Search Results for author: N. Dinesh Reddy

Found 12 papers, 4 papers with code

WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion

no code implementations27 Mar 2024 Khiem Vuong, N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan

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.

3D Reconstruction Object Reconstruction

Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection

no code implementations CVPR 2023 Anurag Ghosh, N. Dinesh Reddy, Christoph Mertz, Srinivasa G. Narasimhan

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).

Autonomous Navigation object-detection +1

WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery

1 code implementation CVPR 2022 N. Dinesh Reddy, Robert Tamburo, Srinivasa G. Narasimhan

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.

4k Amodal Instance Segmentation +5

Traffic4D: Single View Reconstruction of Repetitious Activity Using Longitudinal Self-Supervision

1 code implementation IEEE Intelligent Vehicles Symposium 2021 Fangyu Li, N. Dinesh Reddy, Xudong Chen and Srinivasa G. Narasimhan

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.

3D Reconstruction Anomaly Detection +1

TesseTrack: End-to-End Learnable Multi-Person Articulated 3D Pose Tracking

no code implementations CVPR 2021 N. Dinesh Reddy, Laurent Guigues, Leonid Pischulini, Jayan Eledath, Srinivasa Narasimhan

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)

2D Pose Estimation 3D Human Pose Tracking +4

Occlusion-Net: 2D/3D Occluded Keypoint Localization Using Graph Networks

1 code implementation CVPR 2019 N. Dinesh Reddy, Minh Vo, Srinivasa G. Narasimhan

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.

3D Car Instance Understanding 3D Object Reconstruction From A Single Image +2

CarFusion: Combining Point Tracking and Part Detection for Dynamic 3D Reconstruction of Vehicles

1 code implementation CVPR 2018 N. Dinesh Reddy, Minh Vo, Srinivasa G. Narasimhan

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.

3D Reconstruction Point Tracking

Joint Semantic and Motion Segmentation for dynamic scenes using Deep Convolutional Networks

no code implementations18 Apr 2017 Nazrul Haque, N. Dinesh Reddy, K. Madhava Krishna

This paper proposes an approach to fuse semantic features and motion clues using CNNs, to address the problem of monocular semantic motion segmentation.

Motion Segmentation Optical Flow Estimation +2

Dynamic Body VSLAM with Semantic Constraints

no code implementations27 Apr 2015 N. Dinesh Reddy, Prateek Singhal, Visesh Chari, K. Madhava Krishna

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.

Autonomous Navigation Motion Segmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.