Object pose estimation enables a variety of tasks in computer vision and robotics, including scene understanding and robotic grasping. The complexity of a pose estimation task depends on the unknown variables related to the target object. While instance-level methods already excel for opaque and Lambertian objects, category-level and open-set methods, where texture, shape, and size are partially or entirely unknown, still struggle with these basic material properties. Since texture is unknown in these scenarios, it cannot be used for disambiguating object symmetries, another core challenge of 6D object pose estimation. The complexity of estimating 6D poses with such a manifold of unknowns led to various datasets, accuracy metrics, and algorithmic solutions. This paper compares datasets, accuracy metrics, and algorithms for solving 6D pose estimation on the category-level. Based on this comparison, we analyze how to bridge category-level and open-set object pose estimation to reach generalization and provide actionable recommendations.
In human-centered environments such as restaurants, homes, and warehouses, robots often face challenges in accurately recognizing 3D objects. These challenges stem from the complexity and variability of these environments, including diverse object shapes. In this paper, we propose a novel Lightweight Multi-modal Multi-view Convolutional-Vision Transformer network (LM-MCVT) to enhance 3D object recognition in robotic applications. Our approach leverages the Globally Entropy-based Embeddings Fusion (GEEF) method to integrate multi-views efficiently. The LM-MCVT architecture incorporates pre- and mid-level convolutional encoders and local and global transformers to enhance feature extraction and recognition accuracy. We evaluate our method on the synthetic ModelNet40 dataset and achieve a recognition accuracy of 95.6% using a four-view setup, surpassing existing state-of-the-art methods. To further validate its effectiveness, we conduct 5-fold cross-validation on the real-world OmniObject3D dataset using the same configuration. Results consistently show superior performance, demonstrating the method's robustness in 3D object recognition across synthetic and real-world 3D data.
Generalizable dexterous grasping with suitable grasp types is a fundamental skill for intelligent robots. Developing such skills requires a large-scale and high-quality dataset that covers numerous grasp types (i.e., at least those categorized by the GRASP taxonomy), but collecting such data is extremely challenging. Existing automatic grasp synthesis methods are often limited to specific grasp types or object categories, hindering scalability. This work proposes an efficient pipeline capable of synthesizing contact-rich, penetration-free, and physically plausible grasps for any grasp type, object, and articulated hand. Starting from a single human-annotated template for each hand and grasp type, our pipeline tackles the complicated synthesis problem with two stages: optimize the object to fit the hand template first, and then locally refine the hand to fit the object in simulation. To validate the synthesized grasps, we introduce a contact-aware control strategy that allows the hand to apply the appropriate force at each contact point to the object. Those validated grasps can also be used as new grasp templates to facilitate future synthesis. Experiments show that our method significantly outperforms previous type-unaware grasp synthesis baselines in simulation. Using our algorithm, we construct a dataset containing 10.7k objects and 9.5M grasps, covering 31 grasp types in the GRASP taxonomy. Finally, we train a type-conditional generative model that successfully performs the desired grasp type from single-view object point clouds, achieving an 82.3% success rate in real-world experiments. Project page: https://pku-epic.github.io/Dexonomy.
Vision-and-Language Navigation (VLN) is a challenging task where an agent must understand language instructions and navigate unfamiliar environments using visual cues. The agent must accurately locate the target based on visual information from the environment and complete tasks through interaction with the surroundings. Despite significant advancements in this field, two major limitations persist: (1) Many existing methods input complete language instructions directly into multi-layer Transformer networks without fully exploiting the detailed information within the instructions, thereby limiting the agent's language understanding capabilities during task execution; (2) Current approaches often overlook the modeling of object relationships across different modalities, failing to effectively utilize latent clues between objects, which affects the accuracy and robustness of navigation decisions. We propose a Dual Object Perception-Enhancement Network (DOPE) to address these issues to improve navigation performance. First, we design a Text Semantic Extraction (TSE) to extract relatively essential phrases from the text and input them into the Text Object Perception-Augmentation (TOPA) to fully leverage details such as objects and actions within the instructions. Second, we introduce an Image Object Perception-Augmentation (IOPA), which performs additional modeling of object information across different modalities, enabling the model to more effectively utilize latent clues between objects in images and text, enhancing decision-making accuracy. Extensive experiments on the R2R and REVERIE datasets validate the efficacy of the proposed approach.
