Header logo is


2015


Exploiting Object Similarity in 3D Reconstruction
Exploiting Object Similarity in 3D Reconstruction

Zhou, C., Güney, F., Wang, Y., Geiger, A.

In International Conference on Computer Vision (ICCV), December 2015 (inproceedings)

Abstract
Despite recent progress, reconstructing outdoor scenes in 3D from movable platforms remains a highly difficult endeavor. Challenges include low frame rates, occlusions, large distortions and difficult lighting conditions. In this paper, we leverage the fact that the larger the reconstructed area, the more likely objects of similar type and shape will occur in the scene. This is particularly true for outdoor scenes where buildings and vehicles often suffer from missing texture or reflections, but share similarity in 3D shape. We take advantage of this shape similarity by locating objects using detectors and jointly reconstructing them while learning a volumetric model of their shape. This allows us to reduce noise while completing missing surfaces as objects of similar shape benefit from all observations for the respective category. We evaluate our approach with respect to LIDAR ground truth on a novel challenging suburban dataset and show its advantages over the state-of-the-art.

avg ps

pdf suppmat [BibTex]

2015


pdf suppmat [BibTex]


FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation
FollowMe: Efficient Online Min-Cost Flow Tracking with Bounded Memory and Computation

Lenz, P., Geiger, A., Urtasun, R.

In International Conference on Computer Vision (ICCV), International Conference on Computer Vision (ICCV), December 2015 (inproceedings)

Abstract
One of the most popular approaches to multi-target tracking is tracking-by-detection. Current min-cost flow algorithms which solve the data association problem optimally have three main drawbacks: they are computationally expensive, they assume that the whole video is given as a batch, and they scale badly in memory and computation with the length of the video sequence. In this paper, we address each of these issues, resulting in a computationally and memory-bounded solution. First, we introduce a dynamic version of the successive shortest-path algorithm which solves the data association problem optimally while reusing computation, resulting in faster inference than standard solvers. Second, we address the optimal solution to the data association problem when dealing with an incoming stream of data (i.e., online setting). Finally, we present our main contribution which is an approximate online solution with bounded memory and computation which is capable of handling videos of arbitrary length while performing tracking in real time. We demonstrate the effectiveness of our algorithms on the KITTI and PETS2009 benchmarks and show state-of-the-art performance, while being significantly faster than existing solvers.

avg ps

pdf suppmat video project [BibTex]

pdf suppmat video project [BibTex]


Towards Probabilistic Volumetric Reconstruction using Ray Potentials
Towards Probabilistic Volumetric Reconstruction using Ray Potentials

(Best Paper Award)

Ulusoy, A. O., Geiger, A., Black, M. J.

In 3D Vision (3DV), 2015 3rd International Conference on, pages: 10-18, Lyon, October 2015 (inproceedings)

Abstract
This paper presents a novel probabilistic foundation for volumetric 3-d reconstruction. We formulate the problem as inference in a Markov random field, which accurately captures the dependencies between the occupancy and appearance of each voxel, given all input images. Our main contribution is an approximate highly parallelized discrete-continuous inference algorithm to compute the marginal distributions of each voxel's occupancy and appearance. In contrast to the MAP solution, marginals encode the underlying uncertainty and ambiguity in the reconstruction. Moreover, the proposed algorithm allows for a Bayes optimal prediction with respect to a natural reconstruction loss. We compare our method to two state-of-the-art volumetric reconstruction algorithms on three challenging aerial datasets with LIDAR ground truth. Our experiments demonstrate that the proposed algorithm compares favorably in terms of reconstruction accuracy and the ability to expose reconstruction uncertainty.

avg ps

code YouTube pdf suppmat DOI Project Page [BibTex]

code YouTube pdf suppmat DOI Project Page [BibTex]


Displets: Resolving Stereo Ambiguities using Object Knowledge
Displets: Resolving Stereo Ambiguities using Object Knowledge

Güney, F., Geiger, A.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015, pages: 4165-4175, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2015 (inproceedings)

Abstract
Stereo techniques have witnessed tremendous progress over the last decades, yet some aspects of the problem still remain challenging today. Striking examples are reflecting and textureless surfaces which cannot easily be recovered using traditional local regularizers. In this paper, we therefore propose to regularize over larger distances using object-category specific disparity proposals (displets) which we sample using inverse graphics techniques based on a sparse disparity estimate and a semantic segmentation of the image. The proposed displets encode the fact that objects of certain categories are not arbitrarily shaped but typically exhibit regular structures. We integrate them as non-local regularizer for the challenging object class 'car' into a superpixel based CRF framework and demonstrate its benefits on the KITTI stereo evaluation.

avg ps

pdf abstract suppmat [BibTex]

pdf abstract suppmat [BibTex]


Object Scene Flow for Autonomous Vehicles
Object Scene Flow for Autonomous Vehicles

