Search Results for author: Volkan Isler

Found 35 papers, 3 papers with code

Jointly learning visual motion and confidence from local patches in event cameras

no code implementations ECCV 2020 Daniel R. Kepple, Daewon Lee, Colin Prepsius, Volkan Isler, Il Memming Park, Daniel D. Lee

In the task of recovering pan-tilt ego velocities from events, we show that each individual confident local prediction of our network can be expected to be as accurate as state of the art optimization approaches which utilize the full image.

Motion Segmentation

FineControlNet: Fine-level Text Control for Image Generation with Spatially Aligned Text Control Injection

no code implementations14 Dec 2023 Hongsuk Choi, Isaac Kasahara, Selim Engin, Moritz Graule, Nikhil Chavan-Dafle, Volkan Isler

While ControlNet provides control over the geometric form of the instances in the generated image, it lacks the capability to dictate the visual appearance of each instance.

Image Generation

VioLA: Aligning Videos to 2D LiDAR Scans

no code implementations8 Nov 2023 Jun-Jee Chao, Selim Engin, Nikhil Chavan-Dafle, Bhoram Lee, Volkan Isler

We study the problem of aligning a video that captures a local portion of an environment to the 2D LiDAR scan of the entire environment.

Depth Completion Image Inpainting

HIO-SDF: Hierarchical Incremental Online Signed Distance Fields

no code implementations14 Oct 2023 Vasileios Vasilopoulos, Suveer Garg, Jinwook Huh, Bhoram Lee, Volkan Isler

HIO-SDF combines the advantages of these representations using a hierarchical approach which employs a coarse voxel grid that captures the observed parts of the environment together with high-resolution local information to train a neural network.

HandNeRF: Learning to Reconstruct Hand-Object Interaction Scene from a Single RGB Image

no code implementations14 Sep 2023 Hongsuk Choi, Nikhil Chavan-Dafle, Jiacheng Yuan, Volkan Isler, Hyunsoo Park

The inference as well as training-data generation for 3D hand-object scene reconstruction is challenging due to the depth ambiguity of a single image and occlusions by the hand and object.

Motion Planning Object +1

RIC: Rotate-Inpaint-Complete for Generalizable Scene Reconstruction

no code implementations21 Jul 2023 Isaac Kasahara, Shubham Agrawal, Selim Engin, Nikhil Chavan-Dafle, Shuran Song, Volkan Isler

General scene reconstruction refers to the task of estimating the full 3D geometry and texture of a scene containing previously unseen objects.

Autonomous Navigation

Real-time Simultaneous Multi-Object 3D Shape Reconstruction, 6DoF Pose Estimation and Dense Grasp Prediction

1 code implementation16 May 2023 Shubham Agrawal, Nikhil Chavan-Dafle, Isaac Kasahara, Selim Engin, Jinwook Huh, Volkan Isler

In this paper, we present a novel method to provide this geometric and semantic information of all objects in the scene as well as feasible grasps on those objects simultaneously.

3D Shape Reconstruction Object +1

EV-Catcher: High-Speed Object Catching Using Low-latency Event-based Neural Networks

no code implementations14 Apr 2023 ZiYun Wang, Fernando Cladera Ojeda, Anthony Bisulco, Daewon Lee, Camillo J. Taylor, Kostas Daniilidis, M. Ani Hsieh, Daniel D. Lee, Volkan Isler

Event-based sensors have recently drawn increasing interest in robotic perception due to their lower latency, higher dynamic range, and lower bandwidth requirements compared to standard CMOS-based imagers.

3D Surface Reconstruction in the Wild by Deforming Shape Priors from Synthetic Data

no code implementations24 Feb 2023 Nicolai Häni, Jun-Jee Chao, Volkan Isler

In this work, we present a new method for joint category-specific 3D reconstruction and object pose estimation from a single image.

3D Reconstruction Object +2

Category-Level Global Camera Pose Estimation with Multi-Hypothesis Point Cloud Correspondences

no code implementations28 Sep 2022 Jun-Jee Chao, Selim Engin, Nicolai Häni, Volkan Isler

This paper proposes an optimization method that retains all possible correspondences for each keypoint when matching a partial point cloud to a complete point cloud.

Camera Pose Estimation Point Cloud Registration +1

Self-supervised Wide Baseline Visual Servoing via 3D Equivariance

no code implementations12 Sep 2022 Jinwook Huh, Jungseok Hong, Suveer Garg, Hyun Soo Park, Volkan Isler

Existing approaches that regress absolute camera pose with respect to an object require 3D ground truth data of the object in the forms of 3D bounding boxes or meshes.

Object

Apple Counting using Convolutional Neural Networks

no code implementations24 Aug 2022 Nicolai Häni, Pravakar Roy, Volkan Isler

Estimating accurate and reliable fruit and vegetable counts from images in real-world settings, such as orchards, is a challenging problem that has received significant recent attention.

Multi-class Classification

PoseKernelLifter: Metric Lifting of 3D Human Pose using Sound

no code implementations CVPR 2022 Zhijian Yang, Xiaoran Fan, Volkan Isler, Hyun Soo Park

Based on this insight, we introduce a time-invariant transfer function called pose kernel -- the impulse response of audio signals induced by the body pose.

regression

Learning Continuous Cost-to-Go Functions for Non-holonomic Systems

no code implementations20 Mar 2021 Jinwook Huh, Daniel D. Lee, Volkan Isler

In this work, we show that uniform sampling fails for non-holonomic systems.

