Recent advancements in 3D Large Language Models (LLMs) have demonstrated promising capabilities for 3D scene understanding. However, previous methods exhibit deficiencies in general referencing and grounding capabilities for intricate scene comprehension. In this paper, we introduce the use of object identifiers and object-centric representations to interact with scenes at the object level. Specifically, we decompose the input 3D scene into a set of object proposals, each assigned a unique identifier token, which enables efficient object referencing and grounding during user-assistant interactions. Given the scarcity of scene-language data, we model the scene embeddings as a sequence of explicit object-level embeddings, derived from semantic-rich 2D or 3D representations. By employing object identifiers, we transform diverse 3D scene-language tasks into a unified question-answering format, facilitating joint training without the need for additional task-specific heads. With minimal fine-tuning on all downstream tasks, our model significantly outperforms existing methods on benchmarks including ScanRefer, Multi3DRefer, Scan2Cap, ScanQA, and SQA3D.
Unlike opaque object, novel view synthesis of transparent object is a challenging task, because transparent object refracts light of background causing visual distortions on the transparent object surface along the viewpoint change. Recently introduced Neural Radiance Fields (NeRF) is a view synthesis method. Thanks to its remarkable performance improvement, lots of following applications based on NeRF in various topics have been developed. However, if an object with a different refractive index is included in a scene such as transparent object, NeRF shows limited performance because refracted light ray at the surface of the transparent object is not appropriately considered. To resolve the problem, we propose a NeRF-based method consisting of the following three steps: First, we reconstruct a three-dimensional shape of a transparent object using visual hull. Second, we simulate the refraction of the rays inside of the transparent object according to Snell's law. Last, we sample points through refracted rays and put them into NeRF. Experimental evaluation results demonstrate that our method addresses the limitation of conventional NeRF with transparent objects.
We introduce a novel task of 3D visual grounding in monocular RGB images using language descriptions with both appearance and geometry information. Specifically, we build a large-scale dataset, Mono3DRefer, which contains 3D object targets with their corresponding geometric text descriptions, generated by ChatGPT and refined manually. To foster this task, we propose Mono3DVG-TR, an end-to-end transformer-based network, which takes advantage of both the appearance and geometry information in text embeddings for multi-modal learning and 3D object localization. Depth predictor is designed to explicitly learn geometry features. The dual text-guided adapter is proposed to refine multiscale visual and geometry features of the referred object. Based on depth-text-visual stacking attention, the decoder fuses object-level geometric cues and visual appearance into a learnable query. Comprehensive benchmarks and some insightful analyses are provided for Mono3DVG. Extensive comparisons and ablation studies show that our method significantly outperforms all baselines. The dataset and code will be publicly available at: https://github.com/ZhanYang-nwpu/Mono3DVG.
Referring expression segmentation (RES) aims at segmenting the foreground masks of the entities that match the descriptive natural language expression. Previous datasets and methods for classic RES task heavily rely on the prior assumption that one expression must refer to object-level targets. In this paper, we take a step further to finer-grained part-level RES task. To promote the object-level RES task towards finer-grained vision-language understanding, we put forward a new multi-granularity referring expression segmentation (MRES) task and construct an evaluation benchmark called RefCOCOm by manual annotations. By employing our automatic model-assisted data engine, we build the largest visual grounding dataset namely MRES-32M, which comprises over 32.2M high-quality masks and captions on the provided 1M images. Besides, a simple yet strong model named UniRES is designed to accomplish the unified object-level and part-level grounding task. Extensive experiments on our RefCOCOm for MRES and three datasets (i.e., RefCOCO(+/g) for classic RES task demonstrate the superiority of our method over previous state-of-the-art methods. To foster future research into fine-grained visual grounding, our benchmark RefCOCOm, the MRES-32M dataset and model UniRES will be publicly available at https://github.com/Rubics-Xuan/MRES
Artificial intelligence-enhanced identification of organs, lesions, and other structures in medical imaging is typically done using convolutional neural networks (CNNs) designed to make voxel-accurate segmentations of the region of interest. However, the labels required to train these CNNs are time-consuming to generate and require attention from subject matter experts to ensure quality. For tasks where voxel-level precision is not required, object detection models offer a viable alternative that can reduce annotation effort. Despite this potential application, there are few options for general purpose object detection frameworks available for 3-D medical imaging. We report on MedYOLO, a 3-D object detection framework using the one-shot detection method of the YOLO family of models and designed for use with medical imaging. We tested this model on four different datasets: BRaTS, LIDC, an abdominal organ Computed Tomography (CT) dataset, and an ECG-gated heart CT dataset. We found our models achieve high performance on commonly present medium and large-sized structures such as the heart, liver, and pancreas even without hyperparameter tuning. However, the models struggle with very small or rarely present structures.
