Multi-object grounding in 3D scenes involves localizing multiple objects based on natural language input. While previous work has primarily focused on single-object grounding, real-world scenarios often demand the localization of several objects. To tackle this challenge, we propose Hierarchical Contrastive Siamese Transformers (H-COST), which employs a Hierarchical Processing strategy to progressively refine object localization, enhancing the understanding of complex language instructions. Additionally, we introduce a Contrastive Siamese Transformer framework, where two networks with the identical structure are used: one auxiliary network processes robust object relations from ground-truth labels to guide and enhance the second network, the reference network, which operates on segmented point-cloud data. This contrastive mechanism strengthens the model' s semantic understanding and significantly enhances its ability to process complex point-cloud data. Our approach outperforms previous state-of-the-art methods by 9.5% on challenging multi-object grounding benchmarks.
Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image editing remains a challenging problem, requiring precise modifications while preserving visual coherence. Existing text-based instructional editing methods struggle with localized shape and layout transformations, often introducing unintended global changes. Image interaction-based approaches offer better accuracy but require manual human effort to provide precise guidance. To reduce this manual effort while maintaining a high image editing accuracy, in this paper, we propose POEM, a framework for Precise Object-level Editing using Multimodal Large Language Models (MLLMs). POEM leverages MLLMs to analyze instructional prompts and generate precise object masks before and after transformation, enabling fine-grained control without extensive user input. This structured reasoning stage guides the diffusion-based editing process, ensuring accurate object localization and transformation. To evaluate our approach, we introduce VOCEdits, a benchmark dataset based on PASCAL VOC 2012, augmented with instructional edit prompts, ground-truth transformations, and precise object masks. Experimental results show that POEM outperforms existing text-based image editing approaches in precision and reliability while reducing manual effort compared to interaction-based methods.
Modern Vision-Language Models (VLMs) exhibit remarkable visual and linguistic capabilities, achieving impressive performance in various tasks such as image recognition and object localization. However, their effectiveness in fine-grained tasks remains an open question. In everyday scenarios, individuals encountering design materials, such as magazines, typography tutorials, research papers, or branding content, may wish to identify aesthetically pleasing fonts used in the text. Given their multimodal capabilities and free accessibility, many VLMs are often considered potential tools for font recognition. This raises a fundamental question: Do VLMs truly possess the capability to recognize fonts? To investigate this, we introduce the Font Recognition Benchmark (FRB), a compact and well-structured dataset comprising 15 commonly used fonts. FRB includes two versions: (i) an easy version, where 10 sentences are rendered in different fonts, and (ii) a hard version, where each text sample consists of the names of the 15 fonts themselves, introducing a stroop effect that challenges model perception. Through extensive evaluation of various VLMs on font recognition tasks, we arrive at the following key findings: (i) Current VLMs exhibit limited font recognition capabilities, with many state-of-the-art models failing to achieve satisfactory performance. (ii) Few-shot learning and Chain-of-Thought (CoT) prompting provide minimal benefits in improving font recognition accuracy across different VLMs. (iii) Attention analysis sheds light on the inherent limitations of VLMs in capturing semantic features.
Weakly supervised object localization (WSOL) methods allow training models to classify images and localize ROIs. WSOL only requires low-cost image-class annotations yet provides a visually interpretable classifier, which is important in histology image analysis. Standard WSOL methods rely on class activation mapping (CAM) methods to produce spatial localization maps according to a single- or two-step strategy. While both strategies have made significant progress, they still face several limitations with histology images. Single-step methods can easily result in under- or over-activation due to the limited visual ROI saliency in histology images and the limited localization cues. They also face the well-known issue of asynchronous convergence between classification and localization tasks. The two-step approach is sub-optimal because it is tied to a frozen classifier, limiting the capacity for localization. Moreover, these methods also struggle when applied to out-of-distribution (OOD) datasets. In this paper, a multi-task approach for WSOL is introduced for simultaneous training of both tasks to address the asynchronous convergence problem. In particular, localization is performed in the pixel-feature space of an image encoder that is shared with classification. This allows learning discriminant features and accurate delineation of foreground/background regions to support ROI localization and image classification. We propose PixelCAM, a cost-effective foreground/background pixel-wise classifier in the pixel-feature space that allows for spatial object localization. PixelCAM is trained using pixel pseudo-labels collected from a pretrained WSOL model. Both image and pixel-wise classifiers are trained simultaneously using standard gradient descent. In addition, our pixel classifier can easily be integrated into CNN- and transformer-based architectures without any modifications.
