Related papers: Geo3DVQA: Evaluating Vision-Language Models for 3D…
Spatial reasoning is a core component of human cognition, enabling individuals to perceive, comprehend, and interact with the physical world. It relies on a nuanced understanding of spatial structures and inter-object relationships, serving…
Multimodal large language models (MLLMs) have achieved impressive performance across various tasks such as image captioning and visual question answer(VQA); however, they often struggle to accurately interpret depth information inherent in…
Existing aerial Vision-Language Navigation (VLN) methods predominantly adopt a detection-and-planning pipeline, which converts open-vocabulary detections into discrete textual scene graphs. These approaches are plagued by inadequate spatial…
Vision-Language Models (VLMs) have emerged as powerful tools for image understanding tasks, yet their practical deployment remains hindered by significant architectural heterogeneity across model families. This paper introduces UVLM…
Recent advances in multimodal large language models(MLLMs) have led to remarkable progress in visual grounding, enabling fine-grained cross-modal alignment between textual queries and image regions. However, transferring such capabilities…
Spatial relation reasoning is a crucial task for multimodal large language models (MLLMs) to understand the objective world. However, current benchmarks have issues like relying on bounding boxes, ignoring perspective substitutions, or…
Current large vision-language models (LVLMs) typically employ a connector module to link visual features with text embeddings of large language models (LLMs) and use end-to-end training to achieve multi-modal understanding in a unified…
Cross-view spatial reasoning is essential for embodied AI, underpinning spatial understanding, mental simulation and planning in complex environments. Existing benchmarks primarily emphasize indoor or street settings, overlooking the unique…
Vision-language models (VLMs) show great promise for 3D scene understanding but are mainly applied to indoor spaces or autonomous driving, focusing on low-level tasks like segmentation. This work expands their use to urban-scale…
The advancement of 3D vision-language (3D VL) learning is hindered by several limitations in existing 3D VL datasets: they rarely necessitate reasoning beyond a close range of objects in single viewpoint, and annotations often link…
Vision-Language Models like GPT-4, LLaVA, and CogVLM have surged in popularity recently due to their impressive performance in several vision-language tasks. Current evaluation methods, however, overlook an essential component: uncertainty,…
Accurate spatial reasoning in outdoor environments - covering geometry, object pose, and inter-object relationships - is fundamental to downstream tasks such as mapping, motion forecasting, and high-level planning in autonomous driving. We…
Recently, 3D vision-and-language tasks have attracted increasing research interest. Compared to other vision-and-language tasks, the 3D visual question answering (VQA) task is less exploited and is more susceptible to language priors and…
Remote sensing (RS) large vision-language models (LVLMs) have shown strong promise across visual grounding (VG) tasks. However, existing RS VG datasets predominantly rely on explicit referring expressions-such as relative position, relative…
The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability, resulting in their mediocre performance. While some…
Recent advancements in Large Vision-Language Models (VLMs) have shown great promise in natural image domains, allowing users to hold a dialogue about given visual content. However, such general-domain VLMs perform poorly for Remote Sensing…
An embodied AI assistant operating on egocentric video must integrate spatial cues across time - for instance, determining where an object A, glimpsed a few moments ago lies relative to an object B encountered later. We introduce…
Visual Question Answering (VQA) is increasingly used in diverse applications ranging from general visual reasoning to safety-critical domains such as medical imaging and autonomous systems, where models must provide not only accurate…
A key frontier for Multimodal Large Language Models (MLLMs) is the ability to perform deep mathematical and spatial reasoning directly from images, moving beyond their established success in semantic description. Mathematical surface plots…
Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on comprehensive 3D data inputs, such as point…