Search Results for author:
Found 55 papers, 35 papers with code
Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
We demonstrate that these directions can be used to augment the prompt text input with fine-grained control over attributes of specific subjects in a compositional manner (control over multiple attributes of a single subject) without having to adapt the diffusion model.
Enabling Visual Composition and Animation in Unsupervised Video Generation
We call our model CAGE for visual Composition and Animation for video GEneration.
DepthFM: Fast Monocular Depth Estimation with Flow Matching
Due to the generative nature of our approach, our model reliably predicts the confidence of its depth estimates.
ZigMa: A DiT-style Zigzag Mamba Diffusion Model
The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures.
On the Challenges and Opportunities in Generative AI
The field of deep generative modeling has grown rapidly and consistently over the years.
Quantum Denoising Diffusion Models
In recent years, machine learning models like DALL-E, Craiyon, and Stable Diffusion have gained significant attention for their ability to generate high-resolution images from concise descriptions.
Boosting Latent Diffusion with Flow Matching
We demonstrate that introducing FM between the Diffusion model and the convolutional decoder offers high-resolution image synthesis with reduced computational cost and model size.
State of the Art on Diffusion Models for Visual Computing
The field of visual computing is rapidly advancing due to the emergence of generative artificial intelligence (AI), which unlocks unprecedented capabilities for the generation, editing, and reconstruction of images, videos, and 3D scenes.
SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis
To address this limitation, we propose a novel guidance approach for the sampling process in the diffusion model that leverages bounding box and segmentation map information at inference time without additional training data.
Cross-Image-Attention for Conditional Embeddings in Deep Metric Learning
Experiments on established DML benchmarks show that our cross-attention conditional embedding during training improves the underlying standard DML pipeline significantly so that it outperforms the state-of-the-art.
Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models
In RDMs, a set of nearest neighbors is retrieved from an external database during training for each training instance, and the diffusion model is conditioned on these informative samples.
ArtFID: Quantitative Evaluation of Neural Style Transfer
The field of neural style transfer has experienced a surge of research exploring different avenues ranging from optimization-based approaches and feed-forward models to meta-learning methods.
Semi-Parametric Neural Image Synthesis
Much of this success is due to the scalability of these architectures and hence caused by a dramatic increase in model complexity and in the computational resources invested in training these models.
High-Resolution Image Synthesis with Latent Diffusion Models
By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond.
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 256x256
Unsupervised View-Invariant Human Posture Representation
Most recent view-invariant action recognition and performance assessment approaches rely on a large amount of annotated 3D skeleton data to extract view-invariant features.
Improving Deep Metric Learning by Divide and Conquer
We propose to build a more expressive representation by jointly splitting the embedding space and the data hierarchically into smaller sub-parts.
ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis
Thus, in contrast to pure autoregressive models, it can solve free-form image inpainting and, in the case of conditional models, local, text-guided image modification without requiring mask-specific training.
Ranked #4 on
Text-to-Image Generation
on Conceptual Captions
Characterizing Generalization under Out-Of-Distribution Shifts in Deep Metric Learning
Finally, we propose few-shot DML as an efficient way to consistently improve generalization in response to unknown test shifts presented in ooDML.
Object Retrieval and Localization in Large Art Collections using Deep Multi-Style Feature Fusion and Iterative Voting
In the following, we introduce an algorithm that allows users to search for image regions containing specific motifs or objects and find similar regions in an extensive dataset, helping art historians to analyze large digitized art collections.
iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis
There will be distinctive movement, despite evident variations caused by the stochastic nature of our world.
Understanding Object Dynamics for Interactive Image-to-Video Synthesis
Given a static image of an object and a local poking of a pixel, the approach then predicts how the object would deform over time.
High-Resolution Complex Scene Synthesis with Transformers
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity.
Stochastic Image-to-Video Synthesis using cINNs
Video understanding calls for a model to learn the characteristic interplay between static scene content and its dynamics: Given an image, the model must be able to predict a future progression of the portrayed scene and, conversely, a video should be explained in terms of its static image content and all the remaining characteristics not present in the initial frame.
Geometry-Free View Synthesis: Transformers and no 3D Priors
Is a geometric model required to synthesize novel views from a single image?
Ranked #1 on
Novel View Synthesis
on RealEstate10K
Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes
There have been many successful implementations of neural style transfer in recent years.
Behavior-Driven Synthesis of Human Dynamics
Using this representation, we are able to change the behavior of a person depicted in an arbitrary posture, or to even directly transfer behavior observed in a given video sequence.
Shape or Texture: Disentangling Discriminative Features in CNNs
Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs actually exhibit a 'texture bias': given an image with both texture and shape cues (e. g., a stylized image), a CNN is biased towards predicting the category corresponding to the texture.
Taming Transformers for High-Resolution Image Synthesis
We demonstrate how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images.
