Search Results for author:
Found 11 papers, 6 papers with code
ROADWork Dataset: Learning to Recognize, Observe, Analyze and Drive Through Work Zones
Perceiving and navigating through work zones is challenging and under-explored, even with major strides in self-driving research.
Enhancing Visual Domain Adaptation with Source Preparation
Our Almost Unsupervised Domain Adaptation (AUDA) framework, a label-efficient semi-supervised approach for robotic scenarios -- employs Source Preparation (SP), Unsupervised Domain Adaptation (UDA) and Supervised Alignment (SA) from limited labeled data.
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).
Leveraging Structure from Motion to Localize Inaccessible Bus Stops
Specifically, our method learns the locations of sidewalks in a given scene by applying a segmentation model and SfM to images from bus cameras during clear weather.
Multimodal Object Detection via Probabilistic Ensembling
Object detection with multimodal inputs can improve many safety-critical systems such as autonomous vehicles (AVs).
Ranked #2 on
Object Detection
on InOutDoor
CrackFormer: Transformer Network for Fine-Grained Crack Detection
The CrackFormer is composed of novel attention modules in a SegNet-like encoder-decoder architecture.
Depth Completion via Inductive Fusion of Planar LIDAR and Monocular Camera
This late-fusion block uses the dense context features to guide the depth prediction based on demonstrations by sparse depth features.
DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter
The Long Short-Term Memory (LSTM) neural network based data association algorithm named as DeepDA for multi-target tracking in clutters is proposed to deal with the NP-hard combinatorial optimization problem in this paper.
Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency
We demonstrate our ability to learn MVS without 3D supervision using a real dataset, and show that each component of our proposed robust loss results in a significant improvement.
Iterative Transformer Network for 3D Point Cloud
Recently, neural networks operating on point clouds have shown superior performance on 3D understanding tasks such as shape classification and part segmentation.
PCN: Point Completion Network
Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications.
Ranked #6 on
Point Cloud Completion
on Completion3D
