Alert button
Picture for Nikolaos Gkanatsios

Nikolaos Gkanatsios

Alert button

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations

Feb 16, 2024
Tsung-Wei Ke, Nikolaos Gkanatsios, Katerina Fragkiadaki

Viaarxiv icon

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

Feb 09, 2024
Brian Yang, Huangyuan Su, Nikolaos Gkanatsios, Tsung-Wei Ke, Ayush Jain, Jeff Schneider, Katerina Fragkiadaki

Viaarxiv icon

ODIN: A Single Model for 2D and 3D Perception

Jan 04, 2024
Ayush Jain, Pushkal Katara, Nikolaos Gkanatsios, Adam W. Harley, Gabriel Sarch, Kriti Aggarwal, Vishrav Chaudhary, Katerina Fragkiadaki

Viaarxiv icon

Act3D: Infinite Resolution Action Detection Transformer for Robotic Manipulation

Jun 30, 2023
Theophile Gervet, Zhou Xian, Nikolaos Gkanatsios, Katerina Fragkiadaki

Figure 1 for Act3D: Infinite Resolution Action Detection Transformer for Robotic Manipulation
Figure 2 for Act3D: Infinite Resolution Action Detection Transformer for Robotic Manipulation
Figure 3 for Act3D: Infinite Resolution Action Detection Transformer for Robotic Manipulation
Figure 4 for Act3D: Infinite Resolution Action Detection Transformer for Robotic Manipulation
Viaarxiv icon

Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement

May 06, 2023
Nikolaos Gkanatsios, Ayush Jain, Zhou Xian, Yunchu Zhang, Christopher Atkeson, Katerina Fragkiadaki

Figure 1 for Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
Figure 2 for Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
Figure 3 for Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
Figure 4 for Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangement
Viaarxiv icon

Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement

Apr 27, 2023
Nikolaos Gkanatsios, Ayush Jain, Zhou Xian, Yunchu Zhang, Christopher Atkeson, Katerina Fragkiadaki

Figure 1 for Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement
Figure 2 for Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement
Figure 3 for Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement
Figure 4 for Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement
Viaarxiv icon

Analogy-Forming Transformers for Few-Shot 3D Parsing

Apr 27, 2023
Nikolaos Gkanatsios, Mayank Singh, Zhaoyuan Fang, Shubham Tulsiani, Katerina Fragkiadaki

Figure 1 for Analogy-Forming Transformers for Few-Shot 3D Parsing
Figure 2 for Analogy-Forming Transformers for Few-Shot 3D Parsing
Figure 3 for Analogy-Forming Transformers for Few-Shot 3D Parsing
Figure 4 for Analogy-Forming Transformers for Few-Shot 3D Parsing
Viaarxiv icon

Looking Outside the Box to Ground Language in 3D Scenes

Dec 19, 2021
Ayush Jain, Nikolaos Gkanatsios, Ishita Mediratta, Katerina Fragkiadaki

Figure 1 for Looking Outside the Box to Ground Language in 3D Scenes
Figure 2 for Looking Outside the Box to Ground Language in 3D Scenes
Figure 3 for Looking Outside the Box to Ground Language in 3D Scenes
Figure 4 for Looking Outside the Box to Ground Language in 3D Scenes
Viaarxiv icon

Orientation Attentive Robot Grasp Synthesis

Jun 09, 2020
Nikolaos Gkanatsios, Georgia Chalvatzaki, Petros Maragos, Jan Peters

Figure 1 for Orientation Attentive Robot Grasp Synthesis
Figure 2 for Orientation Attentive Robot Grasp Synthesis
Figure 3 for Orientation Attentive Robot Grasp Synthesis
Figure 4 for Orientation Attentive Robot Grasp Synthesis
Viaarxiv icon

Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection

Feb 15, 2019
Nikolaos Gkanatsios, Vassilis Pitsikalis, Petros Koutras, Athanasia Zlatintsi, Petros Maragos

Figure 1 for Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
Figure 2 for Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
Figure 3 for Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
Figure 4 for Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection
Viaarxiv icon