Search Results for author: Sinisa Stekovic

Found 10 papers, 7 papers with code

PyTorchGeoNodes: Enabling Differentiable Shape Programs for 3D Shape Reconstruction

no code implementations16 Apr 2024 Sinisa Stekovic, Stefan Ainetter, Mattia D'Urso, Friedrich Fraundorfer, Vincent Lepetit

In our experiments, we apply our algorithm to reconstruct 3D objects in the ScanNet dataset and evaluate our results against CAD model retrieval-based reconstructions.

3D Reconstruction 3D Shape Reconstruction +2

HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans

2 code implementations12 Sep 2023 Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We present an automated and efficient approach for retrieving high-quality CAD models of objects and their poses in a scene captured by a moving RGB-D camera.

3D Object Retrieval 3D Scene Reconstruction +3

Automatically Annotating Indoor Images with CAD Models via RGB-D Scans

2 code implementations22 Dec 2022 Stefan Ainetter, Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans.

3D Object Retrieval Pose Estimation +1

MonteBoxFinder: Detecting and Filtering Primitives to Fit a Noisy Point Cloud

1 code implementation28 Jul 2022 Michaël Ramamonjisoa, Sinisa Stekovic, Vincent Lepetit

We present MonteBoxFinder, a method that, given a noisy input point cloud, fits cuboids to the input scene.

Scene Understanding

MonteFloor: Extending MCTS for Reconstructing Accurate Large-Scale Floor Plans

2 code implementations ICCV 2021 Sinisa Stekovic, Mahdi Rad, Friedrich Fraundorfer, Vincent Lepetit

For this step, we propose a novel differentiable method for rendering the polygonal shapes of these proposals.

General 3D Room Layout from a Single View by Render-and-Compare

1 code implementation ECCV 2020 Sinisa Stekovic, Shreyas Hampali, Mahdi Rad, Sayan Deb Sarkar, Friedrich Fraundorfer, Vincent Lepetit

In order to deal with occlusions between components of the layout, which is a problem ignored by previous works, we introduce an analysis-by-synthesis method to iteratively refine the 3D layout estimate.

Casting Geometric Constraints in Semantic Segmentation as Semi-Supervised Learning

no code implementations29 Apr 2019 Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We propose a simple yet effective method to learn to segment new indoor scenes from video frames: State-of-the-art methods trained on one dataset, even as large as the SUNRGB-D dataset, can perform poorly when applied to images that are not part of the dataset, because of the dataset bias, a common phenomenon in computer vision.

Semantic Segmentation

S4-Net: Geometry-Consistent Semi-Supervised Semantic Segmentation

no code implementations27 Dec 2018 Sinisa Stekovic, Friedrich Fraundorfer, Vincent Lepetit

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views.

Segmentation Semi-Supervised Semantic Segmentation

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