相关论文: SPARE3D: A Dataset for SPAtial REasoning on Three-…

In this paper, we propose using deep neural architectures (i.e., vision transformers and ResNet) as heuristics for sequential decision-making in robotic manipulation problems. This formulation enables predicting the subset of objects that…

For more than a decade, deep learning models have been dominating in various 2D imaging tasks. Their application is now extending to 3D imaging, with 3D Convolutional Neural Networks (3D CNNs) being able to process LIDAR, MRI, and CT scans,…

Understanding 3D spatial relationships remains a major limitation of current Vision-Language Models (VLMs). Prior work has addressed this issue by creating spatial question-answering (QA) datasets based on single images or indoor videos.…

Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial…

Multimodal Large Language Models (MLLMs) have demonstrated impressive performance in general vision-language tasks. However, recent studies have exposed critical limitations in their spatial reasoning capabilities. This deficiency in…

A robot's ability to act is fundamentally constrained by what it can perceive. Many existing approaches to visual representation learning utilize general-purpose training criteria, e.g. image reconstruction, smoothness in latent space, or…

Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision. In almost all cases these benchmarks are observational in the sense they are composed of behavioural and brain responses…

Though performed almost effortlessly by humans, segmenting 2D gray-scale or color images into respective regions of interest (e.g.~background, objects, or portions of objects) constitutes one of the greatest challenges in science and…

Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}'…

Deep neural networks have established themselves as the state-of-the-art methodology in almost all computer vision tasks to date. But their application to processing data lying on non-Euclidean domains is still a very active area of…

Human perception and understanding is a major domain of computer vision which, like many other vision subdomains recently, stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common…

Deep learning's success in perception, natural language processing, etc. inspires hopes for advancements in autonomous robotics. However, real-world robotics face challenges like variability, high-dimensional state spaces, non-linear…

Multimodal Large Language Models (MLLMs) have made rapid progress in spatial intelligence, yet existing spatial reasoning benchmarks largely assume pristine visual inputs and overlook the degradations that commonly occur in real-world…

As part of human core knowledge, the representation of objects is the building block of mental representation that supports high-level concepts and symbolic reasoning. While humans develop the ability of perceiving objects situated in 3D…

Large vision-language models (VLMs) have made significant strides in 2D visual understanding tasks, sparking interest in extending these capabilities to 3D scene understanding. However, current 3D VLMs often struggle with robust reasoning…

We propose Perceptual Taxonomy, a structured process of scene understanding that first recognizes objects and their spatial configurations, then infers task-relevant properties such as material, affordance, function, and physical attributes…

360 panoramic images are increasingly used in virtual reality, autonomous driving, and robotics for holistic scene understanding. However, current Vision-Language Models (VLMs) struggle with 3D spatial reasoning on Equirectangular…

As spatial intelligence becomes an increasingly important capability for foundation models, it remains unclear whether large language models' (LLMs) performance on spatial reasoning benchmarks reflects structured internal spatial…

Although perception systems have made remarkable advancements in recent years, particularly in 2D reasoning segmentation, these systems still rely on explicit human instruction or pre-defined categories to identify target objects before…

Neural networks have achieved success in a wide array of perceptual tasks but often fail at tasks involving both perception and higher-level reasoning. On these more challenging tasks, bespoke approaches (such as modular symbolic…