Search Results for author:
Found 81 papers, 48 papers with code
Benchmarks and Challenges in Pose Estimation for Egocentric Hand Interactions with Objects
We interact with the world with our hands and see it through our own (egocentric) perspective.
Point-VOS: Pointing Up Video Object Segmentation
We propose a novel Point-VOS task with a spatio-temporally sparse point-wise annotation scheme that substantially reduces the annotation effort.
An Ordinal Regression Framework for a Deep Learning Based Severity Assessment for Chest Radiographs
This study investigates the application of ordinal regression methods for categorizing disease severity in chest radiographs.
Cyto R-CNN and CytoNuke Dataset: Towards reliable whole-cell segmentation in bright-field histological images
Utilizing this dataset, we compared the performance of Cyto R-CNN to other popular cell segmentation algorithms, including QuPath's built-in algorithm, StarDist and Cellpose.
ControlRoom3D: Room Generation using Semantic Proxy Rooms
Central to our approach is a user-defined 3D semantic proxy room that outlines a rough room layout based on semantic bounding boxes and a textual description of the overall room style.
Mask4Former: Mask Transformer for 4D Panoptic Segmentation
With this intention, we propose Mask4Former for the challenging task of 4D panoptic segmentation of LiDAR point clouds.
Ranked #1 on
4D Panoptic Segmentation
on SemanticKITTI
Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements.
UGainS: Uncertainty Guided Anomaly Instance Segmentation
Our approach centers on an out-of-distribution segmentation model for identifying uncertain regions and a strong generalist segmentation model for anomaly instances segmentation.
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
In an iterative process, the model assigns each data point to an object (or the background), while the user corrects errors in the resulting segmentation and feeds them back into the model.
DynaMITe: Dynamic Query Bootstrapping for Multi-object Interactive Segmentation Transformer
We introduce a more efficient approach, called DynaMITe, in which we represent user interactions as spatio-temporal queries to a Transformer decoder with a potential to segment multiple object instances in a single iteration.
Point2Vec for Self-Supervised Representation Learning on Point Clouds
Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach.
Ranked #3 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 10-way (20-shot)
(using extra training data)
3D Part Segmentation
Few-Shot 3D Point Cloud Classification
+3
TarViS: A Unified Approach for Target-based Video Segmentation
A single TarViS model can be trained jointly on a collection of datasets spanning different tasks, and can hot-swap between tasks during inference without any task-specific retraining.
Ranked #2 on
Video Panoptic Segmentation
on KITTI-STEP
(using extra training data)
Learning 3D Human Pose Estimation from Dozens of Datasets using a Geometry-Aware Autoencoder to Bridge Between Skeleton Formats
Our approach scales to an extreme multi-dataset regime, where we use 28 3D human pose datasets to supervise one model, which outperforms prior work on a range of benchmarks, including the challenging 3D Poses in the Wild (3DPW) dataset.
3D Segmentation of Humans in Point Clouds with Synthetic Data
We address this challenge and propose a framework for generating training data of synthetic humans interacting with real 3D scenes.
Mask3D: Mask Transformer for 3D Semantic Instance Segmentation
Modern 3D semantic instance segmentation approaches predominantly rely on specialized voting mechanisms followed by carefully designed geometric clustering techniques.
Ranked #1 on
3D Instance Segmentation
on ScanNet200
3D Instance Segmentation
3D Semantic Instance Segmentation
+1
4D-StOP: Panoptic Segmentation of 4D LiDAR using Spatio-temporal Object Proposal Generation and Aggregation
Our voting-based tracklet generation method followed by geometric feature-based aggregation generates significantly improved panoptic LiDAR segmentation quality when compared to modeling the entire 4D volume using Gaussian probability distributions.
BURST: A Benchmark for Unifying Object Recognition, Segmentation and Tracking in Video
Multiple existing benchmarks involve tracking and segmenting objects in video e. g., Video Object Segmentation (VOS) and Multi-Object Tracking and Segmentation (MOTS), but there is little interaction between them due to the use of disparate benchmark datasets and metrics (e. g. J&F, mAP, sMOTSA).
