相关论文: Modeling geometric-optical illusions: A variationa…

We tackle the challenging problem of human-object interaction (HOI) detection. Existing methods either recognize the interaction of each human-object pair in isolation or perform joint inference based on complex appearance-based features.…

Geometrical optics (GO) is widely used for reduced modeling of waves in plasmas but fails near reflection points, where it predicts a spurious singularity of the wave amplitude. We show how to avoid this singularity by adopting a different…

Human-object interaction (HOI) detection often faces high levels of ambiguity and indeterminacy, as the same interaction can appear vastly different across different human-object pairs. Additionally, the indeterminacy can be further…

Naturalistic scenes are of key interest for visual perception, but controlling their perceptual and semantic properties is challenging. Previous work on naturalistic scenes has frequently focused on collections of discrete images with…

This paper gives an overview of a theory for modelling the interaction between geometric image transformations and receptive field responses for a visual observer that views objects and spatio-temporal events in the environment. This…

Graphical User Interface (GUI) grounding is commonly framed as a coordinate prediction task -- given a natural language instruction, generate on-screen coordinates for actions such as clicks and keystrokes. However, recent Vision Language…

In this paper we first recall the definition of geometical model of the visual cortex, focusing in particular on the geometrical properties of horizontal cortical connectivity. Then we recognize that histograms of edges - co-occurrences are…

We consider the evolution model proposed in [9, 6] to describe illusory contrast perception phenomena induced by surrounding orientations. Firstly, we highlight its analogies and differences with the widely used Wilson-Cowan equations [48],…

Ray optics is an intuitive and computationally efficient model for wave propagation through nonuniform media. However, the underlying geometrical-optics (GO) approximation of ray optics breaks down at caustics, erroneously predicting the…

We consider the problem of visual imitation learning without human supervision (e.g. kinesthetic teaching or teleoperation), nor access to an interactive reinforcement learning (RL) training environment. We present a geometric perspective…

We address the task of open-world class-agnostic object detection, i.e., detecting every object in an image by learning from a limited number of base object classes. State-of-the-art RGB-based models suffer from overfitting the training…

We study behavior change-based visual risk object identification (Visual-ROI), a critical framework designed to detect potential hazards for intelligent driving systems. Existing methods often show significant limitations in spatial…

Illusions are entertaining, but they are also a useful diagnostic tool in cognitive science, philosophy, and neuroscience. A typical illusion shows a gap between how something "really is" and how something "appears to be", and this gap…

We address the problem of generating realistic 3D human-object interactions (HOIs) driven by textual prompts. To this end, we take a modular design and decompose the complex task into simpler sub-tasks. We first develop a dual-branch…

We tackle the challenge of efficiently reconstructing 3D scenes with high detail on objects of interest. Existing 3D Gaussian Splatting (3DGS) methods allocate resources uniformly across the scene, limiting fine detail to Regions Of…

Deformable image registration is inherently a multi-objective optimization (MOO) problem, requiring a delicate balance between image similarity and deformation regularity. These conflicting objectives often lead to poor optimization…

We study the inverse graphics problem of inferring a holistic representation for natural images. Given an input image, our goal is to induce a neuro-symbolic, program-like representation that jointly models camera poses, object locations,…

Compositional Customized Image Generation aims to customize multiple target concepts within generation content, which has gained attention for its wild application. Existing approaches mainly concentrate on the target entity's appearance…

Generative Adversarial Networks (GANs) have recently achieved impressive results for many real-world applications, and many GAN variants have emerged with improvements in sample quality and training stability. However, they have not been…

We address the problem of learning representations from observations of a scene involving an agent and an external object the agent interacts with. To this end, we propose a representation learning framework extracting the location in…