Search Results for author:
Found 24 papers, 7 papers with code
Ref-DVGO: Reflection-Aware Direct Voxel Grid Optimization for an Improved Quality-Efficiency Trade-Off in Reflective Scene Reconstruction
To this end, we investigate an implicit-explicit approach based on conventional volume rendering to enhance the reconstruction quality and accelerate the training and rendering processes.
Locking On: Leveraging Dynamic Vehicle-Imposed Motion Constraints to Improve Visual Localization
In this research, we propose a middle ground, demonstrated in the context of autonomous vehicles, using dynamic vehicles to provide limited pose constraint information in a 6-DoF frame-by-frame PnP-RANSAC localization pipeline.
DisPlacing Objects: Improving Dynamic Vehicle Detection via Visual Place Recognition under Adverse Conditions
In this work we investigate whether a prior map can be leveraged to aid in the detection of dynamic objects in a scene without the need for a 3D map or pixel-level map-query correspondences.
FQDet: Fast-converging Query-based Detector
Recently, two-stage Deformable DETR introduced the query-based two-stage head, a new type of two-stage head different from the region-based two-stage heads of classical detectors as Faster R-CNN.
Category-Level Pose Retrieval with Contrastive Features Learnt with Occlusion Augmentation
In both cases, the idea is to directly predict the pose of an object.
Improving Worst Case Visual Localization Coverage via Place-specific Sub-selection in Multi-camera Systems
6-DoF visual localization systems utilize principled approaches rooted in 3D geometry to perform accurate camera pose estimation of images to a map.
Real-time Full-stack Traffic Scene Perception for Autonomous Driving with Roadside Cameras
We propose a novel and pragmatic framework for traffic scene perception with roadside cameras.
Designing MacPherson Suspension Architectures using Bayesian Optimization
We show that the proposed approach is general, scalable, and efficient, and that the novel convergence criteria can be implemented straightforwardly based on existing concepts and subroutines in popular Bayesian optimization software packages.
Propagating State Uncertainty Through Trajectory Forecasting
As a result, perceptual uncertainties are not propagated through forecasting and predictions are frequently overconfident.
Full-Velocity Radar Returns by Radar-Camera Fusion
A distinctive feature of Doppler radar is the measurement of velocity in the radial direction for radar points.
Radar-Camera Pixel Depth Association for Depth Completion
Here we propose a radar-to-pixel association stage which learns a mapping from radar returns to pixels.
S-BEV: Semantic Birds-Eye View Representation for Weather and Lighting Invariant 3-DoF Localization
We describe a light-weight, weather and lighting invariant, Semantic Bird's Eye View (S-BEV) signature for vision-based vehicle re-localization.
An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigation
Training robots to navigate diverse environments is a challenging problem as it involves the confluence of several different perception tasks such as mapping and localization, followed by optimal path-planning and control.
Sim2Real for Self-Supervised Monocular Depth and Segmentation
Image-based learning methods for autonomous vehicle perception tasks require large quantities of labelled, real data in order to properly train without overfitting, which can often be incredibly costly.
What My Motion tells me about Your Pose: A Self-Supervised Monocular 3D Vehicle Detector
We subsequently demonstrate an optimization-based monocular 3D bounding box detector built on top of the self-supervised vehicle orientation estimator without the requirement of expensive labeled data.
CubifAE-3D: Monocular Camera Space Cubification for Auto-Encoder based 3D Object Detection
We introduce a method for 3D object detection using a single monocular image.
3D Object Detection From Monocular Images
Autonomous Vehicles
+3
Deflating Dataset Bias Using Synthetic Data Augmentation
Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware.
Deep-Geometric 6 DoF Localization from a Single Image in Topo-metric Maps
We describe a Deep-Geometric Localizer that is able to estimate the full 6 Degree of Freedom (DoF) global pose of the camera from a single image in a previously mapped environment.
Trajectron++: Dynamically-Feasible Trajectory Forecasting With Heterogeneous Data
Reasoning about human motion is an important prerequisite to safe and socially-aware robotic navigation.
Ranked #2 on
Trajectory Prediction
on ETH
Hierarchical Sequence to Sequence Voice Conversion with Limited Data
Our seq2seq architecture makes use of a hierarchical encoder to summarize input audio frames.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
GEN-SLAM: Generative Modeling for Monocular Simultaneous Localization and Mapping
We present a Deep Learning based system for the twin tasks of localization and obstacle avoidance essential to any mobile robot.
Who's that Actor? Automatic Labelling of Actors in TV series starting from IMDB Images
In this work, we aim at automatically labeling actors in a TV series.
Expert Gate: Lifelong Learning with a Network of Experts
Further, the autoencoders inherently capture the relatedness of one task to another, based on which the most relevant prior model to be used for training a new expert, with finetuning or learning without-forgetting, can be selected.
Cross-modal Supervision for Learning Active Speaker Detection in Video
We further improve a generic model for active speaker detection by learning person specific models.
