no code implementations • 30 Apr 2024 • Paul Engstler, Andrea Vedaldi, Iro Laina, Christian Rupprecht
These works often depend on pre-trained monocular depth estimators to lift the generated images into 3D, fusing them with the existing scene representation.
no code implementations • 29 Apr 2024 • Minghao Chen, Iro Laina, Andrea Vedaldi
However, this is often slow as it requires do update a computationally expensive 3D representations such as a neural radiance field, and to do so by using contradictory guidance from a 2D model which is inherently not multi-view consistent.
no code implementations • 16 Mar 2024 • Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi
To address this, we introduce Nested Neural Feature Fields (N2F2), a novel approach that employs hierarchical supervision to learn a single feature field, wherein different dimensions within the same high-dimensional feature encode scene properties at varying granularities.
no code implementations • 13 Feb 2024 • Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Natalia Neverova, Andrea Vedaldi, Oran Gafni, Filippos Kokkinos
A mitigation is to fine-tune the 2D generator to be multi-view aware, which can help distillation or can be combined with reconstruction networks to output 3D objects directly.
no code implementations • 14 Dec 2023 • Minghao Chen, Junyu Xie, Iro Laina, Andrea Vedaldi
In particular, we hypothesise that editing can be greatly simplified by first encoding 3D objects in a suitable latent space.
no code implementations • 24 Nov 2023 • Paul Engstler, Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels.
Ranked #2 on Unsupervised Instance Segmentation on COCO val2017
no code implementations • 15 Jun 2023 • Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
This provides a distribution of appearances for a given text circumventing the ambiguity problem.
1 code implementation • NeurIPS 2023 • Vadim Tschernezki, Ahmad Darkhalil, Zhifan Zhu, David Fouhey, Iro Laina, Diane Larlus, Dima Damen, Andrea Vedaldi
Compared to other neural rendering datasets, EPIC Fields is better tailored to video understanding because it is paired with labelled action segments and the recent VISOR segment annotations.
1 code implementation • NeurIPS 2023 • Yash Bhalgat, Iro Laina, João F. Henriques, Andrew Zisserman, Andrea Vedaldi
Our approach outperforms the state-of-the-art on challenging scenes from the ScanNet, Hypersim, and Replica datasets, as well as on our newly created Messy Rooms dataset, demonstrating the effectiveness and scalability of our slow-fast clustering method.
1 code implementation • 6 Apr 2023 • Minghao Chen, Iro Laina, Andrea Vedaldi
We thoroughly evaluate our approach on three benchmarks and provide several qualitative examples and a comparative analysis of the two strategies that demonstrate the superiority of backward guidance compared to forward guidance, as well as prior work.
3 code implementations • 21 Feb 2023 • Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
We consider the problem of reconstructing a full 360{\deg} photographic model of an object from a single image of it.
no code implementations • CVPR 2023 • Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Andrea Vedaldi
We consider the problem of reconstructing a full 360deg photographic model of an object from a single image of it.
no code implementations • 21 Oct 2022 • Laurynas Karazija, Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
We propose a new approach to learn to segment multiple image objects without manual supervision.
no code implementations • 7 Sep 2022 • Vadim Tschernezki, Iro Laina, Diane Larlus, Andrea Vedaldi
We present Neural Feature Fusion Fields (N3F), a method that improves dense 2D image feature extractors when the latter are applied to the analysis of multiple images reconstructible as a 3D scene.
no code implementations • 7 Sep 2022 • Iro Laina, Yuki M. Asano, Andrea Vedaldi
Self-supervised visual representation learning has recently attracted significant research interest.
no code implementations • 16 May 2022 • Subhabrata Choudhury, Laurynas Karazija, Iro Laina, Andrea Vedaldi, Christian Rupprecht
Motion, measured via optical flow, provides a powerful cue to discover and learn objects in images and videos.
Ranked #4 on Unsupervised Object Segmentation on SegTrack-v2
1 code implementation • CVPR 2022 • Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
We find that these eigenvectors already decompose an image into meaningful segments, and can be readily used to localize objects in a scene.
1 code implementation • 19 Nov 2021 • Laurynas Karazija, Iro Laina, Christian Rupprecht
We benchmark a large set of recent unsupervised multi-object segmentation models on ClevrTex and find all state-of-the-art approaches fail to learn good representations in the textured setting, despite impressive performance on simpler data.