We present an embodied robotic system with an LLM-driven agent-orchestration architecture for autonomous household object management. The system integrates memory-augmented task planning, enabling robots to execute high-level user commands while tracking past actions. It employs three specialized agents: a routing agent, a task planning agent, and a knowledge base agent, each powered by task-specific LLMs. By leveraging in-context learning, our system avoids the need for explicit model training. RAG enables the system to retrieve context from past interactions, enhancing long-term object tracking. A combination of Grounded SAM and LLaMa3.2-Vision provides robust object detection, facilitating semantic scene understanding for task planning. Evaluation across three household scenarios demonstrates high task planning accuracy and an improvement in memory recall due to RAG. Specifically, Qwen2.5 yields best performance for specialized agents, while LLaMA3.1 excels in routing tasks. The source code is available at: https://github.com/marc1198/chat-hsr.
Large Vision Language Models (LVLMs) often suffer from object hallucination, which undermines their reliability. Surprisingly, we find that simple object-based visual prompting -- overlaying visual cues (e.g., bounding box, circle) on images -- can significantly mitigate such hallucination; however, different visual prompts (VPs) vary in effectiveness. To address this, we propose Black-Box Visual Prompt Engineering (BBVPE), a framework to identify optimal VPs that enhance LVLM responses without needing access to model internals. Our approach employs a pool of candidate VPs and trains a router model to dynamically select the most effective VP for a given input image. This black-box approach is model-agnostic, making it applicable to both open-source and proprietary LVLMs. Evaluations on benchmarks such as POPE and CHAIR demonstrate that BBVPE effectively reduces object hallucination.
Deep learning models for object detection in autonomous driving have recently achieved impressive performance gains and are already being deployed in vehicles worldwide. However, current models require increasingly large datasets for training. Acquiring and labeling such data is costly, necessitating the development of new strategies to optimize this process. Active learning is a promising approach that has been extensively researched in the image domain. In our work, we extend this concept to the LiDAR domain by developing several inconsistency-based sample selection strategies and evaluate their effectiveness in various settings. Our results show that using a naive inconsistency approach based on the number of detected boxes, we achieve the same mAP as the random sampling strategy with 50% of the labeled data.
Interactive 3D segmentation has emerged as a promising solution for generating accurate object masks in complex 3D scenes by incorporating user-provided clicks. However, two critical challenges remain underexplored: (1) effectively generalizing from sparse user clicks to produce accurate segmentation, and (2) quantifying predictive uncertainty to help users identify unreliable regions. In this work, we propose NPISeg3D, a novel probabilistic framework that builds upon Neural Processes (NPs) to address these challenges. Specifically, NPISeg3D introduces a hierarchical latent variable structure with scene-specific and object-specific latent variables to enhance few-shot generalization by capturing both global context and object-specific characteristics. Additionally, we design a probabilistic prototype modulator that adaptively modulates click prototypes with object-specific latent variables, improving the model's ability to capture object-aware context and quantify predictive uncertainty. Experiments on four 3D point cloud datasets demonstrate that NPISeg3D achieves superior segmentation performance with fewer clicks while providing reliable uncertainty estimations.
