no code implementations • 22 Aug 2022 • JunYoung Gwak, Silvio Savarese, Jeannette Bohg
In this work, we present Minkowski Tracker, a sparse spatio-temporal R-CNN that jointly solves object detection and tracking.
4 code implementations • ECCV 2020 • JunYoung Gwak, Christopher Choy, Silvio Savarese
3D object detection has been widely studied due to its potential applicability to many promising areas such as robotics and augmented reality.
Ranked #6 on 3D Object Detection on S3DIS
1 code implementation • 19 Feb 2020 • Abhijeet Shenoi, Mihir Patel, JunYoung Gwak, Patrick Goebel, Amir Sadeghian, Hamid Rezatofighi, Roberto Martín-Martín, Silvio Savarese
In this work we present JRMOT, a novel 3D MOT system that integrates information from RGB images and 3D point clouds to achieve real-time, state-of-the-art tracking performance.
Ranked #8 on Multiple Object Tracking on KITTI Tracking test
1 code implementation • 25 Oct 2019 • Roberto Martín-Martín, Mihir Patel, Hamid Rezatofighi, Abhijeet Shenoi, JunYoung Gwak, Eric Frankel, Amir Sadeghian, Silvio Savarese
We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot.
1 code implementation • ICCV 2019 • Iro Armeni, Zhi-Yang He, JunYoung Gwak, Amir R. Zamir, Martin Fischer, Jitendra Malik, Silvio Savarese
Given a 3D mesh and registered panoramic images, we construct a graph that spans the entire building and includes semantics on objects (e. g., class, material, and other attributes), rooms (e. g., scene category, volume, etc.)
7 code implementations • CVPR 2019 • Christopher Choy, JunYoung Gwak, Silvio Savarese
To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space.
Ranked #1 on Robust 3D Semantic Segmentation on WOD-C
4D Spatio Temporal Semantic Segmentation Robust 3D Semantic Segmentation
10 code implementations • CVPR 2019 • Hamid Rezatofighi, Nathan Tsoi, JunYoung Gwak, Amir Sadeghian, Ian Reid, Silvio Savarese
By incorporating this generalized $IoU$ ($GIoU$) as a loss into the state-of-the art object detection frameworks, we show a consistent improvement on their performance using both the standard, $IoU$ based, and new, $GIoU$ based, performance measures on popular object detection benchmarks such as PASCAL VOC and MS COCO.
no code implementations • 20 Oct 2017 • Lyne P. Tchapmi, Christopher B. Choy, Iro Armeni, JunYoung Gwak, Silvio Savarese
Coarse voxel predictions from a 3D Fully Convolutional NN are transferred back to the raw 3D points via trilinear interpolation.
Ranked #13 on Semantic Segmentation on Semantic3D
no code implementations • 11 Aug 2017 • Andrey Kurenkov, Jingwei Ji, Animesh Garg, Viraj Mehta, JunYoung Gwak, Christopher Choy, Silvio Savarese
We evaluate our approach on the ShapeNet dataset and show that - (a) the Free-Form Deformation layer is a powerful new building block for Deep Learning models that manipulate 3D data (b) DeformNet uses this FFD layer combined with shape retrieval for smooth and detail-preserving 3D reconstruction of qualitatively plausible point clouds with respect to a single query image (c) compared to other state-of-the-art 3D reconstruction methods, DeformNet quantitatively matches or outperforms their benchmarks by significant margins.
2 code implementations • 31 May 2017 • JunYoung Gwak, Christopher B. Choy, Animesh Garg, Manmohan Chandraker, Silvio Savarese
Supervised 3D reconstruction has witnessed a significant progress through the use of deep neural networks.
no code implementations • NeurIPS 2016 • Christopher B. Choy, JunYoung Gwak, Silvio Savarese, Manmohan Chandraker
We present a deep learning framework for accurate visual correspondences and demonstrate its effectiveness for both geometric and semantic matching, spanning across rigid motions to intra-class shape or appearance variations.
14 code implementations • 2 Apr 2016 • Christopher B. Choy, Danfei Xu, JunYoung Gwak, Kevin Chen, Silvio Savarese
Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural Network (3D-R2N2).
Ranked #4 on 3D Reconstruction on Data3D−R2N2
no code implementations • CVPR 2015 • Jason Rock, Tanmay Gupta, Justin Thorsen, JunYoung Gwak, Daeyun Shin, Derek Hoiem
Our goal is to recover a complete 3D model from a depth image of an object.