Gland instance segmentation is an essential but challenging task in the diagnosis and treatment of adenocarcinoma. The existing models usually achieve gland instance segmentation through multi-task learning and boundary loss constraint. However, how to deal with the problems of gland adhesion and inaccurate boundary in segmenting the complex samples remains a challenge. In this work, we propose a displacement-field assisted graph energy transmitter (DFGET) framework to solve these problems. Specifically, a novel message passing manner based on anisotropic diffusion is developed to update the node features, which can distinguish the isomorphic graphs and improve the expressivity of graph nodes for complex samples. Using such graph framework, the gland semantic segmentation map and the displacement field (DF) of the graph nodes are estimated with two graph network branches. With the constraint of DF, a graph cluster module based on diffusion theory is presented to improve the intra-class feature consistency and inter-class feature discrepancy, as well as to separate the adherent glands from the semantic segmentation maps. Extensive comparison and ablation experiments on the GlaS dataset demonstrate the superiority of DFGET and effectiveness of the proposed anisotropic message passing manner and clustering method. Compared to the best comparative model, DFGET increases the object-Dice and object-F1 score by 2.5% and 3.4% respectively, while decreases the object-HD by 32.4%, achieving state-of-the-art performance.
Object pose estimation is a long-standing problem in computer vision. Recently, attention-based vision transformer models have achieved state-of-the-art results in many computer vision applications. Exploiting the permutation-invariant nature of the attention mechanism, a family of vision transformer models formulate multi-object pose estimation as a set prediction problem. However, existing vision transformer models for multi-object pose estimation rely exclusively on the attention mechanism. Convolutional neural networks, on the other hand, hard-wire various inductive biases into their architecture. In this paper, we investigate incorporating inductive biases in vision transformer models for multi-object pose estimation, which facilitates learning long-range dependencies while circumventing the costly global attention. In particular, we use multi-resolution deformable attention, where the attention operation is performed only between a few deformed reference points. Furthermore, we propose a query aggregation mechanism that enables increasing the number of object queries without increasing the computational complexity. We evaluate the proposed model on the challenging YCB-Video dataset and report state-of-the-art results.
Reliable object grasping is a crucial capability for autonomous robots. However, many existing grasping approaches focus on general clutter removal without explicitly modeling objects and thus only relying on the visible local geometry. We introduce CenterGrasp, a novel framework that combines object awareness and holistic grasping. CenterGrasp learns a general object prior by encoding shapes and valid grasps in a continuous latent space. It consists of an RGB-D image encoder that leverages recent advances to detect objects and infer their pose and latent code, and a decoder to predict shape and grasps for each object in the scene. We perform extensive experiments on simulated as well as real-world cluttered scenes and demonstrate strong scene reconstruction and 6-DoF grasp-pose estimation performance. Compared to the state of the art, CenterGrasp achieves an improvement of 38.5 mm in shape reconstruction and 33 percentage points on average in grasp success. We make the code and trained models publicly available at http://centergrasp.cs.uni-freiburg.de.
