Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable performance in zero-shot classification tasks, yet their efficacy in handling complex multi-object scenarios remains challenging. This study presents a comprehensive analysis of CLIP's performance limitations in multi-object contexts through controlled experiments. We introduce two custom datasets, SimCO and CompCO, to evaluate CLIP's image and text encoders in various multi-object configurations. Our findings reveal significant biases in both encoders: the image encoder favors larger objects, while the text encoder prioritizes objects mentioned first in descriptions. We hypothesize these biases originate from CLIP's training process and provide evidence through analyses of the COCO dataset and CLIP's training progression. Additionally, we extend our investigation to Stable Diffusion models, revealing that biases in the CLIP text encoder significantly impact text-to-image generation tasks. Our experiments demonstrate how these biases affect CLIP's performance in image-caption matching and generation tasks, particularly when manipulating object sizes and their order in captions. This work contributes valuable insights into CLIP's behavior in complex visual environments and highlights areas for improvement in future vision-language models.
Significant advancements have been achieved in the realm of understanding poses and interactions of two hands manipulating an object. The emergence of augmented reality (AR) and virtual reality (VR) technologies has heightened the demand for real-time performance in these applications. However, current state-of-the-art models often exhibit promising results at the expense of substantial computational overhead. In this paper, we present a query-optimized real-time Transformer (QORT-Former), the first Transformer-based real-time framework for 3D pose estimation of two hands and an object. We first limit the number of queries and decoders to meet the efficiency requirement. Given limited number of queries and decoders, we propose to optimize queries which are taken as input to the Transformer decoder, to secure better accuracy: (1) we propose to divide queries into three types (a left hand query, a right hand query and an object query) and enhance query features (2) by using the contact information between hands and an object and (3) by using three-step update of enhanced image and query features with respect to one another. With proposed methods, we achieved real-time pose estimation performance using just 108 queries and 1 decoder (53.5 FPS on an RTX 3090TI GPU). Surpassing state-of-the-art results on the H2O dataset by 17.6% (left hand), 22.8% (right hand), and 27.2% (object), as well as on the FPHA dataset by 5.3% (right hand) and 10.4% (object), our method excels in accuracy. Additionally, it sets the state-of-the-art in interaction recognition, maintaining real-time efficiency with an off-the-shelf action recognition module.
Bird's-eye-view (BEV) representations play a crucial role in autonomous driving tasks. Despite recent advancements in BEV generation, inherent noise, stemming from sensor limitations and the learning process, remains largely unaddressed, resulting in suboptimal BEV representations that adversely impact the performance of downstream tasks. To address this, we propose BEVDiffuser, a novel diffusion model that effectively denoises BEV feature maps using the ground-truth object layout as guidance. BEVDiffuser can be operated in a plug-and-play manner during training time to enhance existing BEV models without requiring any architectural modifications. Extensive experiments on the challenging nuScenes dataset demonstrate BEVDiffuser's exceptional denoising and generation capabilities, which enable significant enhancement to existing BEV models, as evidenced by notable improvements of 12.3\% in mAP and 10.1\% in NDS achieved for 3D object detection without introducing additional computational complexity. Moreover, substantial improvements in long-tail object detection and under challenging weather and lighting conditions further validate BEVDiffuser's effectiveness in denoising and enhancing BEV representations.
Detecting 3D objects in point clouds plays a crucial role in autonomous driving systems. Recently, advanced multi-modal methods incorporating camera information have achieved notable performance. For a safe and effective autonomous driving system, algorithms that excel not only in accuracy but also in speed and low latency are essential. However, existing algorithms fail to meet these requirements due to the latency and bandwidth limitations of fixed frame rate sensors, e.g., LiDAR and camera. To address this limitation, we introduce asynchronous event cameras into 3D object detection for the first time. We leverage their high temporal resolution and low bandwidth to enable high-speed 3D object detection. Our method enables detection even during inter-frame intervals when synchronized data is unavailable, by retrieving previous 3D information through the event camera. Furthermore, we introduce the first event-based 3D object detection dataset, DSEC-3DOD, which includes ground-truth 3D bounding boxes at 100 FPS, establishing the first benchmark for event-based 3D detectors. The code and dataset are available at https://github.com/mickeykang16/Ev3DOD.
