Related papers: A Point in the Right Direction: Vector Prediction …
The goal of 2D human pose estimation (HPE) is to localize anatomical landmarks, given an image of a person in a pose. SOTA techniques make use of thousands of labeled figures (finetuning transformers or training deep CNNs), acquired using…
Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee…
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…
In this paper, we introduce neural texture learning for 6D object pose estimation from synthetic data and a few unlabelled real images. Our major contribution is a novel learning scheme which removes the drawbacks of previous works, namely…
Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…
3D hand-object pose estimation is an important issue to understand the interaction between human and environment. Current hand-object pose estimation methods require detailed 3D labels, which are expensive and labor-intensive. To tackle the…
Most of the existing video self-supervised methods mainly leverage temporal signals of videos, ignoring that the semantics of moving objects and environmental information are all critical for video-related tasks. In this paper, we propose a…
Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy between the two-dimensional image plane and the three-dimensional…
Visual localization is the task of estimating camera pose in a known scene, which is an essential problem in robotics and computer vision. However, long-term visual localization is still a challenge due to the environmental appearance…
In the field of autonomous driving and mobile robotics, there has been a significant shift in the methods used to create Bird's Eye View (BEV) representations. This shift is characterised by using transformers and learning to fuse…
Point clouds provide a flexible and natural representation usable in countless applications such as robotics or self-driving cars. Recently, deep neural networks operating on raw point cloud data have shown promising results on supervised…
Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features. This is typically done through image retrieval, where the query is matched to the most similar images from a…
Perceptual understanding of the scene and the relationship between its different components is important for successful completion of robotic tasks. Representation learning has been shown to be a powerful technique for this, but most of the…
Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination. Scene-level methods tend to lose local details that are crucial for recognizing the road…
Articulated objects exist widely in the real world. However, previous 3D generative methods for unsupervised part decomposition are unsuitable for such objects, because they assume a spatially fixed part location, resulting in inconsistent…
Self-supervised learning is an effective way for label-free model pre-training, especially in the video domain where labeling is expensive. Existing self-supervised works in the video domain use varying experimental setups to demonstrate…
The success of deep learning based models for computer vision applications requires large scale human annotated data which are often expensive to generate. Self-supervised learning, a subset of unsupervised learning, handles this problem by…
Estimating the 3D world from 2D monocular images is a fundamental yet challenging task due to the labour-intensive nature of 3D annotations. To simplify label acquisition, this work proposes a novel approach that bridges 2D vision…
Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vision-based techniques involves the precise extraction of…
While image-text representation learning has become very popular in recent years, existing models tend to lack spatial awareness and have limited direct applicability for dense understanding tasks. For this reason, self-supervised…