activity
20152022
most citedGoing Further with Point Pair Features

129 citations · 188 across the 21 of their papers we have counts for

collaborators
Showing cs.CVShow all

48 papers · 1 filter

cs.CV2022

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…

cs.CV20226 cited

Long-Lived Accurate Keypoints in Event Streams

Philippe Chiberre, Etienne Perot, Amos Sironi +1

We present a novel end-to-end approach to keypoint detection and tracking in an event stream that provides better precision and much longer keypoint tracks than previous methods. T…

cs.CV20229 cited

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…

cs.CV20223 cited

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

Van Nguyen Nguyen, Yinlin Hu, Yang Xiao +2

We present a method that can recognize new objects and estimate their 3D pose in RGB images even under partial occlusions. Our method requires neither a training phase on these obj…

cs.CV2021

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…

cs.CV20215 cited

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…