In this work, we present CoCal, an interpretable and consistent object parsing framework based on dictionary-based mask transformer. Designed around Contrastive Components and Logical Constraints, CoCal rethinks existing cluster-based mask transformer architectures used in segmentation; Specifically, CoCal utilizes a set of dictionary components, with each component being explicitly linked to a specific semantic class. To advance this concept, CoCal introduces a hierarchical formulation of dictionary components that aligns with the semantic hierarchy. This is achieved through the integration of both within-level contrastive components and cross-level logical constraints. Concretely, CoCal employs a component-wise contrastive algorithm at each semantic level, enabling the contrasting of dictionary components within the same class against those from different classes. Furthermore, CoCal addresses logical concerns by ensuring that the dictionary component representing a particular part is closer to its corresponding object component than to those of other objects through a cross-level contrastive learning objective. To further enhance our logical relation modeling, we implement a post-processing function inspired by the principle that a pixel assigned to a part should also be assigned to its corresponding object. With these innovations, CoCal establishes a new state-of-the-art performance on both PartImageNet and Pascal-Part-108, outperforming previous methods by a significant margin of 2.08% and 0.70% in part mIoU, respectively. Moreover, CoCal exhibits notable enhancements in object-level metrics across these benchmarks, highlighting its capacity to not only refine parsing at a finer level but also elevate the overall quality of object segmentation.
Recently, Large Vision-Language Models (LVLMs) show remarkable performance across various domains. However, these models suffer from object hallucination. This study revisits the previous claim that the primary cause of such hallucination lies in the limited representational capacity of the vision encoder. Our analysis reveals that the capacity of the vision encoder itself is already adequate for detecting object hallucination. Based on this insight, we propose a Fine-grained CLIPScore (F-CLIPScore), a simple yet effective evaluation metric that enhances object-level granularity by incorporating text embeddings at the noun level. Evaluations on the OHD-Caps benchmark show that F-CLIPScore significantly outperforms conventional CLIPScore in accuracy by a large margin of 39.6\% without additional training. We further demonstrate that F-CLIPScore-based data filtering reduces object hallucination in LVLMs (4.9\% in POPE).
Hyperspectral object tracking using snapshot mosaic cameras is emerging as it provides enhanced spectral information alongside spatial data, contributing to a more comprehensive understanding of material properties. Using transformers, which have consistently outperformed convolutional neural networks (CNNs) in learning better feature representations, would be expected to be effective for Hyperspectral object tracking. However, training large transformers necessitates extensive datasets and prolonged training periods. This is particularly critical for complex tasks like object tracking, and the scarcity of large datasets in the hyperspectral domain acts as a bottleneck in achieving the full potential of powerful transformer models. This paper proposes an effective methodology that adapts large pretrained transformer-based foundation models for hyperspectral object tracking. We propose an adaptive, learnable spatial-spectral token fusion module that can be extended to any transformer-based backbone for learning inherent spatial-spectral features in hyperspectral data. Furthermore, our model incorporates a cross-modality training pipeline that facilitates effective learning across hyperspectral datasets collected with different sensor modalities. This enables the extraction of complementary knowledge from additional modalities, whether or not they are present during testing. Our proposed model also achieves superior performance with minimal training iterations.
