相关论文: Real-Time ESFP: Estimating, Smoothing, Filtering, …
Generating non-existing frames from a consecutive video sequence has been an interesting and challenging problem in the video processing field. Typical kernel-based interpolation methods predict pixels with a single convolution process that…
This paper discusses video motion capture, namely, 3D reconstruction of human motion from multi-camera images. After the Part Confidence Maps are computed from each camera image, the proposed spatiotemporal filter is applied to deliver the…
Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days…
Heartbeat rhythm and heart rate (HR) are important physiological parameters of the human body. This study presents an efficient multi-hierarchical spatio-temporal convolutional network that can quickly estimate remote physiological (rPPG)…
The recovery of 3D human mesh from monocular images has significantly been developed in recent years. However, existing models usually ignore spatial and temporal information, which might lead to mesh and image misalignment and temporal…
Deploying a humanoid robot to manipulate a new object has traditionally required one to two days of effort: data collection, manual annotation, 3D model acquisition, and model training. This paper presents an end-to-end rapid deployment…
The task of action detection aims at deducing both the action category and localization of the start and end moment for each action instance in a long, untrimmed video. While vision Transformers have driven the recent advances in video…
Parametric human body models are foundational to human reconstruction, animation, and simulation, yet they remain mutually incompatible: SMPL, SMPL-X, MHR, Anny, and related models each diverge in mesh topology, skeletal structure, shape…
Vital sign measurement using cameras presents opportunities for comfortable, ubiquitous health monitoring. Remote photoplethysmography (rPPG), a foundational technology, enables cardiac measurement through minute changes in light reflected…
A new type of ensemble filter is proposed, which combines an ensemble Kalman filter (EnKF) with the ideas of morphing and registration from image processing. This results in filters suitable for nonlinear problems whose solutions exhibit…
Smartphone cameras have gained immense popularity with the adoption of high-resolution and high-dynamic range imaging. As a result, high-performance camera Image Signal Processors (ISPs) are crucial in generating high-quality images for the…
While egocentric cameras like GoPro are gaining popularity, the videos they capture are long, boring, and difficult to watch from start to end. Fast forwarding (i.e. frame sampling) is a natural choice for faster video browsing. However,…
We present a novel method for monocular hand shape and pose estimation at unprecedented runtime performance of 100fps and at state-of-the-art accuracy. This is enabled by a new learning based architecture designed such that it can make use…
Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models that deliver high accuracy while operating in real-time continues to be a major challenge in…
In a continued quest to monitor subsecond surface dynamics on the atomic scale and to improve imaging resolution, a FAST module to accelerate existing scanning probe microscopy setups was previously presented. Hereby, the speedup is enabled…
We propose CrossHuman, a novel method that learns cross-guidance from parametric human model and multi-frame RGB images to achieve high-quality 3D human reconstruction. To recover geometry details and texture even in invisible regions, we…
Non-contact remote photoplethysmography (rPPG) technology enables heart rate measurement from facial videos. However, existing network models still face challenges in accu racy, robustness, and generalization capability under complex…
We propose a real-time 3D human pose estimation and motion analysis method termed RePose for rehabilitation training. It is capable of real-time monitoring and evaluation of patients'motion during rehabilitation, providing immediate…
An end-to-end hardware-software pipeline is introduced to automatize ergonomics assessment in industrial workplaces. The proposed modular solution can interoperate with commercial systems throughout the ergonomics assessment phases involved…
Complex manipulation tasks require careful integration of symbolic reasoning and motion planning. This problem, commonly referred to as Task and Motion Planning (TAMP), is even more challenging if the workspace is non-static, e.g. due to…