65 citations · 154 across the 9 of their papers we have counts for
9 papers
Enhancing Visual Domain Adaptation with Source Preparation
Anirudha Ramesh, Anurag Ghosh, Christoph Mertz +1
Robotic Perception in diverse domains such as low-light scenarios, where new modalities like thermal imaging and specialized night-vision sensors are increasingly employed, remains…
Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection
Anurag Ghosh, N. Dinesh Reddy, Christoph Mertz +1
Real-time efficient perception is critical for autonomous navigation and city scale sensing. Orthogonal to architectural improvements, streaming perception approaches have exploite…
Leveraging Structure from Motion to Localize Inaccessible Bus Stops
Indu Panigrahi, Tom Bu, Christoph Mertz
The detection of hazardous conditions near public transit stations is necessary for ensuring the safety and accessibility of public transit. Smart city infrastructures aim to facil…
Multimodal Object Detection via Probabilistic Ensembling
Yi-Ting Chen, Jinghao Shi, Zelin Ye +3
Object detection with multimodal inputs can improve many safety-critical systems such as autonomous vehicles (AVs). Motivated by AVs that operate in both day and night, we study mu…
Depth Completion via Inductive Fusion of Planar LIDAR and Monocular Camera
Chen Fu, Chiyu Dong, Christoph Mertz +1
Modern high-definition LIDAR is expensive for commercial autonomous driving vehicles and small indoor robots. An affordable solution to this problem is fusion of planar LIDAR with…
DeepDA: LSTM-based Deep Data Association Network for Multi-Targets Tracking in Clutter
Huajun Liu, Hui Zhang, Christoph Mertz
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 combina…
Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency
Tejas Khot, Shubham Agrawal, Shubham Tulsiani +3
We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training dat…
Iterative Transformer Network for 3D Point Cloud
Wentao Yuan, David Held, Christoph Mertz +1
3D point cloud is an efficient and flexible representation of 3D structures. Recently, neural networks operating on point clouds have shown superior performance on 3D understanding…
PCN: Point Completion Network
Wentao Yuan, Tejas Khot, David Held +2
Shape completion, the problem of estimating the complete geometry of objects from partial observations, lies at the core of many vision and robotics applications. In this work, we…