamps, we can predict the…

Parametric human models capture global pose but cannot represent the non-rigid surface dynamics of clothing and soft tissue. Generic scene flow estimates dense motion but breaks down on articulated bodies, where pixel-level supervision is…

We present dynamic neural radiance fields for modeling the appearance and dynamics of a human face. Digitally modeling and reconstructing a talking human is a key building-block for a variety of applications. Especially, for telepresence…

This paper presents novel techniques for recovering 3D dense scene flow, based on differential analysis of 4D light fields. The key enabling result is a per-ray linear equation, called the ray flow equation, that relates 3D scene flow to 4D…

This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model. Existence of dynamic objects in the environment can cause artifacts and traces in current…

In this paper, we aim to model 3D scene dynamics from multi-view videos. Unlike the majority of existing works which usually focus on the common task of novel view synthesis within the training time period, we propose to simultaneously…

Learning representations through deep generative modeling is a powerful approach for dynamical modeling to discover the most simplified and compressed underlying description of the data, to then use it for other tasks such as prediction.…

Flow Matching (FM) is a recent generative modelling technique: we aim to learn how to sample from distribution $\mathfrak{X}_1$ by flowing samples from some distribution $\mathfrak{X}_0$ that is easy to sample from. The key trick is that…

Sampling viable 3D structures (e.g., molecules and point clouds) with SE(3)-invariance using diffusion-based models proved promising in a variety of real-world applications, wherein SE(3)-invariant properties can be naturally characterized…