Menze, M., Geiger, A.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2015, pages: 3061-3070, IEEE, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), June 2015 (inproceedings)

Abstract
This paper proposes a novel model and dataset for 3D scene flow estimation with an application to autonomous driving. Taking advantage of the fact that outdoor scenes often decompose into a small number of independently moving objects, we represent each element in the scene by its rigid motion parameters and each superpixel by a 3D plane as well as an index to the corresponding object. This minimal representation increases robustness and leads to a discrete-continuous CRF where the data term decomposes into pairwise potentials between superpixels and objects. Moreover, our model intrinsically segments the scene into its constituting dynamic components. We demonstrate the performance of our model on existing benchmarks as well as a novel realistic dataset with scene flow ground truth. We obtain this dataset by annotating 400 dynamic scenes from the KITTI raw data collection using detailed 3D CAD models for all vehicles in motion. Our experiments also reveal novel challenges which can't be handled by existing methods.

avg ps

pdf abstract suppmat DOI [BibTex]

pdf abstract suppmat DOI [BibTex]


no image
Coarsening in fluid phase transitions

Das, S., Roy, S., Midya, J.

Comptes Rendus Physique, 16(3):303-315, April 2015 (article)

Abstract
We review the understanding of the kinetics of fluid phase separation in various space dimensions. Morphological differences, percolating or disconnected domains, based on overall composition in a binary liquid or on density in a vapor–liquid system, are discussed. Depending upon the morphology, various possible mechanisms for domain growth are pointed out and discussions of corresponding theoretical predictions are provided. On the computational front, useful models and simulation methodologies are presented. Theoretically predicted growth laws have been tested via molecular dynamics simulations of vapor–liquid transitions. In the case of a disconnected structure, the mechanism has been confirmed directly.

icm

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Structures of simple liquids in contact with nanosculptured surfaces

Singh, S. L., Schimmele, L., Dietrich, S.

Physical Review E, 91(3), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Line contribution to the critical Casimir force between a homogeneous and a chemically stepped surface

Parisen Toldin, F., Tröndle, M., Dietrich, S.

Journal of Physics: Condensed Matter, 27(21), IOP Publishing, Bristol, UK, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Self-propulsion of a catalytically active particle near a planar wall: from reflection to sliding and hovering

Uspal, W. E., Popescu, M. N., Dietrich, S., Tasinkevych, M.

Soft Matter, 11(3):434-438, Royal Society of Chemistry, Cambridge, UK, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
A size dependent evaluation of the cytotoxicity and uptake of nanographene oxide

Mendes, R. G., Koch, B., Bachmatiuk, A., Ma, X., Sanchez, S., Damm, C., Schmidt, O. G., Gemming, T., Eckert, J., Rümmeli, M. H.

Journal of Materials Chemistry B, 3(12):2522-2529, Royal Society of Chemistry, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
A bio-catalytically driven Janus mesoporous silica cluster motor with magnetic guidance

Ma, X., Sanchez, S.

Chemical Communications, 51(25):5467-5470, Royal Society of Chemistry, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Sperm Dynamics in Tubular Confinement

Magdanz, V., Koch, B., Sanchez, S., Schmidt, O. G.

Small, 11(7):781-785, Wiley Online Library, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Chromatic patchy particles: Effects of specific interactions on liquid structure

Vasilyev, O., Klumov, B. A., Tkachenko, A. V.

Physical Review E, 92(1), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Monte Carlo study of anisotropic scaling generated by disorder

Vasilyev, O., Berche, B., Dudka, M., Holovatch, Y.

Physical Review E, 92(4), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Fluctuations and diffusion in sheared athermal suspensions of deformable particles

Gross, M., Krüger, T., Varnik, F.

EPL, 108(6), IoPP, Bristol, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Enzyme-Powered Hollow Mesoporous Janus Nanomotors

Ma, Xing, Jannasch, Anita, Albrecht, Urban-Raphael, Hahn, Kersten, Miguel-Lopéz, Albert, Schäfer, Erik, Sanchez, Samuel

Nano Letters, 15(10):7043-7050, American Chemical Society, Washington, DC, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Interaction between colloidal particles on an oil\textendashwater interface in dilute and dense phases

Parolini, L., Cicuta, A. D. P., Law, A. D., Maestro, A., Buzza, M. A.

Journal of Physics: Condensed Matter, 27(19), IOP Publishing, Bristol, UK, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Anomalous Magnetotransport in Disordered Structures: Classical Edge-State Percolation

Schirmacher, Walter, Fuchs, Benedikt, Höfling, Felix, Franosch, Thomas

Physical Review Letters, 115, American Physical Society, Woodbury, N.Y., 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


Joint 3D Object and Layout Inference from a single RGB-D Image
Joint 3D Object and Layout Inference from a single RGB-D Image

(Best Paper Award)

Geiger, A., Wang, C.