Ranked #4 on
Long-tail Video Object Segmentation
on BURST-val
(using extra training data)
Long-tail Video Object Segmentation
Multi-Object Tracking
+6
Global Hierarchical Attention for 3D Point Cloud Analysis
For the 3D object detection task, GHA improves the CenterPoint baseline by +0. 5% mAP on the nuScenes dataset, and the 3DETR baseline by +2. 1% mAP25 and +1. 5% mAP50 on ScanNet.
Pedestrian-Robot Interactions on Autonomous Crowd Navigation: Reactive Control Methods and Evaluation Metrics
Autonomous navigation in highly populated areas remains a challenging task for robots because of the difficulty in guaranteeing safe interactions with pedestrians in unstructured situations.
Differentiable Soft-Masked Attention
Recently, "Masked Attention" was proposed in which a given object representation only attends to those image pixel features for which the segmentation mask of that object is active.
Opening Up Open World Tracking
A benchmark that would allow us to perform an apple-to-apple comparison of existing efforts is a crucial first step towards advancing this important research field.
Ranked #3 on
Open-World Video Segmentation
on BURST-val
(using extra training data)
HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Images
Existing state-of-the-art methods for Video Object Segmentation (VOS) learn low-level pixel-to-pixel correspondences between frames to propagate object masks across video.
D2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
We further show that D2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
D^2Conv3D: Dynamic Dilated Convolutions for Object Segmentation in Videos
We further show that D^2Conv3D out-performs trivial extensions of existing dilated and deformable convolutions to 3D.
Mix3D: Out-of-Context Data Augmentation for 3D Scenes
Since scene context helps reasoning about object semantics, current works focus on models with large capacity and receptive fields that can fully capture the global context of an input 3D scene.
Ranked #3 on
Semantic Segmentation
on ScanNet
Person-MinkUNet: 3D Person Detection with LiDAR Point Cloud
In this preliminary work we attempt to apply submanifold sparse convolution to the task of 3D person detection.
2D vs. 3D LiDAR-based Person Detection on Mobile Robots
Person detection is a crucial task for mobile robots navigating in human-populated environments.
Opening up Open-World Tracking
We hope to open a new front in multi-object tracking research that will hopefully bring us a step closer to intelligent systems that can operate safely in the real world.
STEP: Segmenting and Tracking Every Pixel
The task of assigning semantic classes and track identities to every pixel in a video is called video panoptic segmentation.
From Points to Multi-Object 3D Reconstruction
We propose a method to detect and reconstruct multiple 3D objects from a single RGB image.
Self-Supervised Person Detection in 2D Range Data using a Calibrated Camera
Through experiments on the JackRabbot dataset with two detector models, DROW3 and DR-SPAAM, we show that self-supervised detectors, trained or fine-tuned with pseudo-labels, outperform detectors trained only on a different dataset.
Reducing the Annotation Effort for Video Object Segmentation Datasets
We use a deep convolutional network to automatically create pseudo-labels on a pixel level from much cheaper bounding box annotations and investigate how far such pseudo-labels can carry us for training state-of-the-art VOS approaches.
HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking
Multi-Object Tracking (MOT) has been notoriously difficult to evaluate.
Making a Case for 3D Convolutions for Object Segmentation in Videos
On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos compared to their 2D convolutional counterparts and lag behind the aforementioned networks in terms of performance.
Ranked #12 on
Unsupervised Video Object Segmentation
on DAVIS 2016 val
MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation
Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research.
Ranked #1 on
3D Human Pose Estimation
on 3D Poses in the Wild Challenge
(MPJPE metric)
Reposing Humans by Warping 3D Features
We address the problem of reposing an image of a human into any desired novel pose.
SAMP: Shape and Motion Priors for 4D Vehicle Reconstruction
In this paper, we propose to use 3D shape and motion priors to regularize the estimation of the trajectory and the shape of vehicles in sequences of stereo images.
DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data
Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data.
Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos
Instead of training the network for estimating keypoint correspondences on video data, it is trained on a large scale image datasets for human pose estimation using self-supervision.
Multi-Person Pose Estimation
Multi-Person Pose Estimation and Tracking
+1
DualConvMesh-Net: Joint Geodesic and Euclidean Convolutions on 3D Meshes
That is, the convolutional kernel weights are mapped to the local surface of a given mesh.
3D-MPA: Multi Proposal Aggregation for 3D Semantic Instance Segmentation
We show that grouping proposals improves over NMS and outperforms previous state-of-the-art methods on the tasks of 3D object detection and semantic instance segmentation on the ScanNetV2 benchmark and the S3DIS dataset.
Ranked #1 on
3D Semantic Instance Segmentation
on ScanNetV2
STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos
In this paper, we propose a different approach that is well-suited to a variety of tasks involving instance segmentation in videos.
Ranked #5 on
Unsupervised Video Object Segmentation
on DAVIS 2017 (val)
(using extra training data)
Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose Estimation
Furthermore, as the image space is decoupled from the heatmap space, the network can learn to reason about joints beyond the image boundary.
Ranked #151 on
3D Human Pose Estimation
on Human3.6M
UnOVOST: Unsupervised Offline Video Object Segmentation and Tracking
UnOVOST even performs competitively with many semi-supervised video object segmentation algorithms even though it is not given any input as to which objects should be tracked and segmented.
Siam R-CNN: Visual Tracking by Re-Detection
We present Siam R-CNN, a Siamese re-detection architecture which unleashes the full power of two-stage object detection approaches for visual object tracking.
Ranked #5 on
Object Tracking
on COESOT
Single-Shot Panoptic Segmentation
We present a novel end-to-end single-shot method that segments countable object instances (things) as well as background regions (stuff) into a non-overlapping panoptic segmentation at almost video frame rate.
AlignNet-3D: Fast Point Cloud Registration of Partially Observed Objects
In this work, we focus on precise 3D track state estimation and propose a learning-based approach for object-centric relative motion estimation of partially observed objects.
Track to Reconstruct and Reconstruct to Track
Object tracking and 3D reconstruction are often performed together, with tracking used as input for reconstruction.
Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds
In a thorough ablation study, we show that the receptive field size is directly related to the performance of 3D point cloud processing tasks, including semantic segmentation and object classification.
Ranked #43 on
Semantic Segmentation
on S3DIS Area5
Visual Person Understanding through Multi-Task and Multi-Dataset Learning
We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation.
BoLTVOS: Box-Level Tracking for Video Object Segmentation
Following this paradigm, we present BoLTVOS (Box-Level Tracking for VOS), which consists of an R-CNN detector conditioned on the first-frame bounding box to detect the object of interest, a temporal consistency rescoring algorithm, and a Box2Seg network that converts bounding boxes to segmentation masks.
3D-BEVIS: Bird's-Eye-View Instance Segmentation
A lot of progress was made in the field of object classification and semantic segmentation.
Ranked #4 on
3D Semantic Instance Segmentation
on ScanNetV2
3D Instance Segmentation
3D Semantic Instance Segmentation
+4
Large-Scale Object Mining for Object Discovery from Unlabeled Video
This paper addresses the problem of object discovery from unlabeled driving videos captured in a realistic automotive setting.
FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentation
Many of the recent successful methods for video object segmentation (VOS) are overly complicated, heavily rely on fine-tuning on the first frame, and/or are slow, and are hence of limited practical use.
Ranked #1 on
Semi-Supervised Video Object Segmentation
on YouTube
MOTS: Multi-Object Tracking and Segmentation
This paper extends the popular task of multi-object tracking to multi-object tracking and segmentation (MOTS).
Ranked #6 on
Multi-Object Tracking
on MOTS20
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+3
4D Generic Video Object Proposals
Many high-level video understanding methods require input in the form of object proposals.
Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds
In this paper, we present a deep learning architecture which addresses the problem of 3D semantic segmentation of unstructured point clouds.
