Related papers: Semantic Compositional Learning for Low-shot Scene…

Semantic layouts based Image synthesizing, which has benefited from the success of Generative Adversarial Network (GAN), has drawn much attention in these days. How to enhance the synthesis image equality while keeping the stochasticity of…

Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. This task has achieved significant momentum in the computer vision community as it enables activity grounding beyond…

Semantic world models enable embodied agents to reason about objects, relations, and spatial context beyond purely geometric representations. In Organic Computing, such models are a key enabler for objective-driven self-adaptation under…

Scene graph generation (SGG) aims to parse a visual scene into an intermediate graph representation for downstream reasoning tasks. Despite recent advancements, existing methods struggle to generate scene graphs with novel visual relation…

Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized…

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

This paper tackles a challenging problem of generating photorealistic images from semantic layouts in few-shot scenarios where annotated training pairs are hardly available but pixel-wise annotation is quite costly. We present a training…

A proper scene representation is central to the pursuit of spatial intelligence where agents can robustly reconstruct and efficiently understand 3D scenes. A scene representation is either metric, such as landmark maps in 3D reconstruction,…

Recent advances in text-to-vision generation excel in visual fidelity but struggle with compositional generalization and semantic alignment. Existing datasets are noisy and weakly compositional, limiting models' understanding of complex…

Object-centric representations promise a key property for few-shot learning: Rather than treating a scene as a single unit, a model can decompose it into individual object-level parts that can be matched and compared across different…

Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene graph generation. Models learned without considering the class…

Objects in a scene are not always related. The execution efficiency of the one-stage scene graph generation approaches are quite high, which infer the effective relation between entity pairs using sparse proposal sets and a few queries.…

Recent works on SLAM extend their pose graphs with higher-level semantic concepts like Rooms exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy…

The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for…

We introduce SceneLinker, a novel framework that generates compositional 3D scenes via semantic scene graph from RGB sequences. To adaptively experience Mixed Reality (MR) content based on each user's space, it is essential to generate a 3D…

We present SemanticNVS, a camera-conditioned multi-view diffusion model for novel view synthesis (NVS), which improves generation quality and consistency by integrating pre-trained semantic feature extractors. Existing NVS methods perform…

In this paper, we address the task of semantic-guided image generation. One challenge common to most existing image-level generation methods is the difficulty in generating small objects and detailed local textures. To address this, in this…

Many real-world problems are compositional - solving them requires completing interdependent sub-tasks, either in series or in parallel, that can be represented as a dependency graph. Deep reinforcement learning (RL) agents often struggle…

Deep learning-based graph generation approaches have remarkable capacities for graph data modeling, allowing them to solve a wide range of real-world problems. Making these methods able to consider different conditions during the generation…

Few-shot Intent Detection is challenging due to the scarcity of available annotated utterances. Although recent works demonstrate that multi-level matching plays an important role in transferring learned knowledge from seen training classes…