Text-driven object insertion in 3D scenes is an emerging task that enables intuitive scene editing through natural language. However, existing 2D editing-based methods often rely on spatial priors such as 2D masks or 3D bounding boxes, and they struggle to ensure consistency of the inserted object. These limitations hinder flexibility and scalability in real-world applications. In this paper, we propose FreeInsert, a novel framework that leverages foundation models including MLLMs, LGMs, and diffusion models to disentangle object generation from spatial placement. This enables unsupervised and flexible object insertion in 3D scenes without spatial priors. FreeInsert starts with an MLLM-based parser that extracts structured semantics, including object types, spatial relationships, and attachment regions, from user instructions. These semantics guide both the reconstruction of the inserted object for 3D consistency and the learning of its degrees of freedom. We leverage the spatial reasoning capabilities of MLLMs to initialize object pose and scale. A hierarchical, spatially aware refinement stage further integrates spatial semantics and MLLM-inferred priors to enhance placement. Finally, the appearance of the object is improved using the inserted-object image to enhance visual fidelity. Experimental results demonstrate that FreeInsert achieves semantically coherent, spatially precise, and visually realistic 3D insertions without relying on spatial priors, offering a user-friendly and flexible editing experience.
We present an open-vocabulary and zero-shot method for arbitrary referring expression segmentation (RES), targeting input expressions that are more general than what prior works were designed to handle. Specifically, our inputs encompass both object- and part-level labels as well as implicit references pointing to properties or qualities of object/part function, design, style, material, etc. Our model, coined RESAnything, leverages Chain-of-Thoughts (CoT) reasoning, where the key idea is attribute prompting. We generate detailed descriptions of object/part attributes including shape, color, and location for potential segment proposals through systematic prompting of a large language model (LLM), where the proposals are produced by a foundational image segmentation model. Our approach encourages deep reasoning about object or part attributes related to function, style, design, etc., enabling the system to handle implicit queries without any part annotations for training or fine-tuning. As the first zero-shot and LLM-based RES method, RESAnything achieves clearly superior performance among zero-shot methods on traditional RES benchmarks and significantly outperforms existing methods on challenging scenarios involving implicit queries and complex part-level relations. Finally, we contribute a new benchmark dataset to offer ~3K carefully curated RES instances to assess part-level, arbitrary RES solutions.
We propose the Compact Clustering Attention (COCA) layer, an effective building block that introduces a hierarchical strategy for object-centric representation learning, while solving the unsupervised object discovery task on single images. COCA is an attention-based clustering module capable of extracting object-centric representations from multi-object scenes, when cascaded into a bottom-up hierarchical network architecture, referred to as COCA-Net. At its core, COCA utilizes a novel clustering algorithm that leverages the physical concept of compactness, to highlight distinct object centroids in a scene, providing a spatial inductive bias. Thanks to this strategy, COCA-Net generates high-quality segmentation masks on both the decoder side and, notably, the encoder side of its pipeline. Additionally, COCA-Net is not bound by a predetermined number of object masks that it generates and handles the segmentation of background elements better than its competitors. We demonstrate COCA-Net's segmentation performance on six widely adopted datasets, achieving superior or competitive results against the state-of-the-art models across nine different evaluation metrics.
The verification of successful grasps is a crucial aspect of robot manipulation, particularly when handling deformable objects. Traditional methods relying on force and tactile sensors often struggle with deformable and non-rigid objects. In this work, we present a vision-based approach for grasp verification to determine whether the robotic gripper has successfully grasped an object. Our method employs a two-stage architecture; first YOLO-based object detection model to detect and locate the robot's gripper and then a ResNet-based classifier determines the presence of an object. To address the limitations of real-world data capture, we introduce HSR-GraspSynth, a synthetic dataset designed to simulate diverse grasping scenarios. Furthermore, we explore the use of Visual Question Answering capabilities as a zero-shot baseline to which we compare our model. Experimental results demonstrate that our approach achieves high accuracy in real-world environments, with potential for integration into grasping pipelines. Code and datasets are publicly available at https://github.com/pauamargant/HSR-GraspSynth .
