Search Results for author:
Found 12 papers, 4 papers with code
Semantic Motion Segmentation Using Dense CRF Formulation
We pro- pose an algorithm that jointly infers the semantic class and motion labels of an object.
Dynamic Body VSLAM with Semantic Constraints
We show results on the challenging KITTI urban dataset for accuracy of motion segmentation and reconstruction of the trajectory and shape of moving objects relative to ground truth.
Incremental Real-Time Multibody VSLAM with Trajectory Optimization Using Stereo Camera
Real time outdoor navigation in highly dynamic environments is an crucial problem.
Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks
This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocular semantic motion segmentation.
CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles
In this work, we develop a framework to fuse both the single-view feature tracks and multi-view detected part locations to significantly improve the detection, localization and reconstruction of moving vehicles, even in the presence of strong occlusions.
Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks
Central to this work is a trifocal tensor loss that provides indirect self-supervision for occluded keypoint locations that are visible in other views of the object.
Ranked #1 on
Vehicle Pose Estimation
on CarFusion
3D Car Instance Understanding
3D Object Reconstruction From A Single Image
+2
TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking
At the core of our approach is a novel spatio-temporal formulation that operates in a common voxelized feature space aggregated from single- or multiple camera views.
Ranked #1 on
3D Human Pose Estimation
on Panoptic
(using extra training data)
Traffic4D: Single View Reconstruction of Repetitious Activity Using Longitudinal Self-Supervision
Reconstructing 4D vehicular activity (3D space and time) from cameras is useful for autonomous vehicles, commuters and local authorities to plan for smarter and safer cities.
WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery
Labeled real data of occlusions is scarce (even in large datasets) and synthetic data leaves a domain gap, making it hard to explicitly model and learn occlusions.
Ranked #1 on
Amodal Instance Segmentation
on WALT
Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection
For autonomous navigation, using the same detector and scale, our approach improves detection rate by +4. 1 $AP_{S}$ or +39% and in real-time performance by +5. 3 $sAP_{S}$ or +63% for small objects over state-of-the-art (SOTA).
WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion
Current methods for 2D and 3D object understanding struggle with severe occlusions in busy urban environments, partly due to the lack of large-scale labeled ground-truth annotations for learning occlusion.
