Search Results for author:
Found 69 papers, 37 papers with code
MATCHA:Towards Matching Anything
Extensive experiments validate that MATCHA consistently surpasses state-of-the-art methods across geometric, semantic, and temporal matching tasks, setting a new foundation for a unified approach for the fundamental correspondence problem in computer vision.
Light3R-SfM: Towards Feed-forward Structure-from-Motion
We present Light3R-SfM, a feed-forward, end-to-end learnable framework for efficient large-scale Structure-from-Motion (SfM) from unconstrained image collections.
BEV-SUSHI: Multi-Target Multi-Camera 3D Detection and Tracking in Bird's-Eye View
Object perception from multi-view cameras is crucial for intelligent systems, particularly in indoor environments, e. g., warehouses, retail stores, and hospitals.
Ranked #1 on
Multi-Object Tracking
on Wildtrack
(using extra training data)
DynOMo: Online Point Tracking by Dynamic Online Monocular Gaussian Reconstruction
We target the challenge of online 2D and 3D point tracking from unposed monocular camera input introducing Dynamic Online Monocular Reconstruction (DynOMo).
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation
Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain, e. g., synthetic data, and an unlabeled target domain.
SPAMming Labels: Efficient Annotations for the Trackers of Tomorrow
Increasing the annotation efficiency of trajectory annotations from videos has the potential to enable the next generation of data-hungry tracking algorithms to thrive on large-scale datasets.
SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation
In recent years, semantic segmentation has become a pivotal tool in processing and interpreting satellite imagery.
Better Call SAL: Towards Learning to Segment Anything in Lidar
We propose the SAL (Segment Anything in Lidar) method consisting of a text-promptable zero-shot model for segmenting and classifying any object in Lidar, and a pseudo-labeling engine that facilitates model training without manual supervision.
The NeRFect Match: Exploring NeRF Features for Visual Localization
Significantly, we introduce NeRFMatch, an advanced 2D-3D matching function that capitalizes on the internal knowledge of NeRF learned via view synthesis.
SeMoLi: What Moves Together Belongs Together
Recent results suggest that heuristic-based clustering methods in conjunction with object trackers can be used to pseudo-label instances of moving objects and use these as supervisory signals to train 3D object detectors in Lidar data without manual supervision.
Lidar Panoptic Segmentation and Tracking without Bells and Whistles
Our network is modular by design and optimized for all aspects of both the panoptic segmentation and tracking task.
Staged Contact-Aware Global Human Motion Forecasting
So far, only Mao et al. NeurIPS'22 have addressed scene-aware global motion, cascading the prediction of future scene contact points and the global motion estimation.
Ranked #2 on
Human Pose Forecasting
on GTA-IM Dataset
Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis
To highlight the importance of privacy issues and motivate future research, we motivate and introduce the Pedestrian Dataset De-Identification (PDI) task.
Walking Your LiDOG: A Journey Through Multiple Domains for LiDAR Semantic Segmentation
To answer this question, we design the first experimental setup for studying domain generalization (DG) for LiDAR semantic segmentation (DG-LSS).
G-MSM: Unsupervised Multi-Shape Matching with Graph-based Affinity Priors
We present G-MSM (Graph-based Multi-Shape Matching), a novel unsupervised learning approach for non-rigid shape correspondence.
Unifying Short and Long-Term Tracking with Graph Hierarchies
Tracking objects over long videos effectively means solving a spectrum of problems, from short-term association for un-occluded objects to long-term association for objects that are occluded and then reappear in the scene.
Ranked #2 on
Multiple Object Tracking
on BDD100K test
Soft Augmentation for Image Classification
We draw inspiration from human visual classification studies and propose generalizing augmentation with invariant transforms to soft augmentation where the learning target softens non-linearly as a function of the degree of the transform applied to the sample: e. g., more aggressive image crop augmentations produce less confident learning targets.
Learning to Discover and Detect Objects
We then train our network to learn to classify each RoI, either as one of the known classes, seen in the source dataset, or one of the novel classes, with a long-tail distribution constraint on the class assignments, reflecting the natural frequency of classes in the real world.
