Search Results for author:
Found 37 papers, 10 papers with code
Text in the Dark: Extremely Low-Light Text Image Enhancement
We also labeled texts in the extremely low-light See In the Dark (SID) and ordinary LOw-Light (LOL) datasets to allow for objective assessment of extremely low-light image enhancement through scene text tasks.
Two Tales of Single-Phase Contrastive Hebbian Learning
The search for ``biologically plausible'' learning algorithms has converged on the idea of representing gradients as activity differences.
Learned Trajectory Embedding for Subspace Clustering
Clustering multiple motions from observed point trajectories is a fundamental task in understanding dynamic scenes.
Fully Variational Noise-Contrastive Estimation
By using the underlying theory of proper scoring rules, we design a family of noise-contrastive estimation (NCE) methods that are tractable for latent variable models.
Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons
Activity difference based learning algorithms-such as contrastive Hebbian learning and equilibrium propagation-have been proposed as biologically plausible alternatives to error back-propagation.
GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection
Its performance is demonstrated on the large-scale ImageNet-1k OOD detection benchmark.
Extremely Low-light Image Enhancement with Scene Text Restoration
Deep learning-based methods have made impressive progress in enhancing extremely low-light images - the image quality of the reconstructed images has generally improved.
AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networks
We propose a new algorithm for training deep neural networks (DNNs) with binary weights.
BabelCalib: A Universal Approach to Calibrating Central Cameras
A lot of the difficulties of general camera calibration lie in the use of a forward projection model.
Bilevel Programs Meet Deep Learning: A Unifying View on Inference Learning Methods
In this work we unify a number of inference learning methods, that are proposed in the literature as alternative training algorithms to the ones based on regular error back-propagation.
Escaping Poor Local Minima in Large Scale Robust Estimation
Robust parameter estimation is a crucial task in several 3D computer vision pipelines such as Structure from Motion (SfM).
Progressive Batching for Efficient Non-linear Least Squares
Non-linear least squares solvers are used across a broad range of offline and real-time model fitting problems.
Lifted Regression/Reconstruction Networks
In this work we propose lifted regression/reconstruction networks (LRRNs), which combine lifted neural networks with a guaranteed Lipschitz continuity property for the output layer.
A Graduated Filter Method for Large Scale Robust Estimation
Due to the highly non-convex nature of large-scale robust parameter estimation, avoiding poor local minima is challenging in real-world applications where input data is contaminated by a large or unknown fraction of outliers.
Truncated Inference for Latent Variable Optimization Problems: Application to Robust Estimation and Learning
Optimization problems with an auxiliary latent variable structure in addition to the main model parameters occur frequently in computer vision and machine learning.
SG-VAE: Scene Grammar Variational Autoencoder to generate new indoor scenes
Our method learns the co-occurrences, and appearance parameters such as shape and pose, for different objects categories through a grammar-based auto-encoder, resulting in a compact and accurate representation for scene layouts.
Pareto Meets Huber: Efficiently Avoiding Poor Minima in Robust Estimation
Robust cost optimization is the task of fitting parameters to data points containing outliers.
Monocular 3D Object Detection and Box Fitting Trained End-to-End Using Intersection-over-Union Loss
We show how modeling heteroscedastic uncertainty improves performance upon our baseline, and furthermore, how back-propagation can be done through the optimizer in order to train the pipeline end-to-end for additional accuracy.
Seeing Behind Things: Extending Semantic Segmentation to Occluded Regions
In our experiments we demonstrate that a CNN trained by minimizing the proposed loss is able to predict semantic categories for visible and occluded object parts without requiring to increase the network size (compared to a standard segmentation task).
Contrastive Learning for Lifted Networks
In this work we address supervised learning of neural networks via lifted network formulations.
Descending, lifting or smoothing: Secrets of robust cost optimization
Robust cost optimization is the challenging task of fitting a large number of parameters to data points containing a significant and unknown fraction of outliers.
Weakly supervised learning of indoor geometry by dual warping
A major element of depth perception and 3D understanding is the ability to predict the 3D layout of a scene and its contained objects for a novel pose.
pOSE: Pseudo Object Space Error for Initialization-Free Bundle Adjustment
Bundle adjustment is a nonlinear refinement method for camera poses and 3D structure requiring sufficiently good initialization.
ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time
Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets.
Ranked #87 on
Semantic Segmentation
on Cityscapes val
Maximum Consensus Parameter Estimation by Reweighted $\ell_1$ Methods
Robust parameter estimation in computer vision is frequently accomplished by solving the maximum consensus (MaxCon) problem.
SPP-Net: Deep Absolute Pose Regression with Synthetic Views
In this work we design a deep neural network architecture based on sparse feature descriptors to estimate the absolute pose of an image.
Minimal Solvers for Monocular Rolling Shutter Compensation under Ackermann Motion
Modern automotive vehicles are often equipped with a budget commercial rolling shutter camera.
Rolling Shutter Correction in Manhattan World
A vast majority of consumer cameras operate the rolling shutter mechanism, which often produces distorted images due to inter-row delay while capturing an image.
Revisiting the Variable Projection Method for Separable Nonlinear Least Squares Problems
Variable Projection (VarPro) is a framework to solve optimization problems efficiently by optimally eliminating a subset of the unknowns.
The Likelihood-Ratio Test and Efficient Robust Estimation
Robust estimation of model parameters in the presence of outliers is a key problem in computer vision.
A Dynamic Programming Approach for Fast and Robust Object Pose Recognition From Range Images
Joint object recognition and pose estimation solely from range images is an important task e. g. in robotics applications and in automated manufacturing environments.
Multi-modal Image Registration for Correlative Microscopy
In this report, I introduce two methods of image registration for correlative microscopy.
A Principled Approach for Coarse-to-Fine MAP Inference
In this work we reconsider labeling problems with (virtually) continuous state spaces, which are of relevance in low level computer vision.
Compact Relaxations for MAP Inference in Pairwise MRFs with Piecewise Linear Priors
The number of unknowns is O(LK) per pairwise clique in terms of the state space size $L$ and the number of linear segments K. This compares to an O(L^2) size complexity of the standard LP relaxation if the piecewise linear structure is ignored.
Joint 3D Scene Reconstruction and Class Segmentation
Image segmentations provide geometric cues about which surface orientations are more likely to appear at a certain location in space whereas a dense 3D reconstruction yields a suitable regularization for the segmentation problem by lifting the labeling from 2D images to 3D space.
Scene Coordinate Regression Forests for Camera Relocalization in RGB-D Images
We address the problem of inferring the pose of an RGB-D camera relative to a known 3D scene, given only a single acquired image.
Gated Softmax Classification
We describe a log-bilinear" model that computes class probabilities by combining an input vector multiplicatively with a vector of binary latent variables.