Imitation learning has proven to be highly effective in teaching robots dexterous manipulation skills. However, it typically relies on large amounts of human demonstration data, which limits its scalability and applicability in dynamic, real-world environments. One key challenge in this context is object generalization, where a robot trained to perform a task with one object, such as "hand over the apple," struggles to transfer its skills to a semantically similar but visually different object, such as "hand over the peach." This gap in generalization to new objects beyond those in the same category has yet to be adequately addressed in previous work on end-to-end visuomotor policy learning. In this paper, we present a simple yet effective approach for achieving object generalization through Vision-Language-Action (VLA) models, referred to as \textbf{ObjectVLA}. Our model enables robots to generalize learned skills to novel objects without requiring explicit human demonstrations for each new target object. By leveraging vision-language pair data, our method provides a lightweight and scalable way to inject knowledge about the target object, establishing an implicit link between the object and the desired action. We evaluate ObjectVLA on a real robotic platform, demonstrating its ability to generalize across 100 novel objects with a 64\% success rate in selecting objects not seen during training. Furthermore, we propose a more accessible method for enhancing object generalization in VLA models, using a smartphone to capture a few images and fine-tune the pre-trained model. These results highlight the effectiveness of our approach in enabling object-level generalization and reducing the need for extensive human demonstrations, paving the way for more flexible and scalable robotic learning systems.
We present an integrated (or end-to-end) framework for the Real2Sim2Real problem of manipulating deformable linear objects (DLOs) based on visual perception. Working with a parameterised set of DLOs, we use likelihood-free inference (LFI) to compute the posterior distributions for the physical parameters using which we can approximately simulate the behaviour of each specific DLO. We use these posteriors for domain randomisation while training, in simulation, object-specific visuomotor policies (i.e. assuming only visual and proprioceptive sensory) for a DLO reaching task, using model-free reinforcement learning. We demonstrate the utility of this approach by deploying sim-trained DLO manipulation policies in the real world in a zero-shot manner, i.e. without any further fine-tuning. In this context, we evaluate the capacity of a prominent LFI method to perform fine classification over the parametric set of DLOs, using only visual and proprioceptive data obtained in a dynamic manipulation trajectory. We then study the implications of the resulting domain distributions in sim-based policy learning and real-world performance.
Achieving realistic simulations of humans interacting with a wide range of objects has long been a fundamental goal. Extending physics-based motion imitation to complex human-object interactions (HOIs) is challenging due to intricate human-object coupling, variability in object geometries, and artifacts in motion capture data, such as inaccurate contacts and limited hand detail. We introduce InterMimic, a framework that enables a single policy to robustly learn from hours of imperfect MoCap data covering diverse full-body interactions with dynamic and varied objects. Our key insight is to employ a curriculum strategy -- perfect first, then scale up. We first train subject-specific teacher policies to mimic, retarget, and refine motion capture data. Next, we distill these teachers into a student policy, with the teachers acting as online experts providing direct supervision, as well as high-quality references. Notably, we incorporate RL fine-tuning on the student policy to surpass mere demonstration replication and achieve higher-quality solutions. Our experiments demonstrate that InterMimic produces realistic and diverse interactions across multiple HOI datasets. The learned policy generalizes in a zero-shot manner and seamlessly integrates with kinematic generators, elevating the framework from mere imitation to generative modeling of complex human-object interactions.
Recent advances in human shape learning have focused on achieving accurate human reconstruction from single-view images. However, in the real world, humans share space with other objects. Reconstructing images with humans and objects is challenging due to the occlusions and lack of 3D spatial awareness, which leads to depth ambiguity in the reconstruction. Existing methods in monocular human-object reconstruction fail to capture intricate details of clothed human bodies and object surfaces due to their template-based nature. In this paper, we jointly reconstruct clothed humans and objects in a spatially coherent manner from single-view images, while addressing human-object occlusions. A novel attention-based neural implicit model is proposed that leverages image pixel alignment to retrieve high-quality details, and incorporates semantic features extracted from the human-object pose to enable 3D spatial awareness. A generative diffusion model is used to handle human-object occlusions. For training and evaluation, we introduce a synthetic dataset with rendered scenes of inter-occluded 3D human scans and diverse objects. Extensive evaluation on both synthetic and real datasets demonstrates the superior quality of proposed human-object reconstructions over competitive methods.
