Search Results - "Engelmann, Francis"

3D-MPA: Multi-Proposal Aggregation for 3D Semantic Instance Segmentation by Engelmann, Francis, Bokeloh, Martin, Fathi, Alireza, Leibe, Bastian, NieBner, Matthias

“…We present 3D-MPA, a method for instance segmentation on 3D point clouds. Given an input point cloud, we propose an object-centric approach where each point…”
Get full text

DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes by Schult, Jonas, Engelmann, Francis, Kontogianni, Theodora, Leibe, Bastian

“…We propose DualConvMesh-Nets (DCM-Net) a family of deep hierarchical convolutional networks over 3D geometric data that combines two types of convolutions. The…”
Get full text

From Points to Multi-Object 3D Reconstruction by Engelmann, Francis, Rematas, Konstantinos, Leibe, Bastian, Ferrari, Vittorio

“…We propose a method to detect and reconstruct multiple 3D objects from a single RGB image. The key idea is to optimize for detection, alignment and shape…”
Get full text

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries by Yue, Yuanwen, Kontogianni, Theodora, Schindler, Konrad, Engelmann, Francis

“…We address 2D floorplan reconstruction from 3D scans. Existing approaches typically employ heuristically designed multi-stage pipelines. Instead, we formulate…”
Get full text

Keyframe-based visual-inertial online SLAM with relocalization by Kasyanov, Anton, Engelmann, Francis, Stuckler, Jorg, Leibe, Bastian

“…Complementing images with inertial measurements has become one of the most popular approaches to achieve highly accurate and robust real-time camera pose…”
Get full text

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds by Engelmann, Francis, Kontogianni, Theodora, Hermans, Alexander, Leibe, Bastian

“…Deep learning approaches have made tremendous progress in the field of semantic segmentation over the past few years. However, most current approaches operate…”
Get full text

Mix3D: Out-of-Context Data Augmentation for 3D Scenes by Nekrasov, Alexey, Schult, Jonas, Litany, Or, Leibe, Bastian, Engelmann, Francis

“…We present Mix3D, a data augmentation technique for segmenting large-scale 3D scenes. Since scene context helps reasoning about object semantics, current works…”
Get full text

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds by Engelmann, Francis, Kontogianni, Theodora, Leibe, Bastian

“…In this work, we propose Dilated Point Convolutions (DPC). In a thorough ablation study, we show that the receptive field size is directly related to the…”
Get full text

Mask3D: Mask Transformer for 3D Semantic Instance Segmentation by Schult, Jonas, Engelmann, Francis, Hermans, Alexander, Litany, Or, Tang, Siyu, Leibe, Bastian

“…Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering…”
Get full text

ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding by Ji, Guangda, Weder, Silvan, Engelmann, Francis, Pollefeys, Marc, Blum, Hermann

“…The performance of neural networks scales with both their size and the amount of data they have been trained on. This is shown in both language and image…”
Get full text

OpenDAS: Open-Vocabulary Domain Adaptation for 2D and 3D Segmentation by Yilmaz, Gonca, Peng, Songyou, Pollefeys, Marc, Engelmann, Francis, Blum, Hermann

“…Recently, Vision-Language Models (VLMs) have advanced segmentation techniques by shifting from the traditional segmentation of a closed-set of predefined…”
Get full text

LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories by Weder, Silvan, Blum, Hermann, Engelmann, Francis, Pollefeys, Marc

“…Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D…”
Get full text

LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories by Weder, Silvan, Blum, Hermann, Engelmann, Francis, Pollefeys, Marc

“…Semantic annotations are indispensable to train or evaluate perception models, yet very costly to acquire. This work introduces a fully automated 2D/3D…”
Get full text

SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction by Engelmann, Francis, Stuckler, Jorg, Leibe, Bastian

“…Inferring the pose and shape of vehicles in 3D from a movable platform still remains a challenging task due to the projective sensing principle of cameras,…”
Get full text

Search3D: Hierarchical Open-Vocabulary 3D Segmentation by Takmaz, Ayca, Delitzas, Alexandros, Sumner, Robert W, Engelmann, Francis, Wald, Johanna, Tombari, Federico

“…Open-vocabulary 3D segmentation enables the exploration of 3D spaces using free-form text descriptions. Existing methods for open-vocabulary 3D instance…”
Get full text

P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising by Vogel, Mathias, Tateno, Keisuke, Pollefeys, Marc, Tombari, Federico, Rakotosaona, Marie-Julie, Engelmann, Francis

“…In this work, we tackle the task of point cloud denoising through a novel framework that adapts Diffusion Schr\"odinger bridges to points clouds. Unlike…”
Get full text

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries by Yue, Yuanwen, Kontogianni, Theodora, Schindler, Konrad, Engelmann, Francis

“…We address 2D floorplan reconstruction from 3D scans. Existing approaches typically employ heuristically designed multi-stage pipelines. Instead, we formulate…”
Get full text

Improving 2D Feature Representations by 3D-Aware Fine-Tuning by Yue, Yuanwen, Das, Anurag, Engelmann, Francis, Tang, Siyu, Lenssen, Jan Eric

“…Current visual foundation models are trained purely on unstructured 2D data, limiting their understanding of 3D structure of objects and scenes. In this work,…”
Get full text

SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes by Delitzas, Alexandros, Takmaz, Ayca, Tombari, Federico, Sumner, Robert, Pollefeys, Marc, Engelmann, Francis

“…Existing 3D scene understanding methods are heavily focused on 3D semantic and instance segmentation. However, identifying objects and their parts only…”
Get full text

ICGNet: A Unified Approach for Instance-Centric Grasping by Zurbrugg, Rene, Liu, Yifan, Engelmann, Francis, Kumar, Suryansh, Hutter, Marco, Patil, Vaishakh, Yu, Fisher

“…Accurate grasping is the key to several robotic tasks including assembly and household robotics. Executing a successful grasp in a cluttered environment…”
Get full text