We demonstrate that this formulation encourages the models to learn embeddings that are invariant to viewpoint variations and consistent across sensor modalities.
The popular object detection metric 3D Average Precision (3D AP) relies on the intersection over union between predicted bounding boxes and ground truth bounding boxes.
We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments.
We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions.
We present 4D-Net, a 3D object detection approach, which utilizes 3D Point Cloud and RGB sensing information, both in time.
We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision.
Based on our findings we propose a new mathematical formulation of memorability decay, resulting in a model that is able to produce the first quantitative estimation of how a video decays in memory over time.
This paper introduces a Unified Model of Saliency and Importance (UMSI), which learns to predict visual importance in input graphic designs, and saliency in natural images, along with a new dataset and applications.
Many computer vision tasks address the problem of scene understanding and are naturally interrelated e. g. object classification, detection, scene segmentation, depth estimation, etc.
We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion.
A common approach is to learn an end-to-end policy that directly predicts controls from raw images by imitating an expert.
High-resolution connectomics data allows for the identification of dysfunctional mitochondria which are linked to a variety of diseases such as autism or bipolar.
Models and examples built with TensorFlow
Ranked #10 on Unsupervised Monocular Depth Estimation on Cityscapes
Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an end-to-end policy, which directly predicts controls from raw images.
Automating the navigation of unmanned aerial vehicles (UAVs) in diverse scenarios has gained much attention in recent years.
We present a photo-realistic training and evaluation simulator (Sim4CV) with extensive applications across various fields of computer vision.