Related papers: Augmenting Tactile Simulators with Real-like and Z…
Generative adversarial networks (GANs) are powerful tools for learning generative models. In practice, the training may suffer from lack of convergence. GANs are commonly viewed as a two-player zero-sum game between two neural networks.…
Accurate physics simulation is essential for robotic learning and control, yet analytical simulators often fail to capture complex contact dynamics, while learning-based simulators typically require large amounts of costly real-world data.…
Accurately predicting pedestrian trajectories is crucial in applications such as autonomous driving or service robotics, to name a few. Deep generative models achieve top performance in this task, assuming enough labelled trajectories are…
In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language…
Tactile sensing is inherently contact based. To use tactile data, robots need to make contact with the surface of an object. This is inefficient in applications where an agent needs to make a decision between multiple alternatives that…
Bimanual manipulation with tactile feedback will be key to human-level robot dexterity. However, this topic is less explored than single-arm settings, partly due to the availability of suitable hardware along with the complexity of…
The integration of visual-tactile stimulus is common while humans performing daily tasks. In contrast, using unimodal visual or tactile perception limits the perceivable dimensionality of a subject. However, it remains a challenge to…
One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on…
Simulators perform an important role in prototyping, debugging, and benchmarking new advances in robotics and learning for control. Although many physics engines exist, some aspects of the real world are harder than others to simulate. One…
Hand pose estimation from a monocular RGB image is an important but challenging task. The main factor affecting its performance is the lack of a sufficiently large training dataset with accurate hand-keypoint annotations. In this work, we…
Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly…
State-of-the-art methods in image-to-image translation are capable of learning a mapping from a source domain to a target domain with unpaired image data. Though the existing methods have achieved promising results, they still produce…
Deep learning is actively being used in biometrics to develop efficient identification and verification systems. Handwritten signatures are a common subset of biometric data for authentication purposes. Generative adversarial networks…
For both humans and robots, the sense of touch, known as tactile sensing, is critical for performing contact-rich manipulation tasks. Three key challenges in robotic tactile sensing are 1) interpreting sensor signals, 2) generating sensor…
We propose to improve unconditional Generative Adversarial Networks (GAN) by training the self-supervised learning with the adversarial process. In particular, we apply self-supervised learning via the geometric transformation on input…
We propose a novel and unified Cycle in Cycle Generative Adversarial Network (C2GAN) for generating human faces, hands, bodies, and natural scenes. Our proposed C2GAN is a cross-modal model exploring the joint exploitation of the input…
With recent progress in graphics, it has become more tractable to train models on synthetic images, potentially avoiding the need for expensive annotations. However, learning from synthetic images may not achieve the desired performance due…
In this paper, we focus on the semantic image synthesis task that aims at transferring semantic label maps to photo-realistic images. Existing methods lack effective semantic constraints to preserve the semantic information and ignore the…
Most of current display devices are with eight or higher bit-depth. However, the quality of most multimedia tools cannot achieve this bit-depth standard for the generating images. De-quantization can improve the visual quality of low…
Generative adversarial networks (GANs) have been shown to produce realistic samples from high-dimensional distributions, but training them is considered hard. A possible explanation for training instabilities is the inherent imbalance…