Ranked #2 on
Novel Object Detection
on LVIS v1.0 val
Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?
While we have significantly advanced short-term tracking performance, bridging longer occlusion gaps remains elusive: state-of-the-art object trackers only bridge less than 10% of occlusions longer than three seconds.
The Unreasonable Effectiveness of Fully-Connected Layers for Low-Data Regimes
This allows us to improve the generalization of a CNN-based model without any increase in the number of weights at test time.
DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustment
Direct methods have shown excellent performance in the applications of visual odometry and SLAM.
PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?
This allows our graph neural network to learn to effectively encode temporal and spatial interactions and fully leverage contextual and motion cues to obtain final scene interpretation by posing data association as edge classification.
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
To reason about all VIS subtasks jointly over multiple frames, we present temporal multi-scale deformable attention with instance-aware object queries.
Simple Cues Lead to a Strong Multi-Object Tracker
For association, most models resourced to motion and appearance cues, e. g., re-identification networks.
A Unified Framework for Implicit Sinkhorn Differentiation
The Sinkhorn operator has recently experienced a surge of popularity in computer vision and related fields.
Forecasting from LiDAR via Future Object Detection
Object detection and forecasting are fundamental components of embodied perception.
Is Geometry Enough for Matching in Visual Localization?
In this paper, we propose to go beyond the well-established approach to vision-based localization that relies on visual descriptor matching between a query image and a 3D point cloud.
DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation
These observations are paired with pixel-wise monthly semantic segmentation labels of 7 land use and land cover (LULC) classes.
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)
The Center of Attention: Center-Keypoint Grouping via Attention for Multi-Person Pose Estimation
We introduce CenterGroup, an attention-based framework to estimate human poses from a set of identity-agnostic keypoints and person center predictions in an image.
Ranked #6 on
Multi-Person Pose Estimation
on MS COCO
Spatial Context Awareness for Unsupervised Change Detection in Optical Satellite Images
It uses this model to analyze differences in the pixel and its spatial context-based predictions in subsequent time periods for change detection.
Scalable Sinkhorn Backpropagation
Our main contribution is deriving a simple and efficient algorithm that performs this backward pass in closed form.
(Just) A Spoonful of Refinements Helps the Registration Error Go Down
However, given the initial rotation estimate supplied by Kabsch, we show we can improve point correspondence learning during model training by extending the original optimization problem.
The 2021 Image Similarity Dataset and Challenge
This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021).
Ranked #1 on
Image Similarity Detection
on DISC21 dev
EagerMOT: 3D Multi-Object Tracking via Sensor Fusion
Multi-object tracking (MOT) enables mobile robots to perform well-informed motion planning and navigation by localizing surrounding objects in 3D space and time.
Ranked #1 on
Multi-Object Tracking and Segmentation
on KITTI MOTS
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.
Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization
The goal of cross-view image based geo-localization is to determine the location of a given street view image by matching it against a collection of geo-tagged satellite images.
Vision-Based Mobile Robotics Obstacle Avoidance With Deep Reinforcement Learning
Obstacle avoidance is a fundamental and challenging problem for autonomous navigation of mobile robots.
4D Panoptic LiDAR Segmentation
In this paper, we propose 4D panoptic LiDAR segmentation to assign a semantic class and a temporally-consistent instance ID to a sequence of 3D points.
Ranked #7 on
4D Panoptic Segmentation
on SemanticKITTI
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.
Learning Intra-Batch Connections for Deep Metric Learning
To this end, we propose an approach based on message passing networks that takes all the relations in a mini-batch into account.
Ranked #3 on
Metric Learning
on CARS196
Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
We propose a novel unsupervised learning approach to 3D shape correspondence that builds a multiscale matching pipeline into a deep neural network.
MOTChallenge: A Benchmark for Single-Camera Multiple Target Tracking
We present MOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data, and create a framework for the standardized evaluation of multiple object tracking methods.
Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimation
Inspired by human navigation, we model the task of trajectory prediction as an intuitive two-stage process: (i) goal estimation, which predicts the most likely target positions of the agent, followed by a (ii) routing module which estimates a set of plausible trajectories that route towards the estimated goal.
