Search Results for author:
Found 145 papers, 73 papers with code
Show or Tell? Effectively prompting Vision-Language Models for semantic segmentation
Large Vision-Language Models (VLMs) are increasingly being regarded as foundation models that can be instructed to solve diverse tasks by prompting, without task-specific training.
Cutting-edge 3D reconstruction solutions for underwater coral reef images: A review and comparison
This work equips scientists and managers with a technical foundation and practical guidance for processing underwater coral reef images for 3D reconstruction....
A Variational Perspective on Generative Protein Fitness Optimization
The goal of protein fitness optimization is to discover new protein variants with enhanced fitness for a given use.
CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
We introduce a novel method for generating 360{\deg} panoramas from text prompts or images.
BRIGHT: A globally distributed multimodal building damage assessment dataset with very-high-resolution for all-weather disaster response
In this paper, we present a BDA dataset using veRy-hIGH-resoluTion optical and SAR imagery (BRIGHT) to support AI-based all-weather disaster response.
Uncertainties of Satellite-based Essential Climate Variables from Deep Learning
Accurate uncertainty information associated with essential climate variables (ECVs) is crucial for reliable climate modeling and understanding the spatiotemporal evolution of the Earth system.
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion
Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image.
Video Depth without Video Models
Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame.
The unrealized potential of agroforestry for an emissions-intensive agricultural commodity
One proposed strategy for addressing this problem is the judicious retention of trees in agricultural systems.
GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation
We propose GALA, a novel representation of 3D shapes that (i) excels at capturing and reproducing complex geometry and surface details, (ii) is computationally efficient, and (iii) lends itself to 3D generative modelling with modern, diffusion-based schemes.
LoopSplat: Loop Closure by Registering 3D Gaussian Splats
However, existing 3DGS-based methods fail to address the global consistency of the scene via loop closure and/or global bundle adjustment.
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
For the training of such a refiner, we propose global pre-alignment and local patch masking methods to ensure BetterDepth remains faithful to the depth conditioning while learning to add fine-grained scene details.
Consistency^2: Consistent and Fast 3D Painting with Latent Consistency Models
Generative 3D Painting is among the top productivity boosters in high-resolution 3D asset management and recycling.
AGBD: A Global-scale Biomass Dataset
This dataset combines AGB reference data from the GEDI mission with data from Sentinel-2 and PALSAR-2 imagery.
An Open-Source Tool for Mapping War Destruction at Scale in Ukraine using Sentinel-1 Time Series
Access to detailed war impact assessments is crucial for humanitarian organizations to effectively assist populations most affected by armed conflicts.
FlowSDF: Flow Matching for Medical Image Segmentation Using Distance Transforms
Medical image segmentation is a crucial task that relies on the ability to accurately identify and isolate regions of interest in medical images.
LoRA-Ensemble: Efficient Uncertainty Modelling for Self-attention Networks
We introduce LoRA-Ensemble, a parameter-efficient deep ensemble method for self-attention networks, which is based on Low-Rank Adaptation (LoRA).
I-Design: Personalized LLM Interior Designer
Interior design allows us to be who we are and live how we want - each design is as unique as our distinct personality.
StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation
Most image-to-image translation models postulate that a unique correspondence exists between the semantic classes of the source and target domains.
Point2Building: Reconstructing Buildings from Airborne LiDAR Point Clouds
What makes 3D building reconstruction from airborne LiDAR hard is the large diversity of building designs and especially roof shapes, the low and varying point density across the scene, and the often incomplete coverage of building facades due to occlusions by vegetation or to the viewing angle of the sensor.
Is Continual Learning Ready for Real-world Challenges?
Our paper aims to initiate a paradigm shift, advocating for the adoption of continual learning methods through new experimental protocols that better emulate real-world conditions to facilitate breakthroughs in the field.
SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data
In conclusion, this study shows the feasibility of a sensor-agnostic model for diverse lidar data, surpassing sensor-specific approaches and setting new standards in tree segmentation, particularly in complex forests.
Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning
Detailed forest inventories are critical for sustainable and flexible management of forest resources, to conserve various ecosystem services.
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments
Research into dynamic 3D scene understanding has primarily focused on short-term change tracking from dense observations, while little attention has been paid to long-term changes with sparse observations.
Dynamic LiDAR Re-simulation using Compositional Neural Fields
We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes.
Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds
Computer-Aided Design (CAD) model reconstruction from point clouds is an important problem at the intersection of computer vision, graphics, and machine learning; it saves the designer significant time when iterating on in-the-wild objects.
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content, specialize to user data through few-shot fine-tuning, and condition their output on other modalities, such as semantic maps.
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Monocular depth estimation is a fundamental computer vision task.
Ranked #6 on
Monocular Depth Estimation
on ETH3D
Neural Fields with Thermal Activations for Arbitrary-Scale Super-Resolution
We present a novel way to design neural fields such that points can be queried with an adaptive Gaussian PSF, so as to guarantee correct anti-aliasing at any desired output resolution.
High-resolution Population Maps Derived from Sentinel-1 and Sentinel-2
With our work we aim to democratize access to up-to-date and high-resolution population maps, recognizing that some regions faced with particularly strong population dynamics may lack the resources for costly micro-census campaigns.
Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change
To this end, we introduce the Nothing Stands Still (NSS) benchmark, which focuses on the spatiotemporal registration of 3D scenes undergoing large spatial and temporal change, ultimately creating one coherent spatiotemporal map.
Cross-attention Spatio-temporal Context Transformer for Semantic Segmentation of Historical Maps
Even though our application is on segmenting historical maps, we believe that the method can be transferred into other fields with similar problems like temporal sequences of satellite images.
Box2Poly: Memory-Efficient Polygon Prediction of Arbitrarily Shaped and Rotated Text
Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features.
Breathing New Life into 3D Assets with Generative Repainting
Diffusion-based text-to-image models ignited immense attention from the vision community, artists, and content creators.
Accuracy and Consistency of Space-based Vegetation Height Maps for Forest Dynamics in Alpine Terrain
Our results demonstrate that vegetation height maps computed from satellite imagery with deep learning are a valuable, complementary, cost-effective source of evidence to increase the temporal resolution for national forest assessments.
Towards accurate instance segmentation in large-scale LiDAR point clouds
Panoptic segmentation is the combination of semantic and instance segmentation: assign the points in a 3D point cloud to semantic categories and partition them into distinct object instances.
SF-FSDA: Source-Free Few-Shot Domain Adaptive Object Detection with Efficient Labeled Data Factory
Domain adaptive object detection aims to leverage the knowledge learned from a labeled source domain to improve the performance on an unlabeled target domain.
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.
Uncertainty Voting Ensemble for Imbalanced Deep Regression
For regression, recent work leverages the continuity of the distribution, while for classification, the trend has been to use ensemble methods, allowing some members to specialize in predictions for sparser regions.
U-TILISE: A Sequence-to-sequence Model for Cloud Removal in Optical Satellite Time Series
Satellite image time series in the optical and infrared spectrum suffer from frequent data gaps due to cloud cover, cloud shadows, and temporary sensor outages.
Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forward
Earth observation (EO) is a prime instrument for monitoring land and ocean processes, studying the dynamics at work, and taking the pulse of our planet.
Neural LiDAR Fields for Novel View Synthesis
We present Neural Fields for LiDAR (NFL), a method to optimise a neural field scene representation from LiDAR measurements, with the goal of synthesizing realistic LiDAR scans from novel viewpoints.
A Review of Panoptic Segmentation for Mobile Mapping Point Clouds
Moreover, a modular pipeline is set up to perform comprehensive, systematic experiments to assess the state of panoptic segmentation in the context of street mapping.
Ranked #2 on
Panoptic Segmentation
on S3DIS Area5
DEFLOW: Self-supervised 3D Motion Estimation of Debris Flow
Our model achieves state-of-the-art optical flow and depth estimation on our dataset, and fully automates the motion estimation for debris flows.
BiasBed - Rigorous Texture Bias Evaluation
With the release of BiasBed, we hope to foster a common understanding of consistent and meaningful comparisons, and consequently faster progress towards learning methods free of texture bias.
BITE: Beyond Priors for Improved Three-D Dog Pose Estimation
To that end, we exploit contact with the ground as a form of side information.
Context-aware multi-head self-attentional neural network model for next location prediction
Accurate activity location prediction is a crucial component of many mobility applications and is particularly required to develop personalized, sustainable transportation systems.
Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries
Instead, we formulate floorplan reconstruction as a single-stage structured prediction task: find a variable-size set of polygons, which in turn are variable-length sequences of ordered vertices.
BiasBed -- Rigorous Texture Bias Evaluation
With the release of BiasBed, we hope to foster a common understanding of consistent and meaningful comparisons, and consequently faster progress towards learning methods free of texture bias.
