Search Results for author:
Found 15 papers, 9 papers with code
DaD: Distilled Reinforcement Learning for Diverse Keypoint Detection
However, designing a keypoint detection objective is a non-trivial task, as SfM is non-differentiable.
Affine steerers for structured keypoint description
We propose a way to train deep learning based keypoint descriptors that makes them approximately equivariant for locally affine transformations of the image plane.
From 2D to 3D: AISG-SLA Visual Localization Challenge
To tackle these challenges, we organized the AISG-SLA Visual Localization Challenge (VLC) at IJCAI 2023 to explore how AI can accurately extract camera pose data from 2D images in 3D space.
DeDoDe v2: Analyzing and Improving the DeDoDe Keypoint Detector
First, we find that DeDoDe keypoints tend to cluster together, which we fix by performing non-max suppression on the target distribution of the detector during training.
Steerers: A framework for rotation equivariant keypoint descriptors
Image keypoint descriptions that are discriminative and matchable over large changes in viewpoint are vital for 3D reconstruction.
Leveraging Cutting Edge Deep Learning Based Image Matching for Reconstructing a Large Scene from Sparse Images
We present the top ranked solution for the AISG-SLA Visual Localisation Challenge benchmark (IJCAI 2023), where the task is to estimate relative motion between images taken in sequence by a camera mounted on a car driving through an urban scene.
Leveraging the Power of Data Augmentation for Transformer-based Tracking
Due to long-distance correlation and powerful pretrained models, transformer-based methods have initiated a breakthrough in visual object tracking performance.
DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matching
To train a descriptor, we maximize the mutual nearest neighbour objective over the keypoints with a separate network.
RoMa: Robust Dense Feature Matching
The aim is to learn a robust model, i. e., a model able to match under challenging real-world changes.
Ranked #3 on
Image Matching
on ZEB
Camera Calibration without Camera Access -- A Robust Validation Technique for Extended PnP Methods
The first question is how to find the projection model that describes the camera, and the second is to detect incorrect models.
DKM: Dense Kernelized Feature Matching for Geometry Estimation
This changes with our novel dense method, which outperforms both dense and sparse methods on geometry estimation.
Ranked #4 on
Image Matching
on ZEB
Dense Gaussian Processes for Few-Shot Segmentation
Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions.
Ranked #1 on
Few-Shot Semantic Segmentation
on COCO-20i (10-shot)
VidHarm: A Clip Based Dataset for Harmful Content Detection
Automatically identifying harmful content in video is an important task with a wide range of applications.
Deep Gaussian Processes for Few-Shot Segmentation
Through the expressivity of the GP, our approach is capable of modeling complex appearance distributions in the deep feature space.
