Related papers: Priors are Powerful: Improving a Transformer for M…

We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D…

Transformers are a popular choice for classification tasks and as backbones for object detection tasks. However, their high latency brings challenges in their adaptation to lightweight object detection systems. We present an approximation…

Deep learning has improved vanishing point detection in images. Yet, deep networks require expensive annotated datasets trained on costly hardware and do not generalize to even slightly different domains, and minor problem variants. Here,…

Neuromorphic cameras, also known as event cameras, are asynchronous brightness-change sensors that can capture extremely fast motion without suffering from motion blur, making them particularly promising for 3D reconstruction in extreme…

Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics. By leveraging a set of primitives to represent the target shape, recent methods have achieved promising results. However, these…

6D pose estimation is the task of predicting the translation and orientation of objects in a given input image, which is a crucial prerequisite for many robotics and augmented reality applications. Lately, the Transformer Network…

Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems. In this paper, we tailor transformer-based…

As demand for robotics manipulation application increases, accurate vision-based 6D pose estimation becomes essential for autonomous operations. Convolutional Neural Networks (CNNs) based approaches for pose estimation have been previously…

Image restoration has seen great progress in the last years thanks to the advances in deep neural networks. Most of these existing techniques are trained using full supervision with suitable image pairs to tackle a specific degradation.…

Symmetry plays a vital role in understanding structural patterns, aiding object recognition and scene interpretation. This paper focuses on rotation symmetry, where objects remain unchanged when rotated around a central axis, requiring…

Particularly in low-data regimes, an outstanding challenge in machine learning is developing principled techniques for augmenting our models with suitable priors. This is to encourage them to learn in ways that are compatible with our…

3D object detection using point clouds has attracted increasing attention due to its wide applications in autonomous driving and robotics. However, most existing studies focus on single point cloud frames without harnessing the temporal…

Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fidelity model trained on data that closely match the unknown…

We introduce a Transformer based 6D Object Pose Estimation framework VideoPose, comprising an end-to-end attention based modelling architecture, that attends to previous frames in order to estimate accurate 6D Object Poses in videos. Our…

Roadside vision centric 3D object detection has received increasing attention in recent years. It expands the perception range of autonomous vehicles, enhances the road safety. Previous methods focused on predicting per-pixel height rather…

Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the…

Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features…

Monocular 3D human pose estimation remains a challenging and ill-posed problem, particularly in real-time settings and unconstrained environments. While direct imageto-3D approaches require large annotated datasets and heavy models,…

The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field. The transformer has been used as a replacement for the widely used convolution operators, due to its…

Self-supervised monocular depth estimation aims to infer depth information without relying on labeled data. However, the lack of labeled information poses a significant challenge to the model's representation, limiting its ability to…