In German Conference on Pattern Recognition (GCPR), 9358, pages: 183-195, Lecture Notes in Computer Science, Springer International Publishing, 2015 (inproceedings)

Abstract
Inferring 3D objects and the layout of indoor scenes from a single RGB-D image captured with a Kinect camera is a challenging task. Towards this goal, we propose a high-order graphical model and jointly reason about the layout, objects and superpixels in the image. In contrast to existing holistic approaches, our model leverages detailed 3D geometry using inverse graphics and explicitly enforces occlusion and visibility constraints for respecting scene properties and projective geometry. We cast the task as MAP inference in a factor graph and solve it efficiently using message passing. We evaluate our method with respect to several baselines on the challenging NYUv2 indoor dataset using 21 object categories. Our experiments demonstrate that the proposed method is able to infer scenes with a large degree of clutter and occlusions.

avg ps

pdf suppmat video project DOI [BibTex]

pdf suppmat video project DOI [BibTex]


no image
Precise Localization and Control of Catalytic Janus Micromotors using Weak Magnetic Fields

Khalil, I. S., Magdanz, V., Sanchez, S., Schmidt, O. G., Misra, S.

International Journal of Advanced Robotic Systems, 12, InTech, Rijeka, Croatia, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Nano-photocatalysts in microfluidics, energy conversion and environmental applications

Parmar, J., Jang, S., Soler, L., Kim, D., Sánchez, S.

Lab on a Chip, 15(11):2352-2356, Royal Society of Chemistry, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Static dielectric properties of dense ionic fluids

Zarubin, G., Bier, M.

The Journal of Chemical Physics, 142(18), American Institute of Physics, Woodbury, N.Y., 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Chemically Powered Micro-and Nanomotors

Sánchez, S., Soler, L., Katuri, J.

Angewandte Chemie, International Edition, 54(5):1414-1444, Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim, 2015 (article)

icm

[BibTex]

[BibTex]


no image
Convergence of large-deviation estimators

Rohwer, C. M., Angeletti, F., Touchette, H.

Physical Review E, 92(5), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Geometrically Tuned Channel Permeability

Malgaretti, P., Pagonabarraga, I., Rubi, J. M.

Macromolecular Symposia, 357(1):178-188, WILEY-VCH Verlag GmbH, Weinheim, Fed. Rep. of Germany, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Critical Casimir forces between planar and crenellated surfaces

Troendle, M., Harnau, L., Dietrich, S.

Journal of Physics: Condensed Matter, 27(21), IOP Publishing, Bristol, UK, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Theory of rheology in confinement

Aerov, A. A., Krüger, M.

Physical Review E, 92(4), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Implications of interface conventions for morphometric thermodynamics

Reindl, A., Bier, M., Dietrich, S.

Physical Review E, 91(2), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Linked topological colloids in a nematic host

Martinez, A., Hermosillo, L., Tasinkevych, M., Smalyukh, I. I.

Proceedings of the National Academy of Sciences of the United States of America, 112(15):4546-4551, National Academy of Sciences, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Colloidal spirals in nematic liquid crystals

Senyuk, B., Pandey, M.B., Liu, Q., Tasinkevych, M., Smalyukh, I. I.

Soft Matter, 11, pages: 8758-8767, Royal Society of Chemistry, Cambridge, UK, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


Discrete Optimization for Optical Flow
Discrete Optimization for Optical Flow

Menze, M., Heipke, C., Geiger, A.

In German Conference on Pattern Recognition (GCPR), 9358, pages: 16-28, Springer International Publishing, 2015 (inproceedings)

Abstract
We propose to look at large-displacement optical flow from a discrete point of view. Motivated by the observation that sub-pixel accuracy is easily obtained given pixel-accurate optical flow, we conjecture that computing the integral part is the hardest piece of the problem. Consequently, we formulate optical flow estimation as a discrete inference problem in a conditional random field, followed by sub-pixel refinement. Naive discretization of the 2D flow space, however, is intractable due to the resulting size of the label set. In this paper, we therefore investigate three different strategies, each able to reduce computation and memory demands by several orders of magnitude. Their combination allows us to estimate large-displacement optical flow both accurately and efficiently and demonstrates the potential of discrete optimization for optical flow. We obtain state-of-the-art performance on MPI Sintel and KITTI.

avg ps

pdf suppmat project DOI [BibTex]

pdf suppmat project DOI [BibTex]


no image
Rheotaxis of spherical active particles near a planar wall

Uspal, W. E., Popescu, M. N., Dietrich, S., Tasinkevych, M.

Soft Matter, 11(33):6613-6632, Royal Society of Chemistry, Cambridge, UK, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Applications of three-dimensional (3D) printing for microswimmers and bio-hybrid robotics

Stanton, M. M., Trichet-Paredes, C., Sanchez, S.

