61 citations · 129 across the 7 of their papers we have counts for
10 papers
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
Francis Engelmann, Ayca Takmaz, Jonas Schult +25
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this wo…
ControlRoom3D: Room Generation using Semantic Proxy Rooms
Jonas Schult, Sam Tsai, Lukas Höllein +11
Manually creating 3D environments for AR/VR applications is a complex process requiring expert knowledge in 3D modeling software. Pioneering works facilitate this process by genera…
Mask4Former: Mask Transformer for 4D Panoptic Segmentation
Kadir Yilmaz, Jonas Schult, Alexey Nekrasov +1
Accurately perceiving and tracking instances over time is essential for the decision-making processes of autonomous agents interacting safely in dynamic environments. With this int…
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
Yuanwen Yue, Sabarinath Mahadevan, Jonas Schult +4
During interactive segmentation, a model and a user work together to delineate objects of interest in a 3D point cloud. In an iterative process, the model assigns each data point t…
3D Segmentation of Humans in Point Clouds with Synthetic Data
Ayça Takmaz, Jonas Schult, Irem Kaftan +5
Segmenting humans in 3D indoor scenes has become increasingly important with the rise of human-centered robotics and AR/VR applications. To this end, we propose the task of joint 3…
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
Jonas Schult, Francis Engelmann, Alexander Hermans +3
Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques. Building on…
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
Alexey Nekrasov, Jonas Schult, Or Litany +2
We present Mix3D, a data augmentation technique for segmenting large-scale 3D scenes. Since scene context helps reasoning about object semantics, current works focus on models with…
DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
Jonas Schult, Francis Engelmann, Theodora Kontogianni +1
We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical convolutional networks over 3D geometric data that combines two types of convolutions. The first type, geodesic…
3D-BEVIS: Bird's-Eye-View Instance Segmentation
Cathrin Elich, Francis Engelmann, Theodora Kontogianni +1
Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of obj…
Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
Francis Engelmann, Theodora Kontogianni, Jonas Schult +1
In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds. Compared to previous work, we introduce…