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 #15 on
Unsupervised Video Object Segmentation
on DAVIS 2016 val
Focus on defocus: bridging the synthetic to real domain gap for depth estimation
We are able to train our model completely on synthetic data and directly apply it to a wide range of real-world images.
Ranked #1 on
Depth Estimation
on NYU-Depth V2
(RMSE metric)
CIAGAN: Conditional Identity Anonymization Generative Adversarial Networks
In many real-world scenarios like people tracking or action recognition, it is important to be able to process the data while taking careful consideration in protecting people's identity.
Planning from Images with Deep Latent Gaussian Process Dynamics
We propose to learn a deep latent Gaussian process dynamics (DLGPD) model that learns low-dimensional system dynamics from environment interactions with visual observations.
MOT20: A benchmark for multi object tracking in crowded scenes
The benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal to establish a standardized evaluation of multiple object tracking methods.
Multi-Object Tracking
Multiple Object Tracking with Transformer
+2
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)
Learn to Predict Sets Using Feed-Forward Neural Networks
In our formulation we define a likelihood for a set distribution represented by a) two discrete distributions defining the set cardinally and permutation variables, and b) a joint distribution over set elements with a fixed cardinality.
Learning a Neural Solver for Multiple Object Tracking
Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm.
HistoNet: Predicting size histograms of object instances
Our method results in an overall improvement in the count and size distribution prediction as compared to state-of-the-art instance segmentation method Mask R-CNN.
Towards Generalizing Sensorimotor Control Across Weather Conditions
The ability of deep learning models to generalize well across different scenarios depends primarily on the quality and quantity of annotated data.
Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
Additionally, we propose a first set of metrics to quantitatively evaluate the accuracy as well as the perceptual quality of the temporal evolution.
Ranked #1 on
Video Super-Resolution
on MSU Video Upscalers: Quality Enhancement
(VMAF metric)
Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs
To this end, we propose to divide the task of vehicle control into two independent modules: a control module which is only trained on one weather condition for which labeled steering data is available, and a perception module which is used as an interface between new weather conditions and the fixed control module.
Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks
We demonstrate the validity of this new formulation on two relevant vision problems: object detection, for which our formulation outperforms state-of-the-art detectors such as Faster R-CNN and YOLO, and a complex CAPTCHA test, where we observe that, surprisingly, our set based network acquired the ability of mimicking arithmetics without any rules being coded.
Deep Appearance Maps
Second, we demonstrate how another network can be used to map from an image or video frames to a DAM network to reproduce this appearance, without using a lengthy optimization such as stochastic gradient descent (learning-to-learn).
Video Object Segmentation Without Temporal Information
Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames.
Ranked #47 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
Fusion of Head and Full-Body Detectors for Multi-Object Tracking
In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach.
Ranked #22 on
Multi-Object Tracking
on MOT16
Discrete-Continuous ADMM for Transductive Inference in Higher-Order MRFs
This paper introduces a novel algorithm for transductive inference in higher-order MRFs, where the unary energies are parameterized by a variable classifier.
Tracking the Trackers: An Analysis of the State of the Art in Multiple Object Tracking
Standardized benchmarks are crucial for the majority of computer vision applications.
Deep Depth From Focus
Depth from focus (DFF) is one of the classical ill-posed inverse problems in computer vision.
Image-based localization using LSTMs for structured feature correlation
In this work we propose a new CNN+LSTM architecture for camera pose regression for indoor and outdoor scenes.
One-Shot Video Object Segmentation
This paper tackles the task of semi-supervised video object segmentation, i. e., the separation of an object from the background in a video, given the mask of the first frame.
Tracking with multi-level features
We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features.
Learning by tracking: Siamese CNN for robust target association
This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections.
MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking
We discuss the challenges of creating such a framework, collecting existing and new data, gathering state-of-the-art methods to be tested on the datasets, and finally creating a unified evaluation system.
Multiple object tracking with context awareness
Multiple people tracking is a key problem for many applications such as surveillance, animation or car navigation, and a key input for tasks such as activity recognition.