Autonomous agents capable of diverse object manipulations should be able to acquire a wide range of manipulation skills with high reusability. Although advances in deep learning have made it increasingly feasible to replicate the dexterity of human teleoperation in robots, generalizing these acquired skills to previously unseen scenarios remains a significant challenge. In this study, we propose a novel algorithm, Gaze-based Bottleneck-aware Robot Manipulation (GazeBot), which enables high reusability of the learned motions even when the object positions and end-effector poses differ from those in the provided demonstrations. By leveraging gaze information and motion bottlenecks, both crucial features for object manipulation, GazeBot achieves high generalization performance compared with state-of-the-art imitation learning methods, without sacrificing its dexterity and reactivity. Furthermore, the training process of GazeBot is entirely data-driven once a demonstration dataset with gaze data is provided. Videos and code are available at https://crumbyrobotics.github.io/gazebot.
Object fetching from cluttered shelves is an important capability for robots to assist humans in real-world scenarios. Achieving this task demands robotic behaviors that prioritize safety by minimizing disturbances to surrounding objects, an essential but highly challenging requirement due to restricted motion space, limited fields of view, and complex object dynamics. In this paper, we introduce FetchBot, a sim-to-real framework designed to enable zero-shot generalizable and safety-aware object fetching from cluttered shelves in real-world settings. To address data scarcity, we propose an efficient voxel-based method for generating diverse simulated cluttered shelf scenes at scale and train a dynamics-aware reinforcement learning (RL) policy to generate object fetching trajectories within these scenes. This RL policy, which leverages oracle information, is subsequently distilled into a vision-based policy for real-world deployment. Considering that sim-to-real discrepancies stem from texture variations mostly while from geometric dimensions rarely, we propose to adopt depth information estimated by full-fledged depth foundation models as the input for the vision-based policy to mitigate sim-to-real gap. To tackle the challenge of limited views, we design a novel architecture for learning multi-view representations, allowing for comprehensive encoding of cluttered shelf scenes. This enables FetchBot to effectively minimize collisions while fetching objects from varying positions and depths, ensuring robust and safety-aware operation. Both simulation and real-robot experiments demonstrate FetchBot's superior generalization ability, particularly in handling a broad range of real-world scenarios, includ
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.
Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural adaptations, limiting zero-shot applicability. Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth. Using large language model insights on object co-occurrence, we introduce compound prompts grounded in realistic object combinations. Analysis of these prompt scores reveals VLM biases and ``AND''/``OR'' signal ambiguities, notably that maximum compound scores are surprisingly suboptimal compared to second-highest scores. We address these through a debiasing and score-fusion algorithm that corrects image bias and clarifies VLM response behaviors. Our method enhances other zero-shot approaches, consistently improving their results. Experiments show superior mean Average Precision (mAP) compared to methods requiring training data, achieved through refined object ranking for robust zero-shot MLR.
Point cloud salient object detection has attracted the attention of researchers in recent years. Since existing works do not fully utilize the geometry context of 3D objects, blurry boundaries are generated when segmenting objects with complex backgrounds. In this paper, we propose a geometry-aware 3D salient object detection network that explicitly clusters points into superpoints to enhance the geometric boundaries of objects, thereby segmenting complete objects with clear boundaries. Specifically, we first propose a simple yet effective superpoint partition module to cluster points into superpoints. In order to improve the quality of superpoints, we present a point cloud class-agnostic loss to learn discriminative point features for clustering superpoints from the object. After obtaining superpoints, we then propose a geometry enhancement module that utilizes superpoint-point attention to aggregate geometric information into point features for predicting the salient map of the object with clear boundaries. Extensive experiments show that our method achieves new state-of-the-art performance on the PCSOD dataset.