TetraDiffusion: Tetrahedral Diffusion Models for 3D Shape Generation
Probabilistic denoising diffusion models (DDMs) have set a new standard for 2D image generation.
Guided Depth Super-Resolution by Deep Anisotropic Diffusion
In this work, we propose a novel approach which combines guided anisotropic diffusion with a deep convolutional network and advances the state of the art for guided depth super-resolution.
Fine-grained Population Mapping from Coarse Census Counts and Open Geodata
Fine-grained population maps are needed in several domains, like urban planning, environmental monitoring, public health, and humanitarian operations.
TT-NF: Tensor Train Neural Fields
Learning neural fields has been an active topic in deep learning research, focusing, among other issues, on finding more compact and easy-to-fit representations.
T4DT: Tensorizing Time for Learning Temporal 3D Visual Data
We show that low-rank tensor compression is extremely compact to store and query time-varying signed distance functions.
Dynamic 3D Scene Analysis by Point Cloud Accumulation
Compared to state-of-the-art scene flow estimators, our proposed approach aims to align all 3D points in a common reference frame correctly accumulating the points on the individual objects.
tntorch: Tensor Network Learning with PyTorch
We present tntorch, a tensor learning framework that supports multiple decompositions (including Candecomp/Parafac, Tucker, and Tensor Train) under a unified interface.
Satellite-based high-resolution maps of cocoa planted area for Côte d'Ivoire and Ghana
C\^ote d'Ivoire and Ghana, the world's largest producers of cocoa, account for two thirds of the global cocoa production.
Recognition of Unseen Bird Species by Learning from Field Guides
Illustrations contained in field guides deliberately focus on discriminative properties of each species, and can serve as side information to transfer knowledge from seen to unseen bird species.
FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation
We show that the idea can be extended to uncertainty quantification: by modulating the network activations of a single deep network with FiLM, one obtains a model ensemble with high diversity, and consequently well-calibrated estimates of epistemic uncertainty, with low computational overhead in comparison.
Urban Change Forecasting from Satellite Images
In Stage 1, a U-Net backbone is pretrained within a Siamese network architecture that aims to solve a (building) change detection task.
Interactive Object Segmentation in 3D Point Clouds
We propose an interactive approach for 3D instance segmentation, where users can iteratively collaborate with a deep learning model to segment objects in a 3D point cloud directly.
Ranked #1 on
Interactive 3D Instance Segmentation -Trained on Scannet40 - Evaluated on Scannet40
on ScanNetV2
Image Segmentation
Interactive 3D Instance Segmentation -Trained on Scannet40 - Evaluated on Scannet40
+4
A high-resolution canopy height model of the Earth
The worldwide variation in vegetation height is fundamental to the global carbon cycle and central to the functioning of ecosystems and their biodiversity.
BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information
But, even with a better shape model, the problem of regressing dog shape from an image is still challenging because we lack paired images with 3D ground truth.
Learning Graph Regularisation for Guided Super-Resolution
With the decision to employ the source as a constraint rather than only as an input to the prediction, our method differs from state-of-the-art deep architectures for guided super-resolution, which produce targets that, when downsampled, will only approximately reproduce the source.
ImpliCity: City Modeling from Satellite Images with Deep Implicit Occupancy Fields
To make full use of the point cloud and the underlying images, we introduce ImpliCity, a neural representation of the 3D scene as an implicit, continuous occupancy field, driven by learned embeddings of the point cloud and a stereo pair of ortho-photos.
Country-wide Retrieval of Forest Structure From Optical and SAR Satellite Imagery With Deep Ensembles
To demonstrate scalability, we provide Norway-wide maps for the five forest structure variables.
3D Reconstruction from public webcams
It turns out that the task to reconstruct scene structure from webcam streams is very different from standard structure-from-motion (SfM), and conventional SfM pipelines fail.
Mapping Vulnerable Populations with AI
Building functions shall be retrieved by parsing social media data like for instance tweets, as well as ground-based imagery, to automatically identify different buildings functions and retrieve further information such as the number of building stories.
Learning a Joint Embedding of Multiple Satellite Sensors: A Case Study for Lake Ice Monitoring
Our application problem is the monitoring of lake ice on Alpine lakes.
High carbon stock mapping at large scale with optical satellite imagery and spaceborne LIDAR
The increasing demand for commodities is leading to changes in land use worldwide.
