Related papers: Time-Conditioned Generative Modeling of Object-Cen…
We propose a framework to continuously learn object-centric representations for visual learning and understanding. Existing object-centric representations either rely on supervisions that individualize objects in the scene, or perform…
The appearance of the same object may vary in different scene images due to perspectives and occlusions between objects. Humans can easily identify the same object, even if occlusions exist, by completing the occluded parts based on its…
Understanding and forecasting future scene states is critical for autonomous agents to plan and act effectively in complex environments. Object-centric models, with structured latent spaces, have shown promise in modeling object dynamics…
We present a novel framework for compositional video synthesis that leverages temporally consistent object-centric representations, extending our previous work, SlotAdapt, from images to video. While existing object-centric approaches…
Humans are remarkably good at understanding and reasoning about complex visual scenes. The capability to decompose low-level observations into discrete objects allows us to build a grounded abstract representation and identify the…
Generative models that can model and predict sequences of future events can, in principle, learn to capture complex real-world phenomena, such as physical interactions. However, a central challenge in video prediction is that the future is…
Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly…
A world model is essential for an agent to predict the future and plan in domains such as autonomous driving and robotics. To achieve this, recent advancements have focused on video generation, which has gained significant attention due to…
Object permanence in humans is a fundamental cue that helps in understanding persistence of objects, even when they are fully occluded in the scene. Present day methods in object segmentation do not account for this amodal nature of the…
Video prediction is a crucial task for intelligent agents such as robots and autonomous vehicles, since it enables them to anticipate and act early on time-critical incidents. State-of-the-art video prediction methods typically model the…
A central goal in AI is to represent scenes as compositions of discrete objects, enabling fine-grained, controllable image and video generation. Yet leading diffusion models treat images holistically and rely on text conditioning, creating…
Object detection in video and image surveillance is a well-established yet rapidly evolving task, strongly influenced by recent deep learning advancements. This review summarises modern techniques by examining architectural innovations,…
Given the complexities inherent in visual scenes, such as object occlusion, a comprehensive understanding often requires observation from multiple viewpoints. Existing multi-viewpoint object-centric learning methods typically employ random…
Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…
In traditional Visual Question Generation (VQG), most images have multiple concepts (e.g. objects and categories) for which a question could be generated, but models are trained to mimic an arbitrary choice of concept as given in their…
The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…
Generating videos predicting the future of a given sequence has been an area of active research in recent years. However, an essential problem remains unsolved: most of the methods require large computational cost and memory usage for…
The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either…
Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability. In this work, we take this idea one step further, ask the following question: "can…
Obtaining a useful estimate of an object from highly incomplete imaging measurements remains a holy grail of imaging science. Deep learning methods have shown promise in learning object priors or constraints to improve the conditioning of…