1,721,241 research outputs found
Synthetic data (Part 2) for "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields"
No full textHere we provide the data of our article "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields". It contains the rendered images and the segmentation masks that we use to train our model on HO3Dv2 dataset.
The overall structure of the data is:
├── render_sdf_ho3d.zip - Contains the rendered images for HO3Dv2.
If you find our code, weights, predictions or ideas useful, please cite:
@inproceedings{qi2024hoisdf, title={HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields}, author={Qi, Haozhe and Zhao, Chen and Salzmann, Mathieu and Mathis, Alexander}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={10392--10402}, year={2024}}UPAMATHISLCAVSDSC-GE2.
Synthetic data (Part 1) for "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields"
No full textHere we provide the data of our article "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields". It contains the preprocessed SDF samples. Meanwhile, we also include rendered data for HO3Dv2 here.
The overall structure of the data is:
├── render_sdf_ho3d.zip - Contains the processed SDF files for HO3Dv2 rendered images.
├── train_ho3d.zip - Contains the processed SDF files for HO3Dv2 training set.
├── full_test_dexycb.zip - Contains the processed SDF files for DexYCB full test set.
The code to reproduce the results is available at: https://github.com/amathislab/HOISDF
--------------------------------
If you find our code, weights, predictions or ideas useful, please cite:
@inproceedings{qi2024hoisdf, title={HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields}, author={Qi, Haozhe and Zhao, Chen and Salzmann, Mathieu and Mathis, Alexander}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={10392--10402}, year={2024}}UPAMATHISLCAVSDSC-G
Leveraging light-curve inversion for kinematic state estimation of uncooperative targets
No full textThe growing number of space objects threatens mission sustainability, making precise real-time tracking essential for Active Debris Removal (ADR) and In-Orbit Servicing (IOS) missions. For an uncooperative target, a Vision Based Navigation (VBN) relative pose (attitude and position) estimation system coupled with a state estimator are likely required. Missions can further be supported by commissioning unresolved observations of the target to produce light curves which can then be used to extract rotation rates and axes of rotation. This work performs the novel task of exploiting the light curves as kinematic priors to enhance the performance of the state estimator.
An Extended Kalman Filter (EKF) and an Unscented Kalman Filter (UKF) are implemented. Light curve motion prior extraction and VBN pose estimation are simulated. Three independent studies are performed exploiting the motion priors: (1) Optimizing the Kalman filter tuning for specific kinematic scenarios; (2) Injecting the priors as an initial condition to improve convergence and steady state errors; and (3) Enhancing an outlier rejection function with supplementary proxy measurements from the priors. Performance is evaluated on a custom synthetic light curve dataset based on the Atlas Centaur rocket body, and a private commercial dataset based on the Vega Secondary Payload Adapter from commercial collaborator, Clearspace. Pose estimation results are simulated based on state-of-the-art machine learning spacecraft pose estimators. By exploiting kinematic priors, convergence time and steady state error reductions of 3× or more are exhibited for certain state components, dependent on the kinematic scenario and filter tuning. In general, several trade-offs are observed with kinematic priors providing the opportunity for the lowest steady state errors. This method has the potential to improve the pose estimation accuracy for proximity operations of uncooperative tumbling objects, supporting ADR and IOS missions, especially considering the mild assumptions required
Volumetric Transformer Networks
No full textExisting techniques to encode spatial invariance within deep convolutional neural networks (CNNs) apply the same warping field to all the feature channels. This does not account for the fact that the individual feature channels can represent different semantic parts, which can undergo different spatial transformations w.r.t. a canonical configuration. To overcome this limitation, we introduce a learnable module, the volumetric transformer network (VTN), that predicts channel-wise warping fields so as to reconfigure intermediate CNN features spatially and channel-wisely. We design our VTN as an encoder-decoder network, with modules dedicated to letting the information flow across the feature channels, to account for the dependencies between the semantic parts. We further propose a loss function defined between the warped features of pairs of instances, which improves the localization ability of VTN. Our experiments show that VTN consistently boosts the features’ representation power and consequently the networks’ accuracy on fine-grained image recognition and instance-level image retrieval
DUNIT: Detection-based Unsupervised Image-to-Image Translation
No full textImage-to-image translation has made great strides in recent years, with current techniques being able to handle unpaired training images and to account for the multimodality of the translation problem. Despite this, most methods treat the image as a whole, which makes the results they produce for content-rich scenes less realistic. In this paper, we introduce a Detection-based Unsupervised Image-to-image Translation (DUNIT) approach that explicitly accounts for the object instances in the translation process. To this end, we extract separate representations for the global image and for the instances, which we then fuse into a common representation from which we generate the translated image. This allows us to preserve the detailed content of object instances, while still modeling the fact that we aim to produce an image of a single consistent scene. We introduce an instance consistency loss to maintain the coherence between the detections. Furthermore, by incorporating a detector into our architecture, we can still exploit object instances at test time. As evidenced by our experiments, this allows us to outperform the state-of-the-art unsupervised image-to-image translation methods. Furthermore, our approach can also be used as an unsupervised domain adaptation strategy for object detection, and it also achieves state-of-the-art performance on this task. Our project page is at https://ivrl.github.io/Dunit/.IVRLCVLA
HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models
No full textHOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields, CVPR 2024
Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis.
Affiliation: EPFL
Date: June, 2024
Link to the CVPR article: https://openaccess.thecvf.com/content/CVPR2024/papers/Qi_HOISDF_Constraining_3D_Hand-Object_Pose_Estimation_with_Global_Signed_Distance_CVPR_2024_paper.pdf
Link to the Arxiv article: https://arxiv.org/abs/2402.17062
--------------------------------
Here we provide the data of our article "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields". It contains the preprocessed data of the interacting objects and SDF samples. Meanwhile, we also include the trained model weights here.
The overall structure of the data is:
├── ckpts.zip - Contains the trained weights model on different datasets (DexYCB and HO3Dv2)
├── annotations.zip - Contains the preprocessed annotations of DexYCB and HO3Dv2 for efficient data loading.
├── simple_ycb_models.zip - Contains the preprocessed YCB objects for batched evaluation.
├── test.zip - Contains the processed SDF files for DexYCB test set.
The code to reproduce the results is available at: https://github.com/amathislab/HOISDF
--------------------------------
If you find our code, weights, predictions or ideas useful, please cite:
@inproceedings{qi2024hoisdf, title={HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields}, author={Qi, Haozhe and Zhao, Chen and Salzmann, Mathieu and Mathis, Alexander}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={10392--10402}, year={2024}}CVLABUPAMATHIS
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