ResDepth: A Deep Residual Prior For 3D Reconstruction From High-resolution Satellite Images
Modern optical satellite sensors enable high-resolution stereo reconstruction from space.
Digital Taxonomist: Identifying Plant Species in Community Scientists' Photographs
Automatic identification of plant specimens from amateur photographs could improve species range maps, thus supporting ecosystems research as well as conservation efforts.
Cherry-Picking Gradients: Learning Low-Rank Embeddings of Visual Data via Differentiable Cross-Approximation
We propose an end-to-end trainable framework that processes large-scale visual data tensors by looking at a fraction of their entries only.
Mapping oil palm density at country scale: An active learning approach
To that end, we propose a new, active deep learning method to estimate oil palm density at large scale from Sentinel-2 satellite images, and apply it to generate complete maps for Malaysia and Indonesia.
Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
Visual re-localization means using a single image as input to estimate the camera's location and orientation relative to a pre-recorded environment.
Recent Ice Trends in Swiss Mountain Lakes: 20-year Analysis of MODIS Imagery
From the ice maps, we derive long-term LIP trends.
In the light of feature distributions: moment matching for Neural Style Transfer
Style transfer aims to render the content of a given image in the graphical/artistic style of another image.
Global canopy height regression and uncertainty estimation from GEDI LIDAR waveforms with deep ensembles
NASA's Global Ecosystem Dynamics Investigation (GEDI) is a key climate mission whose goal is to advance our understanding of the role of forests in the global carbon cycle.
PC2WF: 3D Wireframe Reconstruction from Raw Point Clouds
Next, the corners are linked with an exhaustive set of candidate edges, which is again pruned to obtain the final wireframe.
Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories
Thanks to recent advances in data-driven inertial odometry, such minimalistic input data can be acquired from the IMU readings of consumer-level smartphones, which allows for an effortless and scalable mapping of real-world indoor spaces.
Crop mapping from image time series: deep learning with multi-scale label hierarchies
The three-level label hierarchy is encoded in a convolutional, recurrent neural network (convRNN), such that for each pixel the model predicts three labels at different level of granularity.
Crop Classification under Varying Cloud Cover with Neural Ordinary Differential Equations
We propose to use neural ordinary differential equations (NODEs) in combination with RNNs to classify crop types in irregularly spaced image sequences.
PREDATOR: Registration of 3D Point Clouds with Low Overlap
We introduce PREDATOR, a model for pairwise point-cloud registration with deep attention to the overlap region.
Ice Monitoring in Swiss Lakes from Optical Satellites and Webcams using Machine Learning
and generalisation scores of 71% (approx.)
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.
Deep Active Learning in Remote Sensing for data efficient Change Detection
We investigate active learning in the context of deep neural network models for change detection and map updating.
KAPLAN: A 3D Point Descriptor for Shape Completion
We present a novel 3D shape completion method that operates directly on unstructured point clouds, thus avoiding resource-intensive data structures like voxel grids.
From two rolling shutters to one global shutter
Most consumer cameras are equipped with electronic rolling shutter, leading to image distortions when the camera moves during image capture.
Photometric Multi-View Mesh Refinement for High-Resolution Satellite Images
Modern high-resolution satellite sensors collect optical imagery with ground sampling distances (GSDs) of 30-50cm, which has sparked a renewed interest in photogrammetric 3D surface reconstruction from satellite data.
Minimal Rolling Shutter Absolute Pose with Unknown Focal Length and Radial Distortion
The internal geometry of most modern consumer cameras is not adequately described by the perspective projection.
Fine-grained Species Recognition with Privileged Pooling: Better Sample Efficiency Through Supervised Attention
We propose a scheme for supervised image classification that uses privileged information, in the form of keypoint annotations for the training data, to learn strong models from small and/or biased training sets.
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
Reconstruction of 3D flight trajectories from ad-hoc camera networks
We present a method to reconstruct the 3D trajectory of an airborne robotic system only from videos recorded with cameras that are unsynchronized, may feature rolling shutter distortion, and whose viewpoints are unknown.
Indoor Scene Recognition in 3D
Moreover, we advocate multi-task learning as a way of improving scene recognition, building on the fact that the scene type is highly correlated with the objects in the scene, and therefore with its semantic segmentation into different object classes.
Lake Ice Monitoring with Webcams and Crowd-Sourced Images
On average, it achieves intersection-over-union (IoU) values of ~71% across different cameras and ~69% across different winters, greatly outperforming prior work.