We propose a unified framework that integrates object detection (OD) and visual grounding (VG) for remote sensing (RS) imagery. To support conventional OD and establish an intuitive prior for VG task, we fine-tune an open-set object detector using referring expression data, framing it as a partially supervised OD task. In the first stage, we construct a graph representation of each image, comprising object queries, class embeddings, and proposal locations. Then, our task-aware architecture processes this graph to perform the VG task. The model consists of: (i) a multi-branch network that integrates spatial, visual, and categorical features to generate task-aware proposals, and (ii) an object reasoning network that assigns probabilities across proposals, followed by a soft selection mechanism for final referring object localization. Our model demonstrates superior performance on the OPT-RSVG and DIOR-RSVG datasets, achieving significant improvements over state-of-the-art methods while retaining classical OD capabilities. The code will be available in our repository: \url{https://github.com/rd20karim/MB-ORES}.
The task of LiDAR-based 3D Open-Vocabulary Detection (3D OVD) requires the detector to learn to detect novel objects from point clouds without off-the-shelf training labels. Previous methods focus on the learning of object-level representations and ignore the scene-level information, thus it is hard to distinguish objects with similar classes. In this work, we propose a Global-Local Collaborative Reason and Debate with PSL (GLRD) framework for the 3D OVD task, considering both local object-level information and global scene-level information. Specifically, LLM is utilized to perform common sense reasoning based on object-level and scene-level information, where the detection result is refined accordingly. To further boost the LLM's ability of precise decisions, we also design a probabilistic soft logic solver (OV-PSL) to search for the optimal solution, and a debate scheme to confirm the class of confusable objects. In addition, to alleviate the uneven distribution of classes, a static balance scheme (SBC) and a dynamic balance scheme (DBC) are designed. In addition, to reduce the influence of noise in data and training, we further propose Reflected Pseudo Labels Generation (RPLG) and Background-Aware Object Localization (BAOL). Extensive experiments conducted on ScanNet and SUN RGB-D demonstrate the superiority of GLRD, where absolute improvements in mean average precision are $+2.82\%$ on SUN RGB-D and $+3.72\%$ on ScanNet in the partial open-vocabulary setting. In the full open-vocabulary setting, the absolute improvements in mean average precision are $+4.03\%$ on ScanNet and $+14.11\%$ on SUN RGB-D.
Referring expression comprehension (REC) aims at achieving object localization based on natural language descriptions. However, existing REC approaches are constrained by object category descriptions and single-attribute intention descriptions, hindering their application in real-world scenarios. In natural human-robot interactions, users often express their desires through individual states and intentions, accompanied by guiding gestures, rather than detailed object descriptions. To address this challenge, we propose Multi-ref EC, a novel task framework that integrates state descriptions, derived intentions, and embodied gestures to locate target objects. We introduce the State-Intention-Gesture Attributes Reference (SIGAR) dataset, which combines state and intention expressions with embodied references. Through extensive experiments with various baseline models on SIGAR, we demonstrate that properly ordered multi-attribute references contribute to improved localization performance, revealing that single-attribute reference is insufficient for natural human-robot interaction scenarios. Our findings underscore the importance of multi-attribute reference expressions in advancing visual-language understanding.
Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in 3D data, where approaches rely exclusively on 3D motion, despite its several challenges. In this paper, we present a novel framework that leverages advances in 2D object discovery which are based on 2D motion to exploit the advantages of such motion cues being more flexible and generalizable and to bridge the gap between 2D and 3D modalities. Our primary contributions are twofold: (i) we introduce DIOD-3D, the first baseline for multi-object discovery in 3D data using 2D motion, incorporating scene completion as an auxiliary task to enable dense object localization from sparse input data; (ii) we develop xMOD, a cross-modal training framework that integrates 2D and 3D data while always using 2D motion cues. xMOD employs a teacher-student training paradigm across the two modalities to mitigate confirmation bias by leveraging the domain gap. During inference, the model supports both RGB-only and point cloud-only inputs. Additionally, we propose a late-fusion technique tailored to our pipeline that further enhances performance when both modalities are available at inference. We evaluate our approach extensively on synthetic (TRIP-PD) and challenging real-world datasets (KITTI and Waymo). Notably, our approach yields a substantial performance improvement compared with the 2D object discovery state-of-the-art on all datasets with gains ranging from +8.7 to +15.1 in F1@50 score. The code is available at https://github.com/CEA-LIST/xMOD
Panoramic imagery, with its 360{\deg} field of view, offers comprehensive information to support Multi-Object Tracking (MOT) in capturing spatial and temporal relationships of surrounding objects. However, most MOT algorithms are tailored for pinhole images with limited views, impairing their effectiveness in panoramic settings. Additionally, panoramic image distortions, such as resolution loss, geometric deformation, and uneven lighting, hinder direct adaptation of existing MOT methods, leading to significant performance degradation. To address these challenges, we propose OmniTrack, an omnidirectional MOT framework that incorporates Tracklet Management to introduce temporal cues, FlexiTrack Instances for object localization and association, and the CircularStatE Module to alleviate image and geometric distortions. This integration enables tracking in panoramic field-of-view scenarios, even under rapid sensor motion. To mitigate the lack of panoramic MOT datasets, we introduce the QuadTrack dataset--a comprehensive panoramic dataset collected by a quadruped robot, featuring diverse challenges such as panoramic fields of view, intense motion, and complex environments. Extensive experiments on the public JRDB dataset and the newly introduced QuadTrack benchmark demonstrate the state-of-the-art performance of the proposed framework. OmniTrack achieves a HOTA score of 26.92% on JRDB, representing an improvement of 3.43%, and further achieves 23.45% on QuadTrack, surpassing the baseline by 6.81%. The established dataset and source code are available at https://github.com/xifen523/OmniTrack.
Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene understanding via flexible, scene-level modality alignment. Unlike traditional methods that require aligned modality data for every object instance, CrossOver learns a unified, modality-agnostic embedding space for scenes by aligning modalities - RGB images, point clouds, CAD models, floorplans, and text descriptions - with relaxed constraints and without explicit object semantics. Leveraging dimensionality-specific encoders, a multi-stage training pipeline, and emergent cross-modal behaviors, CrossOver supports robust scene retrieval and object localization, even with missing modalities. Evaluations on ScanNet and 3RScan datasets show its superior performance across diverse metrics, highlighting adaptability for real-world applications in 3D scene understanding.
We introduce Dr. Splat, a novel approach for open-vocabulary 3D scene understanding leveraging 3D Gaussian Splatting. Unlike existing language-embedded 3DGS methods, which rely on a rendering process, our method directly associates language-aligned CLIP embeddings with 3D Gaussians for holistic 3D scene understanding. The key of our method is a language feature registration technique where CLIP embeddings are assigned to the dominant Gaussians intersected by each pixel-ray. Moreover, we integrate Product Quantization (PQ) trained on general large-scale image data to compactly represent embeddings without per-scene optimization. Experiments demonstrate that our approach significantly outperforms existing approaches in 3D perception benchmarks, such as open-vocabulary 3D semantic segmentation, 3D object localization, and 3D object selection tasks. For video results, please visit : https://drsplat.github.io/
Accurately locating key moments within long videos is crucial for solving long video understanding (LVU) tasks. However, existing benchmarks are either severely limited in terms of video length and task diversity, or they focus solely on the end-to-end LVU performance, making them inappropriate for evaluating whether key moments can be accurately accessed. To address this challenge, we propose MomentSeeker, a novel benchmark for long-video moment retrieval (LMVR), distinguished by the following features. First, it is created based on long and diverse videos, averaging over 1200 seconds in duration and collected from various domains, e.g., movie, anomaly, egocentric, and sports. Second, it covers a variety of real-world scenarios in three levels: global-level, event-level, object-level, covering common tasks like action recognition, object localization, and causal reasoning, etc. Third, it incorporates rich forms of queries, including text-only queries, image-conditioned queries, and video-conditioned queries. On top of MomentSeeker, we conduct comprehensive experiments for both generation-based approaches (directly using MLLMs) and retrieval-based approaches (leveraging video retrievers). Our results reveal the significant challenges in long-video moment retrieval in terms of accuracy and efficiency, despite improvements from the latest long-video MLLMs and task-specific fine-tuning. We have publicly released MomentSeeker(https://yhy-2000.github.io/MomentSeeker/) to facilitate future research in this area.