Active Learning has proved to be a relevant approach to perform sample selection for training models for Autonomous Driving. Particularly, previous works on active learning for 3D object detection have shown that selection of samples in uncontrolled scenarios is challenging. Furthermore, current approaches focus exclusively on the theoretical aspects of the sample selection problem but neglect the practical insights that can be obtained from the extensive literature and application of 3D detection models. In this paper, we introduce HeAL (Heuristical-enhanced Active Learning for 3D Object Detection) which integrates those heuristical features together with Localization and Classification to deliver the most contributing samples to the model's training. In contrast to previous works, our approach integrates heuristical features such as object distance and point-quantity to estimate the uncertainty, which enhance the usefulness of selected samples to train detection models. Our quantitative evaluation on KITTI shows that HeAL presents competitive mAP with respect to the State-of-the-Art, and achieves the same mAP as the full-supervised baseline with only 24% of the samples.
Reposing objects in images has a myriad of applications, especially for e-commerce where several variants of product images need to be produced quickly. In this work, we leverage the recent advances in unsupervised keypoint correspondence detection between different object images of the same class to propose an end-to-end framework for generic object reposing. Our method, EOPose, takes a target pose-guidance image as input and uses its keypoint correspondence with the source object image to warp and re-render the latter into the target pose using a novel three-step approach. Unlike generative approaches, our method also preserves the fine-grained details of the object such as its exact colors, textures, and brand marks. We also prepare a new dataset of paired objects based on the Objaverse dataset to train and test our network. EOPose produces high-quality reposing output as evidenced by different image quality metrics (PSNR, SSIM and FID). Besides a description of the method and the dataset, the paper also includes detailed ablation and user studies to indicate the efficacy of the proposed method
Backgrounds in images play a major role in contributing to spurious correlations among different data points. Owing to aesthetic preferences of humans capturing the images, datasets can exhibit positional (location of the object within a given frame) and size (region-of-interest to image ratio) biases for different classes. In this paper, we show that these biases can impact how much a model relies on spurious features in the background to make its predictions. To better illustrate our findings, we propose a synthetic dataset derived from ImageNet1k, Hard-Spurious-ImageNet, which contains images with various backgrounds, object positions, and object sizes. By evaluating the dataset on different pretrained models, we find that most models rely heavily on spurious features in the background when the region-of-interest (ROI) to image ratio is small and the object is far from the center of the image. Moreover, we also show that current methods that aim to mitigate harmful spurious features, do not take into account these factors, hence fail to achieve considerable performance gains for worst-group accuracies when the size and location of core features in an image change.
Hindsight relabeling is a powerful tool for overcoming sparsity in goal-conditioned reinforcement learning (GCRL), especially in certain domains such as navigation and locomotion. However, hindsight relabeling can struggle in object-centric domains. For example, suppose that the goal space consists of a robotic arm pushing a particular target block to a goal location. In this case, hindsight relabeling will give high rewards to any trajectory that does not interact with the block. However, these behaviors are only useful when the object is already at the goal -- an extremely rare case in practice. A dataset dominated by these kinds of trajectories can complicate learning and lead to failures. In object-centric domains, one key intuition is that meaningful trajectories are often characterized by object-object interactions such as pushing the block with the gripper. To leverage this intuition, we introduce Hindsight Relabeling using Interactions (HInt), which combines interactions with hindsight relabeling to improve the sample efficiency of downstream RL. However because interactions do not have a consensus statistical definition tractable for downstream GCRL, we propose a definition of interactions based on the concept of null counterfactual: a cause object is interacting with a target object if, in a world where the cause object did not exist, the target object would have different transition dynamics. We leverage this definition to infer interactions in Null Counterfactual Interaction Inference (NCII), which uses a "nulling'' operation with a learned model to infer interactions. NCII is able to achieve significantly improved interaction inference accuracy in both simple linear dynamics domains and dynamic robotic domains in Robosuite, Robot Air Hockey, and Franka Kitchen and HInt improves sample efficiency by up to 4x.