Change detection for remote sensing images
Image Segmentation
+4
Photi-LakeIce Dataset
On average, it achieves intersection-over-union (IoU) values of ~71% across different cameras and ~69% across different winters, greatly outperforming prior work.
Change detection for remote sensing images
Image Segmentation
+4
Lake Ice Detection from Sentinel-1 SAR with Deep Learning
Lake ice, as part of the Essential Climate Variable (ECV) lakes, is an important indicator to monitor climate change and global warming.
ResDepth: Learned Residual Stereo Reconstruction
We propose an embarrassingly simple but very effective scheme for high-quality dense stereo reconstruction: (i) generate an approximate reconstruction with your favourite stereo matcher; (ii) rewarp the input images with that approximate model; (iii) with the initial reconstruction and the warped images as input, train a deep network to enhance the reconstruction by regressing a residual correction; and (iv) if desired, iterate the refinement with the new, improved reconstruction.
Learned Multi-View Texture Super-Resolution
We present a super-resolution method capable of creating a high-resolution texture map for a virtual 3D object from a set of lower-resolution images of that object.
Chained Representation Cycling: Learning to Estimate 3D Human Pose and Shape by Cycling Between Representations
The goal of many computer vision systems is to transform image pixels into 3D representations.
Self-supervised Object Motion and Depth Estimation from Video
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video.
Gating Revisited: Deep Multi-layer RNNs That Can Be Trained
We propose a new STAckable Recurrent cell (STAR) for recurrent neural networks (RNNs), which has fewer parameters than widely used LSTM and GRU while being more robust against vanishing or exploding gradients.
From Google Maps to a Fine-Grained Catalog of Street trees
We believe this is the first work to exploit publicly available image data for fine-grained tree mapping at city-scale, respectively over many thousands of trees.
Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
In particular, we propose a robust training objective that is invariant to changes in depth range and scale, advocate the use of principled multi-objective learning to combine data from different sources, and highlight the importance of pretraining encoders on auxiliary tasks.
Ranked #2 on
Depth Estimation
on eBDtheque
CVPR19 Tracking and Detection Challenge: How crowded can it get?
Standardized benchmarks are crucial for the majority of computer vision applications.
Country-wide high-resolution vegetation height mapping with Sentinel-2
Sentinel-2 multi-spectral images collected over periods of several months were used to estimate vegetation height for Gabon and Switzerland.
Guided Super-Resolution as Pixel-to-Pixel Transformation
Guided super-resolution is a unifying framework for several computer vision tasks where the inputs are a low-resolution source image of some target quantity (e. g., perspective depth acquired with a time-of-flight camera) and a high-resolution guide image from a different domain (e. g., a grey-scale image from a conventional camera); and the target output is a high-resolution version of the source (in our example, a high-res depth map).
Visual recognition in the wild by sampling deep similarity functions
However, a robot moving in the wild, i. e., in an environment that is not known at the time the recognition system is trained, will often face \emph{domain shift}: the training data cannot be assumed to exhaustively cover all the within-class variability that will be encountered in the test data.
Practical optimal registration of terrestrial LiDAR scan pairs
Point cloud registration is a fundamental problem in 3D scanning.
3D Fluid Flow Estimation with Integrated Particle Reconstruction
We show, for the first time, how to jointly reconstruct both the individual tracer particles and a dense 3D fluid motion field from the image data, using an integrated energy minimization.
Variational 3D-PIV with Sparse Descriptors
We propose a new method for iterative particle reconstruction (IPR), in which the locations and intensities of all particles are inferred in one joint energy minimization.
Super-resolution of Sentinel-2 images: Learning a globally applicable deep neural network
The aim of this research is to super-resolve the lower-resolution (20 m and 60 m Ground Sampling Distance - GSD) bands to 10 m GSD, so as to obtain a complete data cube at the maximal sensor resolution.
Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in Convolutional Networks
While CNNs naturally lend themselves to densely sampled data, and sophisticated implementations are available, they lack the ability to efficiently process sparse data.
Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR Data
Very High Spatial Resolution (VHSR) large-scale SAR image databases are still an unresolved issue in the Remote Sensing field.
Semantic 3D Reconstruction with Finite Element Bases
We propose a novel framework for the discretisation of multi-label problems on arbitrary, continuous domains.
Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations
Here, we propose a variational method for 3D fluid flow estimation from multi-view data.
