Related papers: Backtracking Regression Forests for Accurate Camer…
Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency.…
We study rotation-robust learning for image inputs using Convolutional Model Trees (CMTs) [1], whose split and leaf coefficients can be structured on the image grid and transformed geometrically at deployment time. In a controlled MNIST…
We introduce an approach for updating older tree inventories with geographic coordinates using street-level panorama images and a global optimization framework for tree instance matching. Geolocations of trees in inventories until the early…
While object reconstruction has made great strides in recent years, current methods typically require densely captured images and/or known camera poses, and generalize poorly to novel object categories. To step toward object reconstruction…
Random forests construct each tree with a different, randomised representation of the feature space. Their uniform voting cannot correct errors in regions where trees with incorrect representations probabilistically outnumber correct ones,…
We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images). This task is a vital pre-processing stage for nearly all contemporary (neural) reconstruction algorithms but remains challenging given sparse views,…
Camera traps enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor animal populations. We have recently been making strides towards automatic species classification in…
We consider finding a counterfactual explanation for a classification or regression forest, such as a random forest. This requires solving an optimization problem to find the closest input instance to a given instance for which the forest…
In many situations, the choice of an adequate similarity measure or metric on the feature space dramatically determines the performance of machine learning methods. Building automatically such measures is the specific purpose of…
Scene coordinate regression achieves impressive results in outdoor LiDAR localization but requires days of training. Since training needs to be repeated for each new scene, long training times make these methods impractical for…
Pairwise translation directions are a key input to camera location estimation in global structure-from-motion. Existing estimators usually process each image pair independently, producing directions that may be locally plausible but…
The challenges of learning a robust 6D pose function lie in 1) severe occlusion and 2) systematic noises in depth images. Inspired by the success of point-pair features, the goal of this paper is to recover the 6D pose of an object instance…
Given the image collection of an object, we aim at building a real-time image-based pose estimation method, which requires neither its CAD model nor hours of object-specific training. Recent NeRF-based methods provide a promising solution…
Degraded rangelands undergo continual shifts in the appearance and distribution of plant life. The nature of these changes however is subtle: between seasons seedlings sprout up and some flourish while others perish, meanwhile, over…
Camera relocalization is a crucial problem in computer vision and robotics. Recent advancements in neural radiance fields (NeRFs) have shown promise in synthesizing photo-realistic images. Several works have utilized NeRFs for refining…
Training networks to perform metric relocalization traditionally requires accurate image correspondences. In practice, these are obtained by restricting domain coverage, employing additional sensors, or capturing large multi-view datasets.…
Event cameras are bio-inspired sensors that offer several advantages, such as low latency, high-speed and high dynamic range, to tackle challenging scenarios in computer vision. This paper presents a solution to the problem of 3D…
This paper proposes a fine-grained self-localization method for outdoor robotics that utilizes a flexible number of onboard cameras and readily accessible satellite images. The proposed method addresses limitations in existing cross-view…
Aerial image segmentation is the basis for applications such as automatically creating maps or tracking deforestation. In true orthophotos, which are often used in these applications, many objects and regions can be approximated well by…
Segment matching is an important intermediate task in computer vision that establishes correspondences between semantically or geometrically coherent regions across images. Unlike keypoint matching, which focuses on localized features,…