相关论文: PanoWorld: Towards Spatial Supersensing in 360$^\c…
Multimodal Large Language Models (MLLMs) require comprehensive visual inputs to achieve dense understanding of the physical world. While existing MLLMs demonstrate impressive world understanding capabilities through limited field-of-view…
Generating a consistent whole-house VR tour from a floorplan and style reference requires both photorealistic panoramas and cross-view spatial coherence. Pure 2D generators produce appealing single panoramas but re-imagine geometry and…
In panorama understanding, the widely used equirectangular projection (ERP) entails boundary discontinuity and spatial distortion. It severely deteriorates the conventional CNNs and vision Transformers on panoramas. In this paper, we…
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…
3D Visual Grounding (3DVG) is a critical bridge from vision-language perception to robotics, requiring both language understanding and 3D scene reasoning. Traditional supervised models leverage explicit 3D geometry but exhibit limited…
Understanding perspective is fundamental to human visual perception, yet the extent to which multimodal large language models (MLLMs) internalize perspective geometry remains unclear. We introduce MMPerspective, the first benchmark…
Recent advancements in Multimodal Large Language Models (MLLMs) have significantly enhanced performance on 2D visual tasks. However, improving their spatial intelligence remains a challenge. Existing 3D MLLMs always rely on additional 3D or…
Spatial reasoning is a core aspect of human intelligence that allows perception, inference and planning in 3D environments. However, current vision-language models (VLMs) struggle to maintain geometric coherence and cross-view consistency…
Current Large Multimodal Models (LMMs) in Earth Observation typically neglect the critical "vertical" dimension, limiting their reasoning capabilities in complex remote sensing geometries and disaster scenarios where physical spatial…
Generating a complete and explorable 360-degree visual world enables a wide range of downstream applications. While prior works have advanced the field, they remain constrained by either narrow field-of-view limitations, which hinder the…
Multimodal Large Language Models (MLLMs) show strong visual perception, yet remain limited in reasoning about space under changing viewpoints. We study this challenge as Perspective-Conditioned Spatial Reasoning (PCSR) in 360-degree…
Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and interactions across multiple viewpoints. However, progress in…
Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understanding of Multimodal Large Language Models (MLLMs), where…
Zero-shot object navigation (ZSON) in unseen environments remains a challenging problem for household robots, requiring strong perceptual understanding and decision-making capabilities. While recent methods leverage metric maps and Large…
Benchmarking spatial reasoning in multimodal large language models (MLLMs) has attracted growing interest in computer vision due to its importance for embodied AI and other agentic systems that require precise interaction with the physical…
We present PanoWorld, a panoramic video world model that generates geometry-consistent 360$\degree$ video from a single image and a caption. Existing panoramic video methods optimize primarily for visual realism and do not explicitly…
Recent multimodal large language models (MLLMs) have made remarkable progress in visual understanding and language-based reasoning, yet they lack a persistent world-centered representation for spatially consistent reasoning in 3D…
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…
Multi-view understanding, the ability to reconcile visual information across diverse viewpoints for effective navigation, manipulation, and 3D scene comprehension, is a fundamental challenge in Multi-Modal Large Language Models (MLLMs) to…
Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content, but significant challenges persist in tasks requiring cross-viewpoint understanding and spatial reasoning. We…