Related papers: Sim2Real Instance-Level Style Transfer for 6D Pose…

Recent advances in machine learning have greatly benefited object detection and 6D pose estimation. However, textureless and metallic objects still pose a significant challenge due to few visual cues and the texture bias of CNNs. To address…

We introduce a novel learning method for 3D pose estimation from color images. While acquiring annotations for color images is a difficult task, our approach circumvents this problem by learning a mapping from paired color and depth images…

Domain adaptive pose estimation aims to enable deep models trained on source domain (synthesized) datasets produce similar results on the target domain (real-world) datasets. The existing methods have made significant progress by conducting…

Automation in surgical robotics has the potential to improve patient safety and surgical efficiency, but it is difficult to achieve due to the need for robust perception algorithms. In particular, 6D pose estimation of surgical instruments…

It is often desired to train 6D pose estimation systems on synthetic data because manual annotation is expensive. However, due to the large domain gap between the synthetic and real images, synthesizing color images is expensive. In…

We present a system for training deep neural networks for object detection using synthetic images. To handle the variability in real-world data, the system relies upon the technique of domain randomization, in which the parameters of the…

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on…

Robots working in unstructured environments must be capable of sensing and interpreting their surroundings. One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for…

We describe a novel learning-by-synthesis method for estimating gaze direction of an automated intelligent surveillance system. Recently, progress in learning-by-synthesis has proposed training models on synthetic images, which can…

Developing meaningful and efficient representations that separate the fundamental structure of the data generation mechanism is crucial in representation learning. However, Disentangled Representation Learning has not fully shown its…

Human pose estimation (HPE) is a central part of understanding the visual narration and body movements of characters depicted in artwork collections, such as Greek vase paintings. Unfortunately, existing HPE methods do not generalise well…

Modern pose estimation models are trained on large, manually-labelled datasets which are costly and may not cover the full extent of human poses and appearances in the real world. With advances in neural rendering, analysis-by-synthesis and…

In this paper, we address the Sim2Real gap in the field of vision-based tactile sensors for classifying object surfaces. We train a Diffusion Model to bridge this gap using a relatively small dataset of real-world images randomly collected…

Multi-person pose estimation from a 2D image is an essential technique for human behavior understanding. In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose.…

State-of-the-art Style Transfer methods often leverage pre-trained encoders optimized for discriminative tasks, which may not be ideal for image synthesis. This can result in significant artifacts and loss of photorealism. Motivated by the…

Deep models trained using synthetic data require domain adaptation to bridge the gap between the simulation and target environments. State-of-the-art domain adaptation methods often demand sufficient amounts of (unlabelled) data from the…

Recently simulation methods have been developed for optical tactile sensors to enable the Sim2Real learning, i.e., firstly training models in simulation before deploying them on the real robot. However, some artefacts in the real objects…

The Robotics community has started to heavily rely on increasingly realistic 3D simulators for large-scale training of robots on massive amounts of data. But once robots are deployed in the real world, the simulation gap, as well as changes…

In this work, we tackle the task of estimating the 6D pose of an object from point cloud data. While recent learning-based approaches to addressing this task have shown great success on synthetic datasets, we have observed them to fail in…

Building generic robotic manipulation systems often requires large amounts of real-world data, which can be dificult to collect. Synthetic data generation offers a promising alternative, but limiting the sim-to-real gap requires significant…