Related papers: Learning Rigidity in Dynamic Scenes with a Moving …

Conventional image motion based structure from motion methods first compute optical flow, then solve for the 3D motion parameters based on the epipolar constraint, and finally recover the 3D geometry of the scene. However, errors in optical…

Scene recognition is one of the basic problems in computer vision research with extensive applications in robotics. When available, depth images provide helpful geometric cues that complement the RGB texture information and help to identify…

Estimating dense 2D optical flow and 3D scene flow is essential for dynamic scene understanding. Recent work combines images, LiDAR, and event data to jointly predict 2D and 3D motion, yet most approaches operate in separate heterogeneous…

Reconstruction of 3D neural fields from posed images has emerged as a promising method for self-supervised representation learning. The key challenge preventing the deployment of these 3D scene learners on large-scale video data is their…

In this paper, we propose a global method for estimating the motion of a camera which films a static scene. Our approach is direct, fast and robust, and deals with adjacent frames of a sequence. It is based on a quadratic approximation of…

There has been extensive progress in the reconstruction and generation of 4D scenes from monocular casually-captured video. While these tasks rely heavily on known camera poses, the problem of finding such poses using structure-from-motion…

In this paper, we aim to jointly model the geometry, appearance, and physical information of 3D scenes solely from dynamic multi-view videos, without relying on any physical priors. Existing works typically employ physical losses merely as…

We investigate how a residual network can learn to predict the dynamics of interacting shapes purely as an image-to-image regression task. With a simple 2d physics simulator, we generate short sequences composed of rectangles put in motion…

3D scene flow estimation aims to estimate point-wise motions between two consecutive frames of point clouds. Superpoints, i.e., points with similar geometric features, are usually employed to capture similar motions of local regions in 3D…

Video classification is productive in many practical applications, and the recent deep learning has greatly improved its accuracy. However, existing works often model video frames indiscriminately, but from the view of motion, video frames…

We address the challenging problem of dense dynamic scene reconstruction and camera pose estimation from multiple freely moving cameras -- a setting that arises naturally when multiple observers capture a shared event. Prior approaches…

We propose a new multi-frame method for efficiently computing scene flow (dense depth and optical flow) and camera ego-motion for a dynamic scene observed from a moving stereo camera rig. Our technique also segments out moving objects from…

Generating videos guided by camera trajectories poses significant challenges in achieving consistency and generalizability, particularly when both camera and object motions are present. Existing approaches often attempt to learn these…

Nowadays, it is possible to scan faces and automatically register them with high quality. However, the resulting face meshes often need further processing: we need to stabilize them to remove unwanted head movement. Stabilization is…

Mask-based lensless cameras replace the lens of a conventional camera with a custom mask. These cameras can potentially be very thin and even flexible. Recently, it has been demonstrated that such mask-based cameras can recover light…

3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completeness -- objects have 3D occupancy, even if only partial…

We study the problem of self-supervised 3D scene flow estimation from real large-scale raw point cloud sequences, which is crucial to various tasks like trajectory prediction or instance segmentation. In the absence of ground truth scene…

Current deep neural network approaches for camera pose estimation rely on scene structure for 3D motion estimation, but this decreases the robustness and thereby makes cross-dataset generalization difficult. In contrast, classical…

Videos shot by laymen using hand-held cameras contain undesirable shaky motion. Estimating the global motion between successive frames, in a manner not influenced by moving objects, is central to many video stabilization techniques, but…

With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…