Related papers: Spatiotemporal Bundle Adjustment for Dynamic 3D Hu…
Humans are in constant contact with the world as they move through it and interact with it. This contact is a vital source of information for understanding 3D humans, 3D scenes, and the interactions between them. In fact, we demonstrate…
Learning to understand dynamic 3D scenes from imagery is crucial for applications ranging from robotics to scene reconstruction. Yet, unlike other problems where large-scale supervised training has enabled rapid progress, directly…
This paper focuses on self-supervised video representation learning. Most existing approaches follow the contrastive learning pipeline to construct positive and negative pairs by sampling different clips. However, this formulation tends to…
This research proposes a novel adjustable algorithm for reconstructing 3D body shapes from front and side silhouettes. Most recent silhouette-based approaches use a deep neural network trained by silhouettes and key points to estimate the…
This paper presents a novel method to generate spatial constraints for motion planning in dynamic environments. Motion planning methods for autonomous driving and mobile robots typically need to rely on the spatial constraints imposed by a…
We introduce an approach that accurately reconstructs 3D human poses and detailed 3D full-body geometric models from single images in realtime. The key idea of our approach is a novel end-to-end multi-task deep learning framework that uses…
Multi-view stereo reconstruction (MVS) in the wild requires to first estimate the camera parameters e.g. intrinsic and extrinsic parameters. These are usually tedious and cumbersome to obtain, yet they are mandatory to triangulate…
This paper presents a self-supervised temporal video alignment framework which is useful for several fine-grained human activity understanding applications. In contrast with the state-of-the-art method of CASA, where sequences of 3D…
Video anomaly detection aims to discover abnormal events in videos, and the principal objects are target objects such as people and vehicles. Each target in the video data has rich spatio-temporal context information. Most existing methods…
Given enough multi-view image corresponding points (also called tie points) and ground control points (GCP), bundle adjustment for high-resolution satellite images is used to refine the orientations or most often used geometric parameters…
Despite recent progress in 3D hand reconstruction from monocular videos, most existing methods rely on data captured in well-controlled environments and therefore degrade in real-world settings with severe perturbations, such as hand-object…
Reconstructing high-fidelity and animatable 3D head avatars from monocular videos remains a challenging yet essential task. Existing methods based on 3D Gaussian Splatting typically bind Gaussians to mesh triangles and model deformations…
This paper presents SIM-Sync, a certifiably optimal algorithm that estimates camera trajectory and 3D scene structure directly from multiview image keypoints. SIM-Sync fills the gap between pose graph optimization and bundle adjustment; the…
Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits…
Multi-person pose understanding from RGB videos involves three complex tasks: pose estimation, tracking and motion forecasting. Intuitively, accurate multi-person pose estimation facilitates robust tracking, and robust tracking builds…
Image-based 3D reconstruction or 3D photogrammetry of small-scale objects including insects and biological specimens is challenging due to the use of high magnification lens with inherent limited depth of field, and the object's fine…
In this paper, we tackle the problem of video alignment, the process of matching the frames of a pair of videos containing similar actions. The main challenge in video alignment is that accurate correspondence should be established despite…
A video autoencoder is proposed for learning disentan- gled representations of 3D structure and camera pose from videos in a self-supervised manner. Relying on temporal continuity in videos, our work assumes that the 3D scene structure in…
Existing volumetric neural rendering techniques, such as Neural Radiance Fields (NeRF), face limitations in synthesizing high-quality novel views when the camera poses of input images are imperfect. To address this issue, we propose a novel…
The motion measurement of point targets constitutes a fundamental problem in photogrammetry, with extensive applications across various engineering domains. Reconstructing a point's 3D motion just from the images captured by only a…