The variety of objects in the real world is nearly unlimited and is thus...
Neural rendering is fuelling a unification of learning, 3D geometry and ...
Instance segmentation in 3D is a challenging task due to the lack of
lar...
Recent diffusion-based generators can produce high-quality images based ...
We consider the problem of reconstructing a full 360 photographic model
...
We propose a new approach to learn to segment multiple image objects wit...
We present Neural Feature Fusion Fields (N3F), a method that improves de...
Self-supervised visual representation learning has recently attracted
si...
Motion, measured via optical flow, provides a powerful cue to discover a...
Unsupervised localization and segmentation are long-standing computer vi...
There has been a recent surge in methods that aim to decompose and segme...
The goal of self-supervised visual representation learning is to learn
s...
Most of us are not experts in specific fields, such as ornithology.
None...
Recent research has shown that numerous human-interpretable directions e...
The increasing impact of black box models, and particularly of unsupervi...
Image manipulation can be considered a special case of image generation ...
Understanding images without explicit supervision has become an importan...
In mainstream computer vision and machine learning, public datasets such...
Humans excel in grasping and manipulating objects because of their life-...
While conventional depth estimation can infer the geometry of a scene fr...
Interaction and collaboration between humans and intelligent machines ha...
Given the recent advances in depth prediction from Convolutional Neural
...
Real-time instrument tracking is a crucial requirement for various
compu...
Many prediction tasks contain uncertainty. In some cases, uncertainty is...
This paper addresses the problem of estimating the depth map of a scene ...