activity
20162023
most cited3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin

47 citations · 90 across the 12 of their papers we have counts for

collaborators
Showing cs.CVShow all

31 papers · 1 filter

cs.CV20233 cited

GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer

Zheng Qin, Hao Yu, Changjian Wang +5

We study the problem of extracting accurate correspondences for point cloud registration. Recent keypoint-free methods have shown great potential through bypassing the detection of…

cs.CV2023

On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks

HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai +10

Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data. The respectively used principle of measuring distances provides advantages and drawbacks…

cs.CV2022

What can we learn about a generated image corrupting its latent representation?

Agnieszka Tomczak, Aarushi Gupta, Slobodan Ilic +2

Generative adversarial networks (GANs) offer an effective solution to the image-to-image translation problem, thereby allowing for new possibilities in medical imaging. They can tr…

cs.CV20225 cited

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

Hao Yu, Ji Hou, Zheng Qin +5

Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-varian…

cs.CV20223 cited

Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression

HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai +9

Depth estimation is a core task in 3D computer vision. Recent methods investigate the task of monocular depth trained with various depth sensor modalities. Every sensor has its adv…

cs.CV20222 cited

OSOP: A Multi-Stage One Shot Object Pose Estimation Framework

Ivan Shugurov, Fu Li, Benjamin Busam +1

We present a novel one-shot method for object detection and 6 DoF pose estimation, that does not require training on target objects. At test time, it takes as input a target image…