Search Results for author:
Found 54 papers, 13 papers with code
Deep intra-operative illumination calibration of hyperspectral cameras
Hyperspectral imaging (HSI) is emerging as a promising novel imaging modality with various potential surgical applications.
NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
During inference, CNN is used to predict view-invariant features which can be used to establish correspondences with the implicit 3d model in NeRF.
MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images
MatchU is a generic approach that fuses 2D texture and 3D geometric cues for 6D pose prediction of unseen objects.
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
They seek correspondences over downsampled superpoints, which are then propagated to dense points.
On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks
Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data.
Rotation-Invariant Transformer for Point Cloud Matching
To this end, we introduce RoITr, a Rotation-Invariant Transformer to cope with the pose variations in the point cloud matching task.
What can we learn about a generated image corrupting its latent representation?
The purpose of this work is to investigate the hypothesis that we can predict image quality based on its latent representation in the GANs bottleneck.
RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration
More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions.
Multi-View Object Pose Refinement With Differentiable Renderer
This paper introduces a novel multi-view 6 DoF object pose refinement approach focusing on improving methods trained on synthetic data.
DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation
The main conclusions is that RGB excels in correspondence estimation, while depth contributes to the pose accuracy if good 3D-3D correspondences are available.
Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression
Depth estimation is a core task in 3D computer vision.
OSOP: A Multi-Stage One Shot Object Pose Estimation Framework
We present a novel one-shot method for object detection and 6 DoF pose estimation, that does not require training on target objects.
NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimation
Pose estimation of 3D objects in monocular images is a fundamental and long-standing problem in computer vision.
CoFiNet: Reliable Coarse-to-fine Correspondences for Robust Point Cloud Registration
We study the problem of extracting correspondences between a pair of point clouds for registration.
DistillPose: Lightweight Camera Localization Using Auxiliary Learning
A siamese convolutional neural network regresses the relative pose from the nearest neighboring database image to the query image.
CoFiNet: Reliable Coarse-to-fine Correspondences for Robust PointCloud Registration
We study the problem of extracting correspondences between a pair of point clouds for registration.
Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation
For the former we contributed our own dataset composed of five indoor scenes where it is unavoidable to capture images corresponding to views that are hard to uniquely identify.
3D Object Detection and Pose Estimation of Unseen Objects in Color Images with Local Surface Embeddings
We demonstrate the performance of this approach on the T-LESS dataset, by using a small number of objects to learn the embedding and testing it on the other objects.
6D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inference
We present a multimodal camera relocalization framework that captures ambiguities and uncertainties with continuous mixture models defined on the manifold of camera poses.
Real-Time 3D Model Tracking in Color and Depth on a Single CPU Core
We present a novel method to track 3D models in color and depth data.
CorNet: Generic 3D Corners for 6D Pose Estimation of New Objects without Retraining
We first learn to detect object corners of various shapes in images and also to predict their 3D poses, by using training images of a small set of objects.
On Object Symmetries and 6D Pose Estimation from Images
Objects with symmetries are common in our daily life and in industrial contexts, but are often ignored in the recent literature on 6D pose estimation from images.
3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin
In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks.
3D Local Features for Direct Pairwise Registration
Our extensive quantitative and qualitative experiments suggests that our approach outperforms the state of the art in challenging real datasets of pairwise registration and that augmenting the keypoints with local pose information leads to better generalization and a dramatic speed-up.
HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objects
We also present a set of benchmarks to test various desired detector properties, particularly focusing on scalability with respect to the number of objects and resistance to changing light conditions, occlusions and clutter.
DeceptionNet: Network-Driven Domain Randomization
We present a novel approach to tackle domain adaptation between synthetic and real data.
Adversarial Networks for Camera Pose Regression and Refinement
Despite recent advances on the topic of direct camera pose regression using neural networks, accurately estimating the camera pose of a single RGB image still remains a challenging task.
DPOD: 6D Pose Object Detector and Refiner
An additional RGB pose refinement of the initial pose estimates is performed using a custom deep learning-based refinement scheme.
Ranked #8 on
6D Pose Estimation using RGB
on LineMOD
Generic Primitive Detection in Point Clouds Using Novel Minimal Quadric Fits
Based upon the idea of aligning the quadric gradients with the surface normals, our first formulation is exact and requires as low as four oriented points.
Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition
Applying our approach to object recognition from texture-less CAD data, we present a custom generative network which fully utilizes the purely geometrical information to learn robust features and achieve a more refined mapping for unseen color images.
Survey of Higher Order Rigid Body Motion Interpolation Methods for Keyframe Animation and Continuous-Time Trajectory Estimation
In this survey we carefully analyze the characteristics of higher order rigid body motion interpolation methods to obtain a continuous trajectory from a discrete set of poses.