Ranked #3 on Unsupervised Object Segmentation on ClevrTex
1 code implementation • NeurIPS 2021 • Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
First, we construct a proxy task through a set of objectives that encourages the model to learn a meaningful decomposition of the image into its parts.
Ranked #1 on Unsupervised Keypoint Estimation on CUB
1 code implementation • 5 Nov 2021 • Subhabrata Choudhury, Iro Laina, Christian Rupprecht, Andrea Vedaldi
We then train a fine-grained textual similarity model that matches image descriptions with documents on a sentence-level basis.
no code implementations • ICLR 2022 • Iro Laina, Yuki M Asano, Andrea Vedaldi
Self-supervised visual representation learning has attracted significant research interest.
Ranked #90 on Image Classification on ObjectNet (using extra training data)
1 code implementation • ICLR 2022 • Luke Melas-Kyriazi, Christian Rupprecht, Iro Laina, Andrea Vedaldi
Recent research has shown that numerous human-interpretable directions exist in the latent space of GANs.
no code implementations • NeurIPS 2020 • Iro Laina, Ruth C. Fong, Andrea Vedaldi
The increasing impact of black box models, and particularly of unsupervised ones, comes with an increasing interest in tools to understand and interpret them.
1 code implementation • CVPR 2020 • Helisa Dhamo, Azade Farshad, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari, Christian Rupprecht
In our work, we address the novel problem of image manipulation from scene graphs, in which a user can edit images by merely applying changes in the nodes or edges of a semantic graph that is generated from the image.
no code implementations • ICCV 2019 • Iro Laina, Christian Rupprecht, Nassir Navab
The core component of our approach is a shared latent space that is structured by visual concepts.
3 code implementations • 18 Feb 2019 • Max Allan, Alex Shvets, Thomas Kurmann, Zichen Zhang, Rahul Duggal, Yun-Hsuan Su, Nicola Rieke, Iro Laina, Niveditha Kalavakonda, Sebastian Bodenstedt, Luis Herrera, Wenqi Li, Vladimir Iglovikov, Huoling Luo, Jian Yang, Danail Stoyanov, Lena Maier-Hein, Stefanie Speidel, Mahdi Azizian
In mainstream computer vision and machine learning, public datasets such as ImageNet, COCO and KITTI have helped drive enormous improvements by enabling researchers to understand the strengths and limitations of different algorithms via performance comparison.
no code implementations • 2 Nov 2018 • Ghazal Ghazaei, Iro Laina, Christian Rupprecht, Federico Tombari, Nassir Navab, Kianoush Nazarpour
Further, we reformulate the problem of robotic grasping by replacing conventional grasp rectangles with grasp belief maps, which hold more precise location information than a rectangle and account for the uncertainty inherent to the task.
no code implementations • 23 Jul 2018 • Helisa Dhamo, Keisuke Tateno, Iro Laina, Nassir Navab, Federico Tombari
While conventional depth estimation can infer the geometry of a scene from a single RGB image, it fails to estimate scene regions that are occluded by foreground objects.
no code implementations • CVPR 2018 • Christian Rupprecht, Iro Laina, Nassir Navab, Gregory D. Hager, Federico Tombari
Interaction and collaboration between humans and intelligent machines has become increasingly important as machine learning methods move into real-world applications that involve end users.
1 code implementation • CVPR 2017 • Keisuke Tateno, Federico Tombari, Iro Laina, Nassir Navab
Given the recent advances in depth prediction from Convolutional Neural Networks (CNNs), this paper investigates how predicted depth maps from a deep neural network can be deployed for accurate and dense monocular reconstruction.
no code implementations • 30 Mar 2017 • Iro Laina, Nicola Rieke, Christian Rupprecht, Josué Page Vizcaíno, Abouzar Eslami, Federico Tombari, Nassir Navab
Real-time instrument tracking is a crucial requirement for various computer-assisted interventions.
no code implementations • ICCV 2017 • Christian Rupprecht, Iro Laina, Robert DiPietro, Maximilian Baust, Federico Tombari, Nassir Navab, Gregory D. Hager
In future prediction, for example, many distinct outcomes are equally valid.
18 code implementations • 1 Jun 2016 • Iro Laina, Christian Rupprecht, Vasileios Belagiannis, Federico Tombari, Nassir Navab
This paper addresses the problem of estimating the depth map of a scene given a single RGB image.