Picture for Caroline Pantofaru

Caroline Pantofaru

Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

May 09, 2022
Abhijit Kundu, Kyle Genova, Xiaoqi Yin, Alireza Fathi, Caroline Pantofaru, Leonidas Guibas, Andrea Tagliasacchi, Frank Dellaert, Thomas Funkhouser

Figure 1 for Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Figure 2 for Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Figure 3 for Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

Figure 4 for Panoptic Neural Fields: A Semantic Object-Aware Neural Scene Representation

* CVPR 2022 paper. See project page at https://abhijitkundu.info/projects/pnf

Access Paper or Ask Questions

FILM: Frame Interpolation for Large Motion

Feb 12, 2022
Fitsum Reda, Janne Kontkanen, Eric Tabellion, Deqing Sun, Caroline Pantofaru, Brian Curless

Figure 1 for FILM: Frame Interpolation for Large Motion

Figure 2 for FILM: Frame Interpolation for Large Motion

Figure 3 for FILM: Frame Interpolation for Large Motion

Figure 4 for FILM: Frame Interpolation for Large Motion

* Project page: https://film-net.github.io. Code link: https://github.com/google-research/frame-interpolation. YouTube link: https://www.youtube.com/watch?v=OAD-BieIjH4

Access Paper or Ask Questions

Learning 3D Semantic Segmentation with only 2D Image Supervision

Oct 21, 2021
Kyle Genova, Xiaoqi Yin, Abhijit Kundu, Caroline Pantofaru, Forrester Cole, Avneesh Sud, Brian Brewington, Brian Shucker, Thomas Funkhouser

Figure 1 for Learning 3D Semantic Segmentation with only 2D Image Supervision

Figure 2 for Learning 3D Semantic Segmentation with only 2D Image Supervision

Figure 3 for Learning 3D Semantic Segmentation with only 2D Image Supervision

Figure 4 for Learning 3D Semantic Segmentation with only 2D Image Supervision

* Accepted to 3DV 2021 (Oral)

Access Paper or Ask Questions

Pillar-based Object Detection for Autonomous Driving

Jul 26, 2020
Yue Wang, Alireza Fathi, Abhijit Kundu, David Ross, Caroline Pantofaru, Thomas Funkhouser, Justin Solomon

Figure 1 for Pillar-based Object Detection for Autonomous Driving

Figure 2 for Pillar-based Object Detection for Autonomous Driving

Figure 3 for Pillar-based Object Detection for Autonomous Driving

Figure 4 for Pillar-based Object Detection for Autonomous Driving

* Accepted to ECCV2020

Access Paper or Ask Questions

Virtual Multi-view Fusion for 3D Semantic Segmentation

Jul 26, 2020
Abhijit Kundu, Xiaoqi Yin, Alireza Fathi, David Ross, Brian Brewington, Thomas Funkhouser, Caroline Pantofaru

Figure 1 for Virtual Multi-view Fusion for 3D Semantic Segmentation

Figure 2 for Virtual Multi-view Fusion for 3D Semantic Segmentation

Figure 3 for Virtual Multi-view Fusion for 3D Semantic Segmentation

Figure 4 for Virtual Multi-view Fusion for 3D Semantic Segmentation

* To appear in ECCV 2020

Access Paper or Ask Questions

An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Jul 24, 2020
Rui Huang, Wanyue Zhang, Abhijit Kundu, Caroline Pantofaru, David A Ross, Thomas Funkhouser, Alireza Fathi

Figure 1 for An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Figure 2 for An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Figure 3 for An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

Figure 4 for An LSTM Approach to Temporal 3D Object Detection in LiDAR Point Clouds

* To appear in ECCV 2020

Access Paper or Ask Questions

DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

Apr 07, 2020
Mahyar Najibi, Guangda Lai, Abhijit Kundu, Zhichao Lu, Vivek Rathod, Thomas Funkhouser, Caroline Pantofaru, David Ross, Larry S. Davis, Alireza Fathi

Figure 1 for DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

Figure 2 for DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

Figure 3 for DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

Figure 4 for DOPS: Learning to Detect 3D Objects and Predict their 3D Shapes

* To appear in CVPR 2020

Access Paper or Ask Questions