activity
20172024
most citedRobust Dense Mapping for Large-Scale Dynamic Environments

147 citations · 351 across the 23 of their papers we have counts for

collaborators
Showing 2018Show all

7 papers · 1 filter

cs.CV2018

Taking a Deeper Look at the Inverse Compositional Algorithm

Zhaoyang Lv, Frank Dellaert, James M. Rehg +1

In this paper, we provide a modern synthesis of the classic inverse compositional algorithm for dense image alignment. We first discuss the assumptions made by this well-establishe…

cs.CV2018

Occupancy Networks: Learning 3D Reconstruction in Function Space

Lars Mescheder, Michael Oechsle, Michael Niemeyer +2

With the advent of deep neural networks, learning-based approaches for 3D reconstruction have gained popularity. However, unlike for images, in 3D there is no canonical representat…

cs.RO2018

Real-Time Dense Mapping for Self-driving Vehicles using Fisheye Cameras

Zhaopeng Cui, Lionel Heng, Ye Chuan Yeo +3

We present a real-time dense geometric mapping algorithm for large-scale environments. Unlike existing methods which use pinhole cameras, our implementation is based on fisheye cam…

cs.RO2018

Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System

Lionel Heng, Benjamin Choi, Zhaopeng Cui +10

Project AutoVision aims to develop localization and 3D scene perception capabilities for a self-driving vehicle. Such capabilities will enable autonomous navigation in urban and ru…

cs.CV2018

Geometric Image Synthesis

Hassan Abu Alhaija, Siva Karthik Mustikovela, Andreas Geiger +1

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for tr…

cs.CV2018

PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds

Aseem Behl, Despoina Paschalidou, Simon Donné +1

Despite significant progress in image-based 3D scene flow estimation, the performance of such approaches has not yet reached the fidelity required by many applications. Simultaneou…