Related papers: Learning to simulate complex scenes
Procedural models are being widely used to synthesize scenes for graphics, gaming, and to create (labeled) synthetic datasets for ML. In order to produce realistic and diverse scenes, a number of parameters governing the procedural models…
Person re-identification (re-ID) has gained more and more attention due to its widespread applications in intelligent video surveillance. Unfortunately, the mainstream deep learning methods still need a large quantity of labeled data to…
Rare and challenging driving scenarios are critical for autonomous vehicle development. Since they are difficult to encounter, simulating or generating them using generative models is a popular approach. Following previous efforts to…
Identifying predictive world models for robots in novel environments from sparse online observations is essential for robot task planning and execution in novel environments. However, existing methods that leverage differentiable…
The primary goal of motion planning is to generate safe and efficient trajectories for vehicles. Traditionally, motion planning models are trained using imitation learning to mimic the behavior of human experts. However, these models often…
Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…
Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…
Semantic segmentation is key in autonomous driving. Using deep visual learning architectures is not trivial in this context, because of the challenges in creating suitable large scale annotated datasets. This issue has been traditionally…
Detecting a diverse range of objects under various driving scenarios is essential for the effectiveness of autonomous driving systems. However, the real-world data collected often lacks the necessary diversity presenting a long-tail…
In this work we investigate the problem of road scene semantic segmentation using Deconvolutional Networks (DNs). Several constraints limit the practical performance of DNs in this context: firstly, the paucity of existing pixel-wise…
Deep learning-based scene text detection can achieve preferable performance, powered with sufficient labeled training data. However, manual labeling is time consuming and laborious. At the extreme, the corresponding annotated data are…
Synthetic data generation is an appealing approach to generate novel traffic scenarios in autonomous driving. However, deep learning perception algorithms trained solely on synthetic data encounter serious performance drops when they are…
Movement is how people interact with and affect their environment. For realistic character animation, it is necessary to synthesize such interactions between virtual characters and their surroundings. Despite recent progress in character…
Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores domain randomization, a simple technique for training models…
The ability for computational agents to reason about the high-level content of real world scene images is important for many applications. Existing attempts at addressing the problem of complex scene understanding lack representational…
In this paper, we present the submission to the 5th Annual Smoky Mountains Computational Sciences Data Challenge, Challenge 3. This is the solution for semantic segmentation problem in both real-world and synthetic images from a vehicle s…
Unsupervised domain adaptation (UDA) for semantic segmentation has been well-studied in recent years. However, most existing works largely neglect the local regional consistency across different domains and are less robust to changes in…
This paper presents an improved scheme for the generation and adaption of synthetic images for the training of deep Convolutional Neural Networks(CNNs) to perform the object detection task in smart vending machines. While generating…
Unsupervised domain adaptation (UDA) has become increasingly prevalent in scene text recognition (STR), especially where training and testing data reside in different domains. The efficacy of existing UDA approaches tends to degrade when…