Related papers: CompDiff: Hierarchical Compositional Diffusion for…

We introduce the Cross Human Motion Diffusion Model (CrossDiff), a novel approach for generating high-quality human motion based on textual descriptions. Our method integrates 3D and 2D information using a shared transformer network within…

Acquiring aligned visuo-tactile datasets is slow and costly, requiring specialised hardware and large-scale data collection. Synthetic generation is promising, but prior methods are typically single-modality, limiting cross-modal learning.…

Multimodal generative models that can understand and generate across multiple modalities are dominated by autoregressive (AR) approaches, which process tokens sequentially from left to right, or top to bottom. These models jointly handle…

The growing adoption of generative AI in real-world applications has exposed a critical bottleneck in the computational demands of diffusion-based text-to-image models. In this work, we propose KDC-Diff, a novel and scalable generative…

Data-driven deep learning models have enabled tremendous progress in change detection (CD) with the support of pixel-level annotations. However, collecting diverse data and manually annotating them is costly, laborious, and…

Generative methods now produce outputs nearly indistinguishable from real data but often fail to fully capture the data distribution. Unlike quality issues, diversity limitations in generative models are hard to detect visually, requiring…

Training supervised deep neural networks that perform defect detection and segmentation requires large-scale fully-annotated datasets, which can be hard or even impossible to obtain in industrial environments. Generative AI offers…

Recent advances in generative models have sparked research on improving model fairness with AI-generated data. However, existing methods often face limitations in the diversity and quality of synthetic data, leading to compromised fairness…

Effective trajectory stitching for long-horizon planning is a significant challenge in robotic decision-making. While diffusion models have shown promise in planning, they are limited to solving tasks similar to those seen in their training…

Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a…

In this paper, we consider the conditional generation problem by guiding off-the-shelf unconditional diffusion models with differentiable loss functions in a plug-and-play fashion. While previous research has primarily focused on balancing…

We describe Countersynth, a conditional generative model of diffeomorphic deformations that induce label-driven, biologically plausible changes in volumetric brain images. The model is intended to synthesise counterfactual training data…

In medical image segmentation tasks, Domain Generalization (DG) under the Federated Learning (FL) framework is crucial for addressing challenges related to privacy protection and data heterogeneity. However, traditional federated learning…

Graph generation is a fundamental problem in graph learning with broad applications across Web-scale systems, knowledge graphs, and scientific domains such as drug and material discovery. Recent approaches leverage diffusion models for…

Diffusion probabilistic models (DPMs) have become a popular approach to conditional generation, due to their promising results and support for cross-modal synthesis. A key desideratum in conditional synthesis is to achieve high…

Image composition has advanced significantly with large-scale pre-trained T2I diffusion models. Despite progress in same-domain composition, cross-domain composition remains under-explored. The main challenges are the stochastic nature of…

Image composition and generation are processes where the artists need control over various parts of the generated images. However, the current state-of-the-art generation models, like Stable Diffusion, cannot handle fine-grained part-level…

High-resolution image editing is essential for professional and creative applications, yet existing multimodal diffusion-based editors remain computationally inefficient and constrained to relatively low resolutions. Current approaches…

We introduce CompTok, a training framework for learning visual tokenizers whose tokens are enhanced for compositionality. CompTok uses a token-conditioned diffusion decoder. By employing an InfoGAN-style objective, where we train a…

The harnessing of machine learning, especially deep generative models, has opened up promising avenues in the field of synthetic DNA sequence generation. Whilst Generative Adversarial Networks (GANs) have gained traction for this…