Unlocking spatial reasoning in Multimodal Large Language Models (MLLMs) is crucial for enabling intelligent interaction with 3D environments. While prior efforts often rely on explicit 3D inputs or specialized model architectures, we ask: can MLLMs reason about 3D space using only structured 2D representations derived from perception? In this work, we introduce Struct2D, a perception-guided prompting framework that combines bird’s-eye-view (BEV) images with object marks and object-centric metadata, optionally incorporating egocentric keyframes when needed. Using Struct2D, we conduct an in-depth zero-shot analysis of closed-source MLLMs (e.g., GPT-o3) and find that they exhibit surprisingly strong spatial reasoning abilities when provided with projected 2D inputs, effectively handling tasks such as relative direction estimation and route planning. Motivated by these findings, we construct a large-scale instructional tuning dataset, \textbf{Struct2D-Set}, using an automated pipeline that generates fine-grained QA pairs grounded in 3D indoor scenes. We then fine-tune an open-source MLLM (Qwen2.5VL) using Struct2D-Set, relying on noisy 3D perception rather than ground-truth annotations. Despite this, the tuned model achieves strong performance across multiple spatial reasoning benchmarks, including 3D question answering, captioning, and object grounding, spanning eight diverse reasoning categories. Our approach demonstrates that structured 2D inputs can effectively bridge perception and language reasoning in MLLMs—without requiring explicit 3D representations as input. We will release both our code and dataset to support future research.

Abstract We have witnessed significant progress in human-object interaction (HOI) detection. However, relying solely on mAP (mean Average Precision) scores as a summary metric does not provide sufficient insight into the nuances of model performance ( e.g. , why one model outperforms another), which can hinder further innovation in this field. To address this issue, we introduce a diagnosis toolbox in this paper to offer a detailed quantitative breakdown of HOI detection models, inspired by the success of object detection diagnosis tools. We first conduct a holistic investigation into the HOI detection pipeline. By defining a set of errors and using oracles to fix each one, we quantitatively analyze the significance of different errors based on the mAP improvement gained from fixing them. Next, we explore the two key sub-tasks of HOI detection: human-object pair localization and interaction classification. For the pair localization task, we compute the coverage of ground-truth human-object pairs and assess the noisiness of the localization results. For the classification task, we measure a model’s ability to distinguish between positive and negative detection results and to classify actual interactions when human-object pairs are correctly localized. We analyze eight state-of-the-art HOI detection models, providing valuable diagnostic insights to guide future research. For instance, our diagnosis reveals that the state-of-the-art model RLIPv2 outperforms others primarily due to its significant improvement in multi-label interaction classification accuracy. Our toolbox is applicable across various methods and datasets and is available at https://neu-vi.github.io/Diag-HOI/ .

Zero-shot referring expression comprehension aims at localizing bounding boxes in an image corresponding to provided textual prompts, which requires: (i) afine-grained disentanglement of complex visual scene and textual context, and (ii) a capacity to understand relationships among disentangled entities. Unfortunately, existing large vision-language alignment (VLA) models, e.g., CLIP, struggle with both aspects so cannot be directly used for this task. To mitigate this gap, we leverage large foundation models to disentangle both images and texts into triplets in the for-mat of (subject, predicate, object). After that, grounding is accomplished by calculating the structural similarity matrix between visual and textual triplets with a VLA model, and subsequently propagate it to an instance-level similarity matrix. Furthermore, to equip VLA models with the ability of relationship understanding, we design a triplet-matching objective to fine-tune the VLA models on a collection of curated dataset containing abundant entity relationships. Experiments demonstrate that our visual grounding performance increase of up to 19.5% over the SOTA zero-shot model on RefCOCO/+/g. On the more challenging Who's Waldo dataset, our zero-shot approach achieves comparable accuracy to the fully super-vised model. Code is available at https://github.com/Show-han/Zeroshot_REC.

Visual relationship understanding has been studied separately in human-object interaction(HOI) detection, scene graph generation(SGG), and referring relationships(RR) tasks. Given the complexity and interconnectedness of these tasks, it is crucial to have a flexible framework that can effectively address these tasks in a cohesive manner. In this work, we propose FleVRS, a single model that seamlessly integrates the above three aspects in standard and promptable visual relationship segmentation, and further possesses the capability for open-vocabulary segmentation to adapt to novel scenarios. FleVRS leverages the synergy between text and image modalities, to ground various types of relationships from images and use textual features from vision-language models to visual conceptual understanding. Empirical validation across various datasets demonstrates that our framework outperforms existing models in standard, promptable, and open-vocabulary tasks, e.g., +1.9 $mAP$ on HICO-DET, +11.4 $Acc$ on VRD, +4.7 $mAP$ on unseen HICO-DET. Our FleVRS represents a significant step towards a more intuitive, comprehensive, and scalable understanding of visual relationships.

Building an intelligent defect segmentation system for textured images has attracted much increasing attention in both research and industrial communities, due to its significance values in the practical applications of industrial inspection and quality control. Previous models learned the classical classifiers for segmentation by designing handcrafted features. However, defect segmentation of textured surface images poses challenges such as ambiguous shapes and sizes of defects along with varying textures and patterns in the images. Thus, hand-crafted features based segmentation methods can only be applied to particular types of textured images. To this end, it is desirable to learn a general deep learning based representation for the automatic segmentation of defects. Furthermore, it is relatively less study in efficiently extracting the deep features in the frequency domain, which, nevertheless, should be very important to understand the patterns of textured images. In this paper, we propose a novel defect segmentation deep network - Main-Secondary Network (MS-Net). Our MS-Net is trained to model both features from the spatial domain and the frequency domain, where wavelet transform is utilized to extract discriminative information from the frequency domain. Extensive experiments show the effectiveness of our MS-Net.

Calibrating narrow field of view soccer cameras is challenging because there are very few field markings in the image. Unlike previous solutions, we propose a two-point method, which requires only two point correspondences given the prior knowledge of base location and orientation of a pan-tilt-zoom (PTZ) camera. We deploy this new calibration method to annotate pan-tilt-zoom data from soccer videos. The collected data are used as references for new images. We also propose a fast random forest method to predict pan-tilt angles without image-to-image feature matching, leading to an efficient calibration method for new images. We demonstrate our system on synthetic data and two real soccer datasets. Our two-point approach achieves superior performance over the state-of-the-art method.