Humans naturally integrate vision and haptics for robust object perception during manipulation. The loss of either modality significantly degrades performance. Inspired by this multisensory integration, prior object pose estimation research has attempted to combine visual and haptic/tactile feedback. Although these works demonstrate improvements in controlled environments or synthetic datasets, they often underperform vision-only approaches in real-world settings due to poor generalization across diverse grippers, sensor layouts, or sim-to-real environments. Furthermore, they typically estimate the object pose for each frame independently, resulting in less coherent tracking over sequences in real-world deployments. To address these limitations, we introduce a novel unified haptic representation that effectively handles multiple gripper embodiments. Building on this representation, we introduce a new visuo-haptic transformer-based object pose tracker that seamlessly integrates visual and haptic input. We validate our framework in our dataset and the Feelsight dataset, demonstrating significant performance improvement on challenging sequences. Notably, our method achieves superior generalization and robustness across novel embodiments, objects, and sensor types (both taxel-based and vision-based tactile sensors). In real-world experiments, we demonstrate that our approach outperforms state-of-the-art visual trackers by a large margin. We further show that we can achieve precise manipulation tasks by incorporating our real-time object tracking result into motion plans, underscoring the advantages of visuo-haptic perception. Our model and dataset will be made open source upon acceptance of the paper. Project website: https://lhy.xyz/projects/v-hop/
Extracting tables from documents is a critical task across various industries, especially on business documents like invoices and reports. Existing systems based on DEtection TRansformer (DETR) such as TAble TRansformer (TATR), offer solutions for Table Detection (TD) and Table Structure Recognition (TSR) but face challenges with diverse table formats and common errors like incorrect area detection and overlapping columns. This research introduces RAPTOR, a modular post-processing system designed to enhance state-of-the-art models for improved table extraction, particularly for product tables. RAPTOR addresses recurrent TD and TSR issues, improving both precision and structural predictions. For TD, we use DETR (trained on ICDAR 2019) and TATR (trained on PubTables-1M and FinTabNet), while TSR only relies on TATR. A Genetic Algorithm is incorporated to optimize RAPTOR's module parameters, using a private dataset of product tables to align with industrial needs. We evaluate our method on two private datasets of product tables, the public DOCILE dataset (which contains tables similar to our target product tables), and the ICDAR 2013 and ICDAR 2019 datasets. The results demonstrate that while our approach excels at product tables, it also maintains reasonable performance across diverse table formats. An ablation study further validates the contribution of each module in our system.
Multi-object tracking under low-light environments is prevalent in real life. Recent years have seen rapid development in the field of multi-object tracking. However, due to the lack of datasets and the high cost of annotations, multi-object tracking under low-light environments remains a persistent challenge. In this paper, we focus on multi-object tracking under low-light conditions. To address the issues of limited data and the lack of dataset, we first constructed a low-light multi-object tracking dataset (LLMOT). This dataset comprises data from MOT17 that has been enhanced for nighttime conditions as well as multiple unannotated low-light videos. Subsequently, to tackle the high annotation costs and address the issue of image quality degradation, we propose a semi-supervised multi-object tracking method based on consistency regularization named CRTrack. First, we calibrate a consistent adaptive sampling assignment to replace the static IoU-based strategy, enabling the semi-supervised tracking method to resist noisy pseudo-bounding boxes. Then, we design a adaptive semi-supervised network update method, which effectively leverages unannotated data to enhance model performance. Dataset and Code: https://github.com/ZJZhao123/CRTrack.
Advancements in cross-modal feature extraction and integration have significantly enhanced performance in few-shot learning tasks. However, current multi-modal object detection (MM-OD) methods often experience notable performance degradation when encountering substantial domain shifts. We propose that incorporating rich textual information can enable the model to establish a more robust knowledge relationship between visual instances and their corresponding language descriptions, thereby mitigating the challenges of domain shift. Specifically, we focus on the problem of Cross-Domain Multi-Modal Few-Shot Object Detection (CDMM-FSOD) and introduce a meta-learning-based framework designed to leverage rich textual semantics as an auxiliary modality to achieve effective domain adaptation. Our new architecture incorporates two key components: (i) A multi-modal feature aggregation module, which aligns visual and linguistic feature embeddings to ensure cohesive integration across modalities. (ii) A rich text semantic rectification module, which employs bidirectional text feature generation to refine multi-modal feature alignment, thereby enhancing understanding of language and its application in object detection. We evaluate the proposed method on common cross-domain object detection benchmarks and demonstrate that it significantly surpasses existing few-shot object detection approaches.