We introduce Qwen2.5-VL, the latest flagship model of Qwen vision-language series, which demonstrates significant advancements in both foundational capabilities and innovative functionalities. Qwen2.5-VL achieves a major leap forward in understanding and interacting with the world through enhanced visual recognition, precise object localization, robust document parsing, and long-video comprehension. A standout feature of Qwen2.5-VL is its ability to localize objects using bounding boxes or points accurately. It provides robust structured data extraction from invoices, forms, and tables, as well as detailed analysis of charts, diagrams, and layouts. To handle complex inputs, Qwen2.5-VL introduces dynamic resolution processing and absolute time encoding, enabling it to process images of varying sizes and videos of extended durations (up to hours) with second-level event localization. This allows the model to natively perceive spatial scales and temporal dynamics without relying on traditional normalization techniques. By training a native dynamic-resolution Vision Transformer (ViT) from scratch and incorporating Window Attention, we reduce computational overhead while maintaining native resolution. As a result, Qwen2.5-VL excels not only in static image and document understanding but also as an interactive visual agent capable of reasoning, tool usage, and task execution in real-world scenarios such as operating computers and mobile devices. Qwen2.5-VL is available in three sizes, addressing diverse use cases from edge AI to high-performance computing. The flagship Qwen2.5-VL-72B model matches state-of-the-art models like GPT-4o and Claude 3.5 Sonnet, particularly excelling in document and diagram understanding. Additionally, Qwen2.5-VL maintains robust linguistic performance, preserving the core language competencies of the Qwen2.5 LLM.
Weakly supervised landslide extraction aims to identify landslide regions from remote sensing data using models trained with weak labels, particularly image-level labels. However, it is often challenged by the imprecise boundaries of the extracted objects due to the lack of pixel-wise supervision and the properties of landslide objects. To tackle these issues, we propose a simple yet effective method by auto-prompting the Segment Anything Model (SAM), i.e., APSAM. Instead of depending on high-quality class activation maps (CAMs) for pseudo-labeling or fine-tuning SAM, our method directly yields fine-grained segmentation masks from SAM inference through prompt engineering. Specifically, it adaptively generates hybrid prompts from the CAMs obtained by an object localization network. To provide sufficient information for SAM prompting, an adaptive prompt generation (APG) algorithm is designed to fully leverage the visual patterns of CAMs, enabling the efficient generation of pseudo-masks for landslide extraction. These informative prompts are able to identify the extent of landslide areas (box prompts) and denote the centers of landslide objects (point prompts), guiding SAM in landslide segmentation. Experimental results on high-resolution aerial and satellite datasets demonstrate the effectiveness of our method, achieving improvements of at least 3.0\% in F1 score and 3.69\% in IoU compared to other state-of-the-art methods. The source codes and datasets will be available at https://github.com/zxk688.
Weakly supervised object localization (WSOL) using classification models trained with only image-class labels remains an important challenge in computer vision. Given their reliance on classification objectives, traditional WSOL methods like class activation mapping focus on the most discriminative object parts, often missing the full spatial extent. In contrast, recent WSOL methods based on vision-language models like CLIP require ground truth classes or external classifiers to produce a localization map, limiting their deployment in downstream tasks. Moreover, methods like GenPromp attempt to address these issues but introduce considerable complexity due to their reliance on conditional denoising processes and intricate prompt learning. This paper introduces Text Distillation for Localization (TeD-Loc), an approach that directly distills knowledge from CLIP text embeddings into the model backbone and produces patch-level localization. Multiple instance learning of these image patches allows for accurate localization and classification using one model without requiring external classifiers. Such integration of textual and visual modalities addresses the longstanding challenge of achieving accurate localization and classification concurrently, as WSOL methods in the literature typically converge at different epochs. Extensive experiments show that leveraging text embeddings and localization cues provides a cost-effective WSOL model. TeD-Loc improves Top-1 LOC accuracy over state-of-the-art models by about 5% on both CUB and ILSVRC datasets, while significantly reducing computational complexity compared to GenPromp.
Tracking and acquiring simultaneous optical images of randomly moving targets obscured by scattering media remains a challenging problem of importance to many applications that require precise object localization and identification. In this work we develop an end-to-end neuromorphic optical engineering and computational approach to demonstrate how to track and image normally invisible objects by combining an event detecting camera with a multistage neuromorphic deep learning strategy. Photons emerging from dense scattering media are detected by the event camera and converted to pixel-wise asynchronized spike trains - a first step in isolating object-specific information from the dominant uninformative background. Spiking data is fed into a deep spiking neural network (SNN) engine where object tracking and image reconstruction are performed by two separate yet interconnected modules running in parallel in discrete time steps over the event duration. Through benchtop experiments we demonstrate tracking and imaging randomly moving objects in dense turbid media as well as image reconstruction of spatially stationary but optically dynamic objects. Standardized character sets serve as representative proxies for geometrically complex objects, underscoring the method's generality. The results highlight the advantages of a fully neuromorphic approach in meeting a major imaging technology with high computational efficiency and low power consumption.
