Related papers: Learning to Estimate Indoor Lighting from 3D Objec…

Light field applications, especially light field rendering and depth estimation, developed rapidly in recent years. While state-of-the-art light field rendering methods handle semi-transparent and reflective objects well, depth estimation…

Low light images captured in a non-uniform illumination environment usually are degraded with the scene depth and the corresponding environment lights. This degradation results in severe object information loss in the degraded image…

This research is mainly focused on the assessment of machine learning algorithms in the prediction of daylight and visual comfort metrics in the early design stages. A dataset was primarily developed from 2880 simulations derived from…

Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for predicting sets that properly respects the structure of sets…

Reliable and accurate lane detection has been a long-standing problem in the field of autonomous driving. In recent years, many approaches have been developed that use images (or videos) as input and reason in image space. In this paper we…

Accurate depth estimation from images is a fundamental task in many applications including scene understanding and reconstruction. Existing solutions for depth estimation often produce blurry approximations of low resolution. This paper…

Machine learning has been widely applied to clearly defined problems of astronomy and astrophysics. However, deep learning and its conceptual differences to classical machine learning have been largely overlooked in these fields. The broad…

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

Custom and natural lighting conditions can be emulated in images of the scene during post-editing. Extraordinary capabilities of the deep learning framework can be utilized for such purpose. Deep image relighting allows automatic photo…

Object detection in natural scenes can be a challenging task. In many real-life situations, the visible spectrum is not suitable for traditional computer vision tasks. Moving outside the visible spectrum range, such as the thermal spectrum…

LiDAR-based 3D object detection is essential for autonomous driving systems. However, LiDAR point clouds may appear to have sparsity, uneven distribution, and incomplete structures, significantly limiting the detection performance. In road…

We introduce a novel method for robust and accurate 3D object pose estimation from a single color image under large occlusions. Following recent approaches, we first predict the 2D projections of 3D points related to the target object and…

We introduce a scalable approach for object pose estimation trained on simulated RGB views of multiple 3D models together. We learn an encoding of object views that does not only describe an implicit orientation of all objects seen during…

In this work, we study different approaches to self-supervised pretraining of object detection models. We first design a general framework to learn a spatially consistent dense representation from an image, by randomly sampling and…

Light field imaging is a rich way of representing the 3D world around us. However, due to limited sensor resolution capturing light field data inherently poses spatio-angular resolution trade-off. In this paper, we propose a deep learning…

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a…

We present the self-encoder, a neural network trained to guess the identity of each data sample. Despite its simplicity, it learns a very useful representation of data, in a self-supervised way. Specifically, the self-encoder learns to…

We present a machine learning algorithm that takes as input a 2D RGB image and synthesizes a 4D RGBD light field (color and depth of the scene in each ray direction). For training, we introduce the largest public light field dataset,…

Capturing and labeling camera images in the real world is an expensive task, whereas synthesizing labeled images in a simulation environment is easy for collecting large-scale image data. However, learning from only synthetic images may not…