Ranked #3 on
Text-to-Image Generation
on LHQC
A Note on Data Biases in Generative Models
It is tempting to think that machines are less prone to unfairness and prejudice.
S2SD: Simultaneous Similarity-based Self-Distillation for Deep Metric Learning
Deep Metric Learning (DML) provides a crucial tool for visual similarity and zero-shot applications by learning generalizing embedding spaces, although recent work in DML has shown strong performance saturation across training objectives.
Ranked #10 on
Metric Learning
on CARS196
(using extra training data)
Unsupervised Part Discovery by Unsupervised Disentanglement
Our approach leverages a generative model consisting of two disentangled representations for an object's shape and appearance and a latent variable for the part segmentation.
Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs
To open such a black box, it is, therefore, crucial to uncover the different semantic concepts a model has learned as well as those that it has learned to be invariant to.
Network-to-Network Translation with Conditional Invertible Neural Networks
Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation.
DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning
Visual Similarity plays an important role in many computer vision applications.
Ranked #13 on
Metric Learning
on CUB-200-2011
(using extra training data)
A Disentangling Invertible Interpretation Network for Explaining Latent Representations
We formulate interpretation as a translation of hidden representations onto semantic concepts that are comprehensible to the user.
Sharing Matters for Generalization in Deep Metric Learning
The common paradigm is discriminative metric learning, which seeks an embedding that separates different training classes.
Learning Multi-Scale Photo Exposure Correction
In contrast, our proposed method targets both over- and underexposure errors in photographs.
Ranked #3 on
Image Enhancement
on Exposure-Errors
PADS: Policy-Adapted Sampling for Visual Similarity Learning
Learning visual similarity requires to learn relations, typically between triplets of images.
Ranked #17 on
Metric Learning
on CUB-200-2011
(using extra training data)
A Content Transformation Block For Image Style Transfer
Recent work has significantly improved the representation of color and texture and computational speed and image resolution.
Revisiting Training Strategies and Generalization Performance in Deep Metric Learning
Deep Metric Learning (DML) is arguably one of the most influential lines of research for learning visual similarities with many proposed approaches every year.
Unsupervised Representation Learning by Discovering Reliable Image Relations
To nevertheless find those relations which can be reliably utilized for learning, we follow a divide-and-conquer strategy: We find reliable similarities by extracting compact groups of images and reliable dissimilarities by partitioning these groups into subsets, converting the complicated overall problem into few reliable local subproblems.
Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
In experiments on diverse object categories, the approach successfully recombines pose and appearance to reconstruct and retarget novel synthesized images.
MIC: Mining Interclass Characteristics for Improved Metric Learning
In contrast, we propose to explicitly learn the latent characteristics that are shared by and go across object classes.
Ranked #19 on
Metric Learning
on CUB-200-2011
(using extra training data)
Multi-Scale Convolutions for Learning Context Aware Feature Representations
Finding semantic correspondences is a challenging problem.
Divide and Conquer the Embedding Space for Metric Learning
Approaches for learning a single distance metric often struggle to encode all different types of relationships and do not generalize well.
Unsupervised Part-Based Disentangling of Object Shape and Appearance
Large intra-class variation is the result of changes in multiple object characteristics.
Ranked #3 on
Unsupervised Human Pose Estimation
on Human3.6M
Cross and Learn: Cross-Modal Self-Supervision
In this paper we present a self-supervised method for representation learning utilizing two different modalities.
Improving Spatiotemporal Self-Supervision by Deep Reinforcement Learning
Self-supervised learning of convolutional neural networks can harness large amounts of cheap unlabeled data to train powerful feature representations.
A Style-Aware Content Loss for Real-time HD Style Transfer
These and our qualitative results ranging from small image patches to megapixel stylistic images and videos show that our approach better captures the subtle nature in which a style affects content.
A Variational U-Net for Conditional Appearance and Shape Generation
Experiments show that the model enables conditional image generation and transfer.
Deep Unsupervised Learning of Visual Similarities
Exemplar learning of visual similarities in an unsupervised manner is a problem of paramount importance to Computer Vision.
Self-supervised Learning of Pose Embeddings from Spatiotemporal Relations in Videos
Human pose analysis is presently dominated by deep convolutional networks trained with extensive manual annotations of joint locations and beyond.
Deep Unsupervised Similarity Learning using Partially Ordered Sets
Similarity learning is then formulated as a partial ordering task with soft correspondences of all samples to classes.
CliqueCNN: Deep Unsupervised Exemplar Learning
Exemplar learning is a powerful paradigm for discovering visual similarities in an unsupervised manner.
Spatio-temporal Video Parsing for Abnormality Detection
The goal of video parsing is to find a set of indispensable normal spatio-temporal object hypotheses that jointly explain all the foreground of a video, while, at the same time, being supported by normal training samples.