Monocular 3D object detection is a challenging task in autonomous systems due to the lack of explicit depth information in single-view images. Existing methods often depend on external depth estimators or expensive sensors, which increase computational complexity and hinder real-time performance. To overcome these limitations, we propose AuxDepthNet, an efficient framework for real-time monocular 3D object detection that eliminates the reliance on external depth maps or pre-trained depth models. AuxDepthNet introduces two key components: the Auxiliary Depth Feature (ADF) module, which implicitly learns depth-sensitive features to improve spatial reasoning and computational efficiency, and the Depth Position Mapping (DPM) module, which embeds depth positional information directly into the detection process to enable accurate object localization and 3D bounding box regression. Leveraging the DepthFusion Transformer architecture, AuxDepthNet globally integrates visual and depth-sensitive features through depth-guided interactions, ensuring robust and efficient detection. Extensive experiments on the KITTI dataset show that AuxDepthNet achieves state-of-the-art performance, with $\text{AP}_{3D}$ scores of 24.72\% (Easy), 18.63\% (Moderate), and 15.31\% (Hard), and $\text{AP}_{\text{BEV}}$ scores of 34.11\% (Easy), 25.18\% (Moderate), and 21.90\% (Hard) at an IoU threshold of 0.7.
Visual Language Models have demonstrated remarkable capabilities across tasks, including visual question answering and image captioning. However, most models rely on text-based instructions, limiting their effectiveness in human-machine interactions. Moreover, the quality of language models depends on reasoning and prompting techniques, such as COT, which remain underexplored when using speech instructions. To address these challenges, we propose SilVar, a novel end-to-end multimodal model that uses speech instructions for reasoning in visual question answering. In addition, we investigate reasoning techniques with levels including conversational, simple, and complex speech instruction. SilVar is built upon CLIP, Whisper, and LLaMA 3.1-8B, enabling intuitive interactions by allowing users to provide verbal or text instructions. To this end, we introduce a dataset designed to challenge models with speech-based reasoning tasks for object localization. This dataset enhances the model ability to process and explain visual scenes from spoken input, moving beyond object recognition to reasoning-based interactions. The experiments show that SilVar achieves SOTA performance on the MMMU and ScienceQA benchmarks despite the challenge of speech-based instructions. We believe SilVar will inspire next-generation multimodal reasoning models, toward expert artificial general intelligence. Our code and dataset are available here.
The integration of Large Vision-Language Models (LVLMs) such as OpenAI's GPT-4 Vision into various sectors has marked a significant evolution in the field of artificial intelligence, particularly in the analysis and interpretation of visual data. This paper explores the practical application of GPT-4 Vision in the construction industry, focusing on its capabilities in monitoring and tracking the progress of construction projects. Utilizing high-resolution aerial imagery of construction sites, the study examines how GPT-4 Vision performs detailed scene analysis and tracks developmental changes over time. The findings demonstrate that while GPT-4 Vision is proficient in identifying construction stages, materials, and machinery, it faces challenges with precise object localization and segmentation. Despite these limitations, the potential for future advancements in this technology is considerable. This research not only highlights the current state and opportunities of using LVLMs in construction but also discusses future directions for enhancing the model's utility through domain-specific training and integration with other computer vision techniques and digital twins.
3D Gaussian Splatting has recently gained traction for its efficient training and real-time rendering. While the vanilla Gaussian Splatting representation is mainly designed for view synthesis, more recent works investigated how to extend it with scene understanding and language features. However, existing methods lack a detailed comprehension of scenes, limiting their ability to segment and interpret complex structures. To this end, We introduce SuperGSeg, a novel approach that fosters cohesive, context-aware scene representation by disentangling segmentation and language field distillation. SuperGSeg first employs neural Gaussians to learn instance and hierarchical segmentation features from multi-view images with the aid of off-the-shelf 2D masks. These features are then leveraged to create a sparse set of what we call Super-Gaussians. Super-Gaussians facilitate the distillation of 2D language features into 3D space. Through Super-Gaussians, our method enables high-dimensional language feature rendering without extreme increases in GPU memory. Extensive experiments demonstrate that SuperGSeg outperforms prior works on both open-vocabulary object localization and semantic segmentation tasks.