Search Results for author: Yiyi Liao

Found 12 papers, 7 papers with code

Fully Differentiable and Interpretable Model for VIO with 4 Trainable Parameters

1 code implementation25 Sep 2021 Zexi Chen, Haozhe Du, Yiyi Liao, Yue Wang, Rong Xiong

In this paper, we propose a fully differentiable, interpretable, and lightweight monocular VIO model that contains only 4 trainable parameters.

Autonomous Driving Pose Estimation

Shape As Points: A Differentiable Poisson Solver

no code implementations7 Jun 2021 Songyou Peng, Chiyu "Max" Jiang, Yiyi Liao, Michael Niemeyer, Marc Pollefeys, Andreas Geiger

However, the implicit nature of neural implicit representations results in slow inference time and requires careful initialization.

3D Reconstruction

SMD-Nets: Stereo Mixture Density Networks

1 code implementation CVPR 2021 Fabio Tosi, Yiyi Liao, Carolin Schmitt, Andreas Geiger

Despite stereo matching accuracy has greatly improved by deep learning in the last few years, recovering sharp boundaries and high-resolution outputs efficiently remains challenging.

Disparity Estimation Stereo Matching

KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs

1 code implementation25 Mar 2021 Christian Reiser, Songyou Peng, Yiyi Liao, Andreas Geiger

NeRF synthesizes novel views of a scene with unprecedented quality by fitting a neural radiance field to RGB images.

GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis

1 code implementation NeurIPS 2020 Katja Schwarz, Yiyi Liao, Michael Niemeyer, Andreas Geiger

In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity.

Image Generation Novel View Synthesis +1

Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesis

1 code implementation CVPR 2020 Yiyi Liao, Katja Schwarz, Lars Mescheder, Andreas Geiger

We define the new task of 3D controllable image synthesis and propose an approach for solving it by reasoning both in 3D space and in the 2D image domain.

Image Generation

Deep Marching Cubes: Learning Explicit Surface Representations

1 code implementation CVPR 2018 Yiyi Liao, Simon Donné, Andreas Geiger

Existing learning based solutions to 3D surface prediction cannot be trained end-to-end as they operate on intermediate representations (e. g., TSDF) from which 3D surface meshes must be extracted in a post-processing step (e. g., via the marching cubes algorithm).

On the Integration of Optical Flow and Action Recognition

no code implementations22 Dec 2017 Laura Sevilla-Lara, Yiyi Liao, Fatma Guney, Varun Jampani, Andreas Geiger, Michael J. Black

Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better.

Action Recognition Optical Flow Estimation

Parse Geometry from a Line: Monocular Depth Estimation with Partial Laser Observation

5 code implementations17 Oct 2016 Yiyi Liao, Lichao Huang, Yue Wang, Sarath Kodagoda, Yinan Yu, Yong liu

Many standard robotic platforms are equipped with at least a fixed 2D laser range finder and a monocular camera.

Depth Completion

Understand Scene Categories by Objects: A Semantic Regularized Scene Classifier Using Convolutional Neural Networks

no code implementations22 Sep 2015 Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Yong liu

As scene images have larger diversity than the iconic object images, it is more challenging for deep learning methods to automatically learn features from scene images with less samples.

Classification General Classification +3

Place classification with a graph regularized deep neural network model

no code implementations12 Jun 2015 Yiyi Liao, Sarath Kodagoda, Yue Wang, Lei Shi, Yong liu

Furthermore, results show that the features automatically learned from the raw input range data can achieve competitive results to the features constructed based on statistical and geometrical information.

Classification General Classification

Image Representation Learning Using Graph Regularized Auto-Encoders

no code implementations3 Dec 2013 Yiyi Liao, Yue Wang, Yong liu

We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning.

Image Clustering Representation Learning

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