no code implementations • 2 Dec 2023 • Karran Pandey, Paul Guerrero, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy Mitra
Our key insight is to lift diffusion activations for an object to 3D using a proxy depth, 3D-transform the depth and associated activations, and project them back to image space.
no code implementations • CVPR 2023 • Animesh Karnewar, Andrea Vedaldi, David Novotny, Niloy Mitra
We show that our diffusion models are scalable, train robustly, and are competitive in terms of sample quality and fidelity to existing approaches for 3D generative modeling.
no code implementations • 27 Nov 2022 • Animesh Karnewar, Oliver Wang, Tobias Ritschel, Niloy Mitra
We introduce 3inGAN, an unconditional 3D generative model trained from 2D images of a single self-similar 3D scene.
no code implementations • 29 May 2022 • Wamiq Reyaz Para, Paul Guerrero, Niloy Mitra, Peter Wonka
Scalable generation of furniture layouts is essential for many applications in virtual reality, augmented reality, game development and synthetic data generation.
1 code implementation • 22 Sep 2021 • Marie-Julie Rakotosaona, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov, Paul Guerrero
Our method builds on the result that any 2D triangulation can be achieved by a suitably perturbed weighted Delaunay triangulation.
1 code implementation • CVPR 2022 • Sanjeev Muralikrishnan, Siddhartha Chaudhuri, Noam Aigerman, Vladimir Kim, Matthew Fisher, Niloy Mitra
We investigate the problem of training generative models on a very sparse collection of 3D models.
no code implementations • NeurIPS 2021 • Wamiq Reyaz Para, Shariq Farooq Bhat, Paul Guerrero, Tom Kelly, Niloy Mitra, Leonidas Guibas, Peter Wonka
Sketches can be represented as graphs, with the primitives as nodes and the constraints as edges.
1 code implementation • ICCV 2021 • Rameen Abdal, Peihao Zhu, Niloy Mitra, Peter Wonka
We propose an unsupervised segmentation framework for StyleGAN generated objects.
no code implementations • 27 Feb 2021 • Claudio Mura, Renato Pajarola, Konrad Schindler, Niloy Mitra
Thanks to recent advances in data-driven inertial odometry, such minimalistic input data can be acquired from the IMU readings of consumer-level smartphones, which allows for an effortless and scalable mapping of real-world indoor spaces.
1 code implementation • CVPR 2021 • Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman, Niloy Mitra, Maks Ovsjanikov
We leverage the properties of 2D Delaunay triangulations to construct a mesh from manifold surface elements.
no code implementations • 20 Aug 2020 • Qian Zheng, Weikai Wu, Hanting Pan, Niloy Mitra, Daniel Cohen-Or, Hui Huang
In this paper, we present a fine-grained action recognition method that learns to infer such latent object properties from human interaction motion alone.
1 code implementation • ECCV 2020 • Jiahui Lei, Srinath Sridhar, Paul Guerrero, Minhyuk Sung, Niloy Mitra, Leonidas J. Guibas
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views.
3 code implementations • 6 Aug 2020 • Rameen Abdal, Peihao Zhu, Niloy Mitra, Peter Wonka
We evaluate our method using the face and the car latent space of StyleGAN, and demonstrate fine-grained disentangled edits along various attributes on both real photographs and StyleGAN generated images.
1 code implementation • NeurIPS 2020 • Sebastien Ehrhardt, Oliver Groth, Aron Monszpart, Martin Engelcke, Ingmar Posner, Niloy Mitra, Andrea Vedaldi
We present RELATE, a model that learns to generate physically plausible scenes and videos of multiple interacting objects.
1 code implementation • NeurIPS 2020 • Thu Nguyen-Phuoc, Christian Richardt, Long Mai, Yong-Liang Yang, Niloy Mitra
Our experiments show that using explicit 3D features to represent objects allows BlockGAN to learn disentangled representations both in terms of objects (foreground and background) and their properties (pose and identity).
1 code implementation • CVPR 2020 • Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas
Learning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape, transferring edits from one shape to another, and many other applications in 3D content creation.
2 code implementations • 1 Aug 2019 • Kaichun Mo, Paul Guerrero, Li Yi, Hao Su, Peter Wonka, Niloy Mitra, Leonidas J. Guibas
We introduce StructureNet, a hierarchical graph network which (i) can directly encode shapes represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families; and (iii) can be used to generate a great diversity of realistic structured shape geometries.
no code implementations • ICCV 2019 • Philipp Henzler, Niloy Mitra, Tobias Ritschel
We can successfully reconstruct 3D shapes from unstructured 2D images and extensively evaluate PlatonicGAN on a range of synthetic and real data sets achieving consistent improvements over baseline methods.
no code implementations • ECCV 2020 • Yipeng Qin, Niloy Mitra, Peter Wonka
In this work, we uncover an even more important effect of Lipschitz regularization by examining its impact on the loss function: It degenerates GAN loss functions to almost linear ones by restricting their domain and interval of attainable gradient values.
no code implementations • 14 May 2018 • Sebastien Ehrhardt, Aron Monszpart, Niloy Mitra, Andrea Vedaldi
While learning models of intuitive physics is an increasingly active area of research, current approaches still fall short of natural intelligences in one important regard: they require external supervision, such as explicit access to physical states, at training and sometimes even at test times.
no code implementations • 9 May 2018 • John Femiani, Wamiq Reyaz Para, Niloy Mitra, Peter Wonka
Specifically, we propose a MULTIFACSEGNET architecture to assign multiple labels to each pixel, a SEPARABLE architecture as a low-rank formulation that encourages extraction of rectangular elements, and a COMPATIBILITY network that simultaneously seeks segmentation across facade element types allowing the network to 'see' intermediate output probabilities of the various facade element classes.
no code implementations • 22 Dec 2017 • Sebastien Ehrhardt, Aron Monszpart, Niloy Mitra, Andrea Vedaldi
In order to be able to leverage the approximation capabilities of artificial intelligence techniques in such physics related contexts, researchers have handcrafted the relevant states, and then used neural networks to learn the state transitions using simulation runs as training data.
no code implementations • 28 Oct 2017 • Moos Hueting, Pradyumna Reddy, Vladimir Kim, Ersin Yumer, Nathan Carr, Niloy Mitra
Discovering 3D arrangements of objects from single indoor images is important given its many applications including interior design, content creation, etc.
no code implementations • 6 Jun 2017 • Sébastien Ehrhardt, Aron Monszpart, Andrea Vedaldi, Niloy Mitra
While the basic laws of Newtonian mechanics are well understood, explaining a physical scenario still requires manually modeling the problem with suitable equations and associated parameters.
no code implementations • 16 Oct 2013 • Ming-Ming Cheng, Shuai Zheng, Wen-Yan Lin, Jonathan Warrell, Vibhav Vineet, Paul Sturgess, Nigel Crook, Niloy Mitra, Philip Torr
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.