109 citations · 125 across the 7 of their papers we have counts for
9 papers · 1 filter
Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model
Yuming Du, Robin Kips, Albert Pumarola +3
With the recent surge in popularity of AR/VR applications, realistic and accurate control of 3D full-body avatars has become a highly demanded feature. A particular challenge is th…
A Simple and Powerful Global Optimization for Unsupervised Video Object Segmentation
Georgy Ponimatkin, Nermin Samet, Yang Xiao +3
We propose a simple, yet powerful approach for unsupervised object segmentation in videos. We introduce an objective function whose minimum represents the mask of the main salient…
PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking
Van Nguyen Nguyen, Yuming Du, Yang Xiao +2
Estimating the relative pose of a new object without prior knowledge is a hard problem, while it is an ability very much needed in robotics and Augmented Reality. We present a meth…
UVO Challenge on Video-based Open-World Segmentation 2021: 1st Place Solution
Yuming Du, Wen Guo, Yang Xiao +1
In this report, we introduce our (pretty straightforard) two-step "detect-then-match" video instance segmentation method. The first step performs instance segmentation for each fra…
1st Place Solution for the UVO Challenge on Image-based Open-World Segmentation 2021
Yuming Du, Wen Guo, Yang Xiao +1
We describe our two-stage instance segmentation framework we use to compete in the challenge. The first stage of our framework consists of an object detector, which generates objec…
PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learning
Yang Xiao, Yuming Du, Renaud Marlet
Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without C…