Lab on a Chip, 15(7):1634-1637, Royal Society of Chemistry, Cambridge, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Linear and nonlinear magnetic properties of ferrofluids

Szalai, I., Nagy, S., Dietrich, S.

Physical Review E, 92(4), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Microfluidic-Assisted Fabrication of Flexible and Location Traceable Organo-Motor

Seo, K. D., Kwak, B. K., Sanchez, S., Kim, D. S.

IEEE Transactions on Nanobioscience, 14(3):298-304, IEEE, New York, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Tracer diffusion of hard-sphere binary mixtures under nano-confinement

Marconi, U., Malgaretti, P., Pagonabarraga, I.

The Journal of Chemical Physics, 143(18), American Institute of Physics, Woodbury, N.Y., 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Fluctuating multicomponent lattice Boltzmann model

Belardinelli, D., Sbragaglia, M., Biferale, L., Gross, M., Varnik, F.

Physical Review E, 91(2), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Phase diagram of fluid phases in He3\textminusHe4 mixtures

Farahmand Bafi, N., Maciolek, A., Dietrich, S.

Physical Review E, 91(2), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Three-body critical Casimir forces

Gomes de Mattos, T., Harnau, L., Dietrich, S.

Physical Review E, 91(4), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Thermal and structural properties of ionic fluids

Bartsch, H., Dannenmann, O., Bier, M.

Physical Review E, 91(4), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Fluctuational electrodynamics for nonlinear media

Soo, H.

Universität Stuttgart, Stuttgart, 2015 (mastersthesis)

icm

[BibTex]

[BibTex]


no image
Micro- and Nanomachines
IEEE Transactions on Nanobioscience, 14, pages: 74, IEEE, New York, NY, 2015 (misc)

icm

[BibTex]

[BibTex]


Joint 3D Estimation of Vehicles and Scene Flow
Joint 3D Estimation of Vehicles and Scene Flow

Menze, M., Heipke, C., Geiger, A.

In Proc. of the ISPRS Workshop on Image Sequence Analysis (ISA), 2015 (inproceedings)

Abstract
Three-dimensional reconstruction of dynamic scenes is an important prerequisite for applications like mobile robotics or autonomous driving. While much progress has been made in recent years, imaging conditions in natural outdoor environments are still very challenging for current reconstruction and recognition methods. In this paper, we propose a novel unified approach which reasons jointly about 3D scene flow as well as the pose, shape and motion of vehicles in the scene. Towards this goal, we incorporate a deformable CAD model into a slanted-plane conditional random field for scene flow estimation and enforce shape consistency between the rendered 3D models and the parameters of all superpixels in the image. The association of superpixels to objects is established by an index variable which implicitly enables model selection. We evaluate our approach on the challenging KITTI scene flow dataset in terms of object and scene flow estimation. Our results provide a prove of concept and demonstrate the usefulness of our method.

avg ps

PDF [BibTex]

PDF [BibTex]


no image
Frenetic aspects of second order response

Basu, U., Krüger, M., Lazarescu, A., Maes, C.

Physical Chemistry Chemical Physics, 17(9):6653-6666, Royal Society of Chemistry, Cambridge, England, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Critical Casimir forces in the presence of random surface fields

Maciolek, A., Vasilyev, O., Dotsenko, V., Dietrich, S.

Physical Review E, 91(3), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Lab-in-a-tube systems as ultra-compact devices

Sanchez, S.

Lab chip, (3):610-613, 2015 (article)

Abstract
{In this Focus article, I will give an overview on the current and future interests of our multidisciplinary research group. One of our main interests is to develop highly integrated on-chip components towards ultra-compact devices for biosensing technologies (lab-in-a-tube). Our other activities are focused in developing self-powered devices that can generate either motion of a fluid or autonomous propulsion. We are particularly interested in three-dimensional (3D) nanofabrication technologies and stimuli responsive soft materials.}

icm

DOI [BibTex]

DOI [BibTex]


no image
Catalytic Mesoporous Janus Nanomotors for Active Cargo Delivery

Ma, X., Hahn, K., Sanchez, S.

Journal of the American Chemical Society, 137(15):4976-4979, ACS Publications, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Guest Editorial: Special Issue: Micro- and Nanomachines

Paxton, W., Sanchez, S., Nitta, T.

IEEE Transactions on Nanobioscience, 14(3):258-259, IEEE, New York, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Self-Assembly via Microfluidics

Wang, L., Sanchez, S.

Lab on a Chip, 15(23):4383-4386, Royal Society of Chemistry, Cambridge, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]


no image
Nonequilibrium interfacial tension during relaxation

Bier, M.

Physical Review E, 92(4), American Physical Society, Melville, NY, 2015 (article)

icm

DOI [BibTex]

DOI [BibTex]