Cross-domain few-shot object detection (CD-FSOD) aims to detect novel objects across different domains with limited class instances. Feature confusion, including object-background confusion and object-object confusion, presents significant challenges in both cross-domain and few-shot settings. In this work, we introduce CDFormer, a cross-domain few-shot object detection transformer against feature confusion, to address these challenges. The method specifically tackles feature confusion through two key modules: object-background distinguishing (OBD) and object-object distinguishing (OOD). The OBD module leverages a learnable background token to differentiate between objects and background, while the OOD module enhances the distinction between objects of different classes. Experimental results demonstrate that CDFormer outperforms previous state-of-the-art approaches, achieving 12.9% mAP, 11.0% mAP, and 10.4% mAP improvements under the 1/5/10 shot settings, respectively, when fine-tuned.
We introduce InteractVLM, a novel method to estimate 3D contact points on human bodies and objects from single in-the-wild images, enabling accurate human-object joint reconstruction in 3D. This is challenging due to occlusions, depth ambiguities, and widely varying object shapes. Existing methods rely on 3D contact annotations collected via expensive motion-capture systems or tedious manual labeling, limiting scalability and generalization. To overcome this, InteractVLM harnesses the broad visual knowledge of large Vision-Language Models (VLMs), fine-tuned with limited 3D contact data. However, directly applying these models is non-trivial, as they reason only in 2D, while human-object contact is inherently 3D. Thus we introduce a novel Render-Localize-Lift module that: (1) embeds 3D body and object surfaces in 2D space via multi-view rendering, (2) trains a novel multi-view localization model (MV-Loc) to infer contacts in 2D, and (3) lifts these to 3D. Additionally, we propose a new task called Semantic Human Contact estimation, where human contact predictions are conditioned explicitly on object semantics, enabling richer interaction modeling. InteractVLM outperforms existing work on contact estimation and also facilitates 3D reconstruction from an in-the wild image. Code and models are available at https://interactvlm.is.tue.mpg.de.
Semantic 3D city models are worldwide easy-accessible, providing accurate, object-oriented, and semantic-rich 3D priors. To date, their potential to mitigate the noise impact on radar object detection remains under-explored. In this paper, we first introduce a unique dataset, RadarCity, comprising 54K synchronized radar-image pairs and semantic 3D city models. Moreover, we propose a novel neural network, RADLER, leveraging the effectiveness of contrastive self-supervised learning (SSL) and semantic 3D city models to enhance radar object detection of pedestrians, cyclists, and cars. Specifically, we first obtain the robust radar features via a SSL network in the radar-image pretext task. We then use a simple yet effective feature fusion strategy to incorporate semantic-depth features from semantic 3D city models. Having prior 3D information as guidance, RADLER obtains more fine-grained details to enhance radar object detection. We extensively evaluate RADLER on the collected RadarCity dataset and demonstrate average improvements of 5.46% in mean avarage precision (mAP) and 3.51% in mean avarage recall (mAR) over previous radar object detection methods. We believe this work will foster further research on semantic-guided and map-supported radar object detection. Our project page is publicly available athttps://gpp-communication.github.io/RADLER .
Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image. Although recent VRD models have achieved impressive performance, they are all restricted to pre-defined relation categories, while failing to consider the semantic ambiguity characteristic of visual relations. Unlike objects, the appearance of visual relations is always subtle and can be described by multiple predicate words from different perspectives, e.g., ``ride'' can be depicted as ``race'' and ``sit on'', from the sports and spatial position views, respectively. To this end, we propose to model visual relations as continuous embeddings, and design diffusion models to achieve generalized VRD in a conditional generative manner, termed Diff-VRD. We model the diffusion process in a latent space and generate all possible relations in the image as an embedding sequence. During the generation, the visual and text embeddings of subject-object pairs serve as conditional signals and are injected via cross-attention. After the generation, we design a subsequent matching stage to assign the relation words to subject-object pairs by considering their semantic similarities. Benefiting from the diffusion-based generative process, our Diff-VRD is able to generate visual relations beyond the pre-defined category labels of datasets. To properly evaluate this generalized VRD task, we introduce two evaluation metrics, i.e., text-to-image retrieval and SPICE PR Curve inspired by image captioning. Extensive experiments in both human-object interaction (HOI) detection and scene graph generation (SGG) benchmarks attest to the superiority and effectiveness of Diff-VRD.