Autonomous vehicles (AV) require that neural networks used for perceptio...
We present a novel confidence refinement scheme that enhances pseudo-lab...
Indoor scene reconstruction from monocular images has long been sought a...
We present Neural Fields for LiDAR (NFL), a method to optimise a neural ...
3D instance segmentation is fundamental to geometric understanding of th...
Denoising diffusion models (DDMs) have shown promising results in 3D poi...
Modern 3D semantic instance segmentation approaches predominantly rely o...
As several industries are moving towards modeling massive 3D virtual wor...
We propose to utilize self-supervised techniques in the 2D domain for
fi...
Recent advances in 3D semantic segmentation with deep neural networks ha...
Neural implicit fields have recently emerged as a useful representation ...
Modern computer vision applications rely on learning-based perception mo...
Standard Federated Learning (FL) techniques are limited to clients with
...
Evaluating and improving planning for autonomous vehicles requires scala...
We present Neural Kernel Fields: a novel method for reconstructing impli...
Recent advances in machine learning have created increasing interest in
...
We consider the challenging problem of predicting intrinsic object prope...
We present Mix3D, a data augmentation technique for segmenting large-sca...
We present StrobeNet, a method for category-level 3D reconstruction of
a...
Invariance and equivariance to the rotation group have been widely discu...
Spectral geometric methods have brought revolutionary changes to the fie...
The success of learning with noisy labels (LNL) methods relies heavily o...
We propose a data-driven scene flow estimation algorithm exploiting the
...
We propose a self-supervised framework to learn scene representations fr...
We introduce a technique for 3D human keypoint estimation that directly
...
3D object detection is an important yet demanding task that heavily reli...
Shape correspondence is a fundamental problem in computer graphics and
v...
We propose a self-supervised framework to learn scene representations fr...
Many Reinforcement Learning (RL) approaches use joint control signals
(p...
Arguably one of the top success stories of deep learning is transfer
lea...
We present an approach for aggregating a sparse set of views of an objec...
We seek to learn a representation on a large annotated data source that
...
Learning from unordered sets is a fundamental learning setup, which is
a...
The majority of descriptor-based methods for geometric processing of
non...
3D object detection has seen quick progress thanks to advances in deep
l...
According to Aristotle, a philosopher in Ancient Greece, "the whole is
g...
Current 3D object detection methods are heavily influenced by 2D detecto...
We introduce the first completely unsupervised correspondence learning
a...
We propose a fully-convolutional neural-network architecture for image
d...
In recent years, there has been a surge of interest in developing deep
l...
We present SOSELETO (SOurce SELEction for Target Optimization), a new me...
The availability of affordable and portable depth sensors has made scann...
We present a method to match three dimensional shapes under non-isometri...
The increasing demand for high image quality in mobile devices brings fo...
Poisson distribution is used for modeling noise in photon-limited imagin...
With the development of range sensors such as LIDAR and time-of-flight
c...
We present a proof-of-concept end-to-end system for computational extend...
Recently, the dense binary pixel Gigavision camera had been introduced,
...
We present ASIST, a technique for transforming point clouds by replacing...
The pursuit of smaller pixel sizes at ever increasing resolution in digi...