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

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…

Humans build viewpoint-independent cognitive maps through navigation, enabling intuitive reasoning about object permanence and spatial relations. We argue that multimodal large language models (MLLMs), despite extensive video training, lack…

Deep learning has attained remarkable success in many 3D visual recognition tasks, including shape classification, object detection, and semantic segmentation. However, many of these results rely on manually collecting densely annotated…

Large Language Models (LLMs) have undergone rapid progress, largely attributed to reinforcement learning on complex reasoning tasks. In contrast, while spatial intelligence is fundamental for Vision-Language Models (VLMs) in real-world…

Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either…

The ability to understand the ways to interact with objects from visual cues, a.k.a. visual affordance, is essential to vision-guided robotic research. This involves categorizing, segmenting and reasoning of visual affordance. Relevant…

Vision-language models (VLMs) struggle with 3D-related tasks such as spatial cognition and physical understanding, which are crucial for real-world applications like robotics and embodied agents. We attribute this to a modality gap between…

Spatial reasoning is a fundamental capability for embodied intelligence, especially for fine-grained manipulation tasks such as robotic assembly. While recent vision-language models (VLMs) exhibit preliminary spatial awareness, they largely…

Dense indoor scene modeling from 2D images has been bottlenecked due to the absence of depth information and cluttered occlusions. We present an automatic indoor scene modeling approach using deep features from neural networks. Given a…

After the incredible success of deep learning in the computer vision domain, there has been much interest in applying Convolutional Network (ConvNet) features in robotic fields such as visual navigation and SLAM. Unfortunately, there are…

Representing and understanding 3D environments in a structured manner is crucial for autonomous agents to navigate and reason about their surroundings. While traditional Simultaneous Localization and Mapping (SLAM) methods generate metric…

Vision-language models (VLMs) have achieved impressive results on single-view vision tasks, but lack the multi-view spatial reasoning capabilities essential for embodied AI systems to understand 3D environments and manipulate objects across…

Sketch-based modeling strives to bring the ease and immediacy of drawing to the 3D world. However, while drawings are easy for humans to create, they are very challenging for computers to interpret due to their sparsity and ambiguity. We…

With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…

Stable Diffusion models have made remarkable strides in generating photorealistic images from text prompts but often falter when tasked with accurately representing complex spatial arrangements, particularly involving intricate 3D…

To enable robots to comprehend high-level human instructions and perform complex tasks, a key challenge lies in achieving comprehensive scene understanding: interpreting and interacting with the 3D environment in a meaningful way. This…

Spatial reasoning is central to navigation and robotics, yet measuring model capabilities on these tasks remains difficult. Existing benchmarks evaluate models in a one-shot setting, requiring full solution generation in a single response,…

The recent development of Large Language Models (LLMs) with strong reasoning ability has driven research in various domains such as mathematics, coding, and scientific discovery. Meanwhile, 3D visual grounding, as a fundamental task in 3D…

Structured tables are essential for conveying high-density information in professional domains such as finance, healthcare, and scientific research. Despite the progress in Multimodal Large Language Models (MLLMs), reasoning performance…

Humans possess the visual-spatial intelligence to remember spaces from sequential visual observations. However, can Multimodal Large Language Models (MLLMs) trained on million-scale video datasets also ``think in space'' from videos? We…