Ellipse Regression with Predicted Uncertainties for Accurate Multi-View 3D Object Estimation

no code implementations27 Dec 2020 Wenbo Dong, Volkan Isler

We present a novel ellipse regression loss which can learn the offset parameters with their uncertainties and quantify the overall geometric quality of detection for each ellipse.

Object object-detection +2

Cost-to-Go Function Generating Networks for High Dimensional Motion Planning

no code implementations10 Dec 2020 Jinwook Huh, Volkan Isler, Daniel D. Lee

The c2g-HOF architecture consists of a cost-to-go function over the configuration space represented as a neural network (c2g-network) as well as a Higher Order Function (HOF) network which outputs the weights of the c2g-network for a given input workspace.

Motion Planning Vocal Bursts Intensity Prediction

Geodesic-HOF: 3D Reconstruction Without Cutting Corners

no code implementations14 Jun 2020 Ziyun Wang, Eric A. Mitchell, Volkan Isler, Daniel D. Lee

To address this issue, we propose learning an image-conditioned mapping function from a canonical sampling domain to a high dimensional space where the Euclidean distance is equal to the geodesic distance on the object.

3D Object Reconstruction 3D Reconstruction +2

Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction

no code implementations3 Mar 2020 Tarik Tosun, Daniel Yang, Ben Eisner, Volkan Isler, Daniel Lee

We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network.

Robotics

Ellipse R-CNN: Learning to Infer Elliptical Object from Clustering and Occlusion

no code implementations30 Jan 2020 Wenbo Dong, Pravakar Roy, Cheng Peng, Volkan Isler

We first propose a robust and compact ellipse regression based on the Mask R-CNN architecture for elliptical object detection.

Clustering object-detection +3

Surface HOF: Surface Reconstruction from a Single Image Using Higher Order Function Networks

no code implementations18 Dec 2019 Ziyun Wang, Volkan Isler, Daniel D. Lee

Our approach is to learn a Higher Order Function (HOF) which takes an image of an object as input and generates a mapping function.

3D Reconstruction Image Reconstruction +1

QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning

no code implementations13 Oct 2019 Nof Abuzainab, Tugba Erpek, Kemal Davaslioglu, Yalin E. Sagduyu, Yi Shi, Sharon J. Mackey, Mitesh Patel, Frank Panettieri, Muhammad A. Qureshi, Volkan Isler, Aylin Yener

The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks.

reinforcement-learning Reinforcement Learning (RL)

Higher Order Function Networks for View Planning and Multi-View Reconstruction

no code implementations4 Oct 2019 Selim Engin, Eric Mitchell, Daewon Lee, Volkan Isler, Daniel D. Lee

In contrast to offline methods which require a 3D model of the object as input or online methods which rely on only local measurements, our method uses a neural network which encodes shape information for a large number of objects.

3D Reconstruction Object

MinneApple: A Benchmark Dataset for Apple Detection and Segmentation

5 code implementations13 Sep 2019 Nicolai Häni, Pravakar Roy, Volkan Isler

The fruits are labeled using polygonal masks for each object instance to aid in precise object detection, localization, and segmentation.

Object object-detection +2

Higher-Order Function Networks for Learning Composable 3D Object Representations

no code implementations ICLR 2020 Eric Mitchell, Selim Engin, Volkan Isler, Daniel D. Lee

We present a new approach to 3D object representation where a neural network encodes the geometry of an object directly into the weights and biases of a second 'mapping' network.

Decoder Motion Planning +1

Semantics-Aware Image to Image Translation and Domain Transfer

no code implementations3 Apr 2019 Pravakar Roy, Nicolai Häni, Jun-Jee Chao, Volkan Isler

Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain.

Decoder Domain Adaptation +3

A Comparative Study of Fruit Detection and Counting Methods for Yield Mapping in Apple Orchards

no code implementations22 Oct 2018 Nicolai Häni, Pravakar Roy, Volkan Isler

We present new methods for apple detection and counting based on recent deep learning approaches and compare them with state-of-the-art results based on classical methods.

Yield Mapping In Apple Orchards

Semantic Mapping for Orchard Environments by Merging Two-Sides Reconstructions of Tree Rows

no code implementations31 Aug 2018 Wenbo Dong, Pravakar Roy, Volkan Isler

Our first main contribution in this paper is a novel method that utilizes global features and semantic information to obtain an initial solution aligning the two sides.

Robotics

Adaptive View Planning for Aerial 3D Reconstruction

no code implementations1 May 2018 Cheng Peng, Volkan Isler

We then present (i)~a method that builds a view manifold for view selection, and (ii) an algorithm to select a sparse set of views.

3D Reconstruction

Tree Morphology for Phenotyping from Semantics-Based Mapping in Orchard Environments

no code implementations16 Apr 2018 Wenbo Dong, Volkan Isler

Researchers often rely on manual measurements which may not be accurate for example when measuring tree volume.

View Selection with Geometric Uncertainty Modeling

no code implementations31 Mar 2017 Cheng Peng, Volkan Isler

Consider a world point $g \in \mathcal{G}$ and its worst case reconstruction uncertainty $\varepsilon(g,\mathcal{S})$ obtained by merging \emph{all} possible views of $g$ chosen from $\mathcal{S}$.

3D Reconstruction Simultaneous Localization and Mapping

A Novel Method for the Extrinsic Calibration of a 2D Laser Rangefinder and a Camera

no code implementations14 Mar 2016 Wenbo Dong, Volkan Isler

We present a novel method for extrinsically calibrating a camera and a 2D Laser Rangefinder (LRF) whose beams are invisible from the camera image.

Cannot find the paper you are looking for? You can Submit a new open access paper.