PPF-FoldNet: Unsupervised Learning of Rotation Invariant 3D Local Descriptors
We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry.
Ranked #12 on
Point Cloud Registration
on 3DMatch Benchmark
SobolevFusion: 3D Reconstruction of Scenes Undergoing Free Non-Rigid Motion
We present a system that builds 3D models of non-rigidly moving surfaces from scratch in real time using a single RGB-D stream.
Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC
We introduce Tempered Geodesic Markov Chain Monte Carlo (TG-MCMC) algorithm for initializing pose graph optimization problems, arising in various scenarios such as SFM (structure from motion) or SLAM (simultaneous localization and mapping).
Scene Coordinate and Correspondence Learning for Image-Based Localization
Scene coordinate regression has become an essential part of current camera re-localization methods.
When Regression Meets Manifold Learning for Object Recognition and Pose Estimation
By combining the strengths of manifold learning using triplet loss and pose regression, we could either estimate the pose directly reducing the complexity compared to NN search, or use learned descriptor for the NN descriptor matching.
Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Only
With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images.
A Minimalist Approach to Type-Agnostic Detection of Quadrics in Point Clouds
As opposed to state-of-the-art, where a tailored algorithm treats each primitive type separately, we propose to encapsulate all types in a single robust detection procedure.
PPFNet: Global Context Aware Local Features for Robust 3D Point Matching
We present PPFNet - Point Pair Feature NETwork for deeply learning a globally informed 3D local feature descriptor to find correspondences in unorganized point clouds.
Ranked #14 on
Point Cloud Registration
on 3DMatch Benchmark
SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again
We present a novel method for detecting 3D model instances and estimating their 6D poses from RGB data in a single shot.
Ranked #1 on
6D Pose Estimation using RGBD
on Tejani
KillingFusion: Non-Rigid 3D Reconstruction Without Correspondences
We introduce a geometry-driven approach for real-time 3D reconstruction of deforming surfaces from a single RGB-D stream without any templates or shape priors.
CAD Priors for Accurate and Flexible Instance Reconstruction
With aid of this prior acting as a proxy, we propose a fully enhanced pipeline, capable of automatically detecting and segmenting the object of interest from scenes and creating a pose graph, online, with linear complexity.
3D Pictorial Structures Revisited: Multiple Human Pose Estimation
We address the problem of 3D pose estimation of multiple humans from multiple views.
Ranked #15 on
3D Multi-Person Pose Estimation
on Campus
An Octree-Based Approach towards Efficient Variational Range Data Fusion
Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime.
Deep Learning of Local RGB-D Patches for 3D Object Detection and 6D Pose Estimation
We present a 3D object detection method that uses regressed descriptors of locally-sampled RGB-D patches for 6D vote casting.
Hashmod: A Hashing Method for Scalable 3D Object Detection
We present a scalable method for detecting objects and estimating their 3D poses in RGB-D data.
Volumetric 3D Tracking by Detection
In this paper, we propose a new framework for 3D tracking by detection based on fully volumetric representations.
Dominant Codewords Selection with Topic Model for Action Recognition
Latent Dirichlet allocation (LDA) is used to develop approximations of human motion primitives; these are mid-level representations, and they adaptively integrate dominant vectors when classifying human activities.
A Versatile Learning-Based 3D Temporal Tracker: Scalable, Robust, Online
This paper proposes a temporal tracking algorithm based on Random Forest that uses depth images to estimate and track the 3D pose of a rigid object in real-time.
Toward User-Specific Tracking by Detection of Human Shapes in Multi-Cameras
It usually comprises an association step, that finds correspondences between the model and the input data, and a deformation step, that fits the model to the observations given correspondences.
Multiple human pose estimation with temporally consistent 3d pictorial structures
To address these challenges, we propose a temporally consistent 3D Pictorial Structures model (3DPS) for multiple human pose estimation from multiple camera views.
Ranked #16 on
3D Multi-Person Pose Estimation
on Campus
Multi-Forest Tracker: A Chameleon in Tracking
Moreover, it demonstrates robustness to strong illumination changes when tracking templates using intensity images, and robustness in tracking 3D objects from arbitrary viewpoints even in the presence of motion blur that causes missing or erroneous data in depth images.
3D Pictorial Structures for Multiple Human Pose Estimation
In this work, we address the problem of 3D pose estimation of multiple humans from multiple views.
Ranked #24 on
3D Multi-Person Pose Estimation
on Shelf
Human Shape and Pose Tracking Using Keyframes
In contrast to many existing approaches that rely on a single reference model, multiple templates represent a larger variability of human poses.