Learning Aerial Image Segmentation from Online Maps
We adapt a state-of-the-art CNN architecture for semantic segmentation of buildings and roads in aerial images, and compare its performance when using different training data sets, ranging from manually labeled, pixel-accurate ground truth of the same city to automatic training data derived from OpenStreetMap data from distant locations.
A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos
Motivated by the limitations of existing multi-view stereo benchmarks, we present a novel dataset for this task.
Semantically Informed Multiview Surface Refinement
We present a method to jointly refine the geometry and semantic segmentation of 3D surface meshes.
Semantic3D.net: A new Large-scale Point Cloud Classification Benchmark
With the massive data set presented in this paper, we aim at closing this data gap to help unleash the full potential of deep learning methods for 3D labelling tasks.
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.
Learned Spectral Super-Resolution
We describe a novel method for blind, single-image spectral super-resolution.
Learned Multi-Patch Similarity
Estimating a depth map from multiple views of a scene is a fundamental task in computer vision.
Classification With an Edge: Improving Semantic Image Segmentation with Boundary Detection
We present an end-to-end trainable deep convolutional neural network (DCNN) for semantic segmentation with built-in awareness of semantically meaningful boundaries.
Tracking with multi-level features
We present a novel formulation of the multiple object tracking problem which integrates low and mid-level features.
Contour Detection in Unstructured 3D Point Clouds
The contour scores serve as a basis to construct an overcomplete graph of candidate contours.
Large-Scale Location Recognition and the Geometric Burstiness Problem
Visual location recognition is the task of determining the place depicted in a query image from a given database of geo-tagged images.
Cataloging Public Objects Using Aerial and Street-Level Images - Urban Trees
The main technical challenge is combining test time information from multiple views of each geographic location (e. g., aerial and street views).
Large-Scale Semantic 3D Reconstruction: An Adaptive Multi-Resolution Model for Multi-Class Volumetric Labeling
We propose an adaptive multi-resolution formulation of semantic 3D reconstruction.
Just Look at the Image: Viewpoint-Specific Surface Normal Prediction for Improved Multi-View Reconstruction
By training from known points in the same image, the prediction is specifically tailored to the materials and lighting conditions of the particular scene, as well as to the precise camera viewpoint.
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.
Online Multi-Target Tracking Using Recurrent Neural Networks
Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking.
Fast semantic segmentation of 3d point clouds with strongly varying density
We describe an effective and efficient method for point-wise semantic classification of 3D point clouds.
Ranked #17 on
Semantic Segmentation
on Semantic3D
MOT16: A Benchmark for Multi-Object Tracking
Recently, a new benchmark for Multiple Object Tracking, MOTChallenge, was launched with the goal of collecting existing and new data and creating a framework for the standardized evaluation of multiple object tracking methods.
Hyperspectral Super-Resolution by Coupled Spectral Unmixing
Hyperspectral super-resolution addresses this problem, by fusing a low-resolution hyperspectral image and a conventional high-resolution image into a product of both high spatial and high spectral resolution.
Massively Parallel Multiview Stereopsis by Surface Normal Diffusion
We present a new, massively parallel method for high-quality multiview matching.
Ranked #23 on
3D Reconstruction
on DTU
Joint Tracking and Segmentation of Multiple Targets
Tracking-by-detection has proven to be the most successful strategy to address the task of tracking multiple targets in unconstrained scenarios.
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.
Towards Scene Understanding with Detailed 3D Object Representations
An object class - in our case cars - is modeled as a deformable 3D wireframe, which enables fine-grained modeling at the level of individual vertices and faces.
Are Cars Just 3D Boxes? - Jointly Estimating the 3D Shape of Multiple Objects
Current systems for scene understanding typically represent objects as 2D or 3D bounding boxes.
Predicting Matchability
The initial steps of many computer vision algorithms are interest point extraction and matching.
A Higher-Order CRF Model for Road Network Extraction
The aim of this work is to extract the road network from aerial images.
Detection- and Trajectory-Level Exclusion in Multiple Object Tracking
When tracking multiple targets in crowded scenarios, modeling mutual exclusion between distinct targets becomes important at two levels: (1) in data association, each target observation should support at most one trajectory and each trajectory should be assigned at most one observation per frame; (2) in trajectory estimation, two trajectories should remain spatially separated at all times to avoid collisions.
Explicit Occlusion Modeling for 3D Object Class Representations
In this paper, we tackle the challenge of modeling occlusion in the context of a 3D geometric object class model that is capable of fine-grained, part-level 3D object reconstruction.