Combined Image- and World-Space Tracking in Traffic Scenes
Most of the current vision-based tracking methods perform tracking in the image domain.
Ranked #22 on
Multiple Object Tracking
on KITTI Tracking test
Towards Large-Scale Video Video Object Mining
We propose to leverage a generic object tracker in order to perform object mining in large-scale unlabeled videos, captured in a realistic automotive setting.
Synthetic Occlusion Augmentation with Volumetric Heatmaps for the 2018 ECCV PoseTrack Challenge on 3D Human Pose Estimation
In this paper we present our winning entry at the 2018 ECCV PoseTrack Challenge on 3D human pose estimation.
Ranked #211 on
3D Human Pose Estimation
on Human3.6M
How Robust is 3D Human Pose Estimation to Occlusion?
Occlusion is commonplace in realistic human-robot shared environments, yet its effects are not considered in standard 3D human pose estimation benchmarks.
Ranked #222 on
3D Human Pose Estimation
on Human3.6M
PReMVOS: Proposal-generation, Refinement and Merging for Video Object Segmentation
We address semi-supervised video object segmentation, the task of automatically generating accurate and consistent pixel masks for objects in a video sequence, given the first-frame ground truth annotations.
Iteratively Trained Interactive Segmentation
Deep learning requires large amounts of training data to be effective.
Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline
In the past decade many robots were deployed in the wild, and people detection and tracking is an important component of such deployments.
Deep Person Detection in 2D Range Data
Detecting humans is a key skill for mobile robots and intelligent vehicles in a large variety of applications.
Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds
The recently proposed PointNet architecture presents an interesting step ahead in that it can operate on unstructured point clouds, achieving encouraging segmentation results.
Large-Scale Object Discovery and Detector Adaptation from Unlabeled Video
We explore object discovery and detector adaptation based on unlabeled video sequences captured from a mobile platform.
Track, then Decide: Category-Agnostic Vision-based Multi-Object Tracking
In this paper, we propose a model-free multi-object tracking approach that uses a category-agnostic image segmentation method to track objects.
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation
We tackle the task of semi-supervised video object segmentation, i. e. segmenting the pixels belonging to an object in the video using the ground truth pixel mask for the first frame.
Ranked #2 on
Visual Object Tracking
on YouTube-VOS 2018
The Atari Grand Challenge Dataset
Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce.
Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
With the rise of end-to-end learning through deep learning, person detectors and re-identification (ReID) models have recently become very strong.
In Defense of the Triplet Loss for Person Re-Identification
In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning.
Ranked #3 on
Person Re-Identification
on CUHK03
(Rank-5 metric)
Semi-Supervised Deep Learning for Monocular Depth Map Prediction
Supervised deep learning often suffers from the lack of sufficient training data.
Keyframe-Based Visual-Inertial Online SLAM with Relocalization
Our visual-inertial SLAM system is based on a real-time capable visual-inertial odometry method that provides locally consistent trajectory and map estimates.
Superpixels: An Evaluation of the State-of-the-Art
As such, and due to their quick adoption in a wide range of applications, appropriate benchmarks are crucial for algorithm selection and comparison.
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
Therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution.
Ranked #25 on
Real-Time Semantic Segmentation
on Cityscapes test
Incremental Object Discovery in Time-Varying Image Collections
Abstract In this paper, we address the problem of object discovery in time-varying, large-scale image collections.
DROW: Real-Time Deep Learning based Wheelchair Detection in 2D Range Data
We propose a Convolutional Neural Network (CNN) based detector for this task.
Visual Landmark Recognition from Internet Photo Collections: A Large-Scale Evaluation
We evaluate how different choices of methods and parameters for the individual pipeline steps affect overall system performance and examine their effects for different query categories such as buildings, paintings or sculptures.
Probabilistic Labeling Cost for High-Accuracy Multi-View Reconstruction
In this paper, we propose a novel labeling cost for multi- view reconstruction.
Tracking People and Their Objects
Current pedestrian tracking approaches ignore important aspects of human behavior.