This research presents ADOD, a novel approach to address domain generalization in underwater object detection. Our method enhances the model's ability to generalize across diverse and unseen domains, ensuring robustness in various underwater environments. The first key contribution is Residual Attention YOLOv3, a novel variant of the YOLOv3 framework empowered by residual attention modules. These modules enable the model to focus on informative features while suppressing background noise, leading to improved detection accuracy and adaptability to different domains. The second contribution is the attention-based domain classification module, vital during training. This module helps the model identify domain-specific information, facilitating the learning of domain-invariant features. Consequently, ADOD can generalize effectively to underwater environments with distinct visual characteristics. Extensive experiments on diverse underwater datasets demonstrate ADOD's superior performance compared to state-of-the-art domain generalization methods, particularly in challenging scenarios. The proposed model achieves exceptional detection performance in both seen and unseen domains, showcasing its effectiveness in handling domain shifts in underwater object detection tasks. ADOD represents a significant advancement in adaptive object detection, providing a promising solution for real-world applications in underwater environments. With the prevalence of domain shifts in such settings, the model's strong generalization ability becomes a valuable asset for practical underwater surveillance and marine research endeavors.
This paper introduces a novel approach for learning polynomial representations of physical objects. Given a point cloud data set associated with a physical object, we solve a one-class classification problem to bound the data points by a polynomial sublevel set while harnessing Sum-of-Squares (SOS) programming to enforce prior shape knowledge constraints. By representing objects as polynomial sublevel sets we further show it is possible to construct a secondary SOS program to certify whether objects are packed correctly, that is object boundaries do not overlap and are inside some container set. While not employing reinforcement learning (RL) in this work, our proposed secondary SOS program does provide a potential surrogate reward function for RL algorithms, autonomously rewarding agents that propose object rotations and translations that correctly pack objects within a given container set.
The Segment Anything Model (SAM) has been a cornerstone in the field of interactive segmentation, propelling significant progress in generative AI, computational photography, and medical imaging. Despite its ability to process arbitrary user input and generate corresponding segmentation masks, SAM's 600 million parameter architecture, based on ViT-H, is not compatible with current mobile hardware due to its high computational demands and large model size. Our research aims to adapt SAM for use in mobile photography applications. To this end, we have developed a fully convolutional SqueezeSAM model architecture, which is 62.5 times faster and 31.6 times smaller than the original SAM, making it a viable solution for mobile applications. Furthermore, our tiny model achieves an mIOU within 1% of the original VIT-H architecture. Automated segmentation holds significant value in the creation flow for photography applications, as evidenced by its adoption by leading industry players like apple and capcut. To facilitate this automation, we employ salient object detection and simulate potential user clicks for foreground object selection, generating an initial segmentation mask that users can subsequently edit interactively. A common user expectation is that a click on a specific part of an object will result in the segmentation of the entire object. For example, a click on a person's t-shirt in a photo should ideally segment the entire person, not just the t-shirt. However, SAM typically only segments the clicked area. We address this limitation through a novel data augmentation scheme. Consequently, if a user clicks on a person holding a basketball, both the person and the basketball are segmented together, aligning with user expectations and enhancing the overall user experience.
We address the task of generating temporally consistent and physically plausible images of actions and object state transformations. Given an input image and a text prompt describing the targeted transformation, our generated images preserve the environment and transform objects in the initial image. Our contributions are threefold. First, we leverage a large body of instructional videos and automatically mine a dataset of triplets of consecutive frames corresponding to initial object states, actions, and resulting object transformations. Second, equipped with this data, we develop and train a conditioned diffusion model dubbed GenHowTo. Third, we evaluate GenHowTo on a variety of objects and actions and show superior performance compared to existing methods. In particular, we introduce a quantitative evaluation where GenHowTo achieves 88% and 74% on seen and unseen interaction categories, respectively, outperforming prior work by a large margin.
Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing counting model training. Some sophisticated noise-resistance counting methods have been proposed to alleviate this issue. Differently, we aim to directly refine the initial point annotations before training counting models. For that, we propose the Shifted Autoencoders (SAE), which enhances annotation consistency. Specifically, SAE applies random shifts to initial point annotations and employs a UNet to restore them to their original positions. Similar to MAE reconstruction, the trained SAE captures general position knowledge and ignores specific manual offset noise. This allows to restore the initial point annotations to more general and thus consistent positions. Extensive experiments show that using such refined consistent annotations to train some advanced (including noise-resistance) object counting models steadily/significantly boosts their performances. Remarkably, the proposed SAE helps to set new records on nine datasets. We will make codes and refined point annotations available.
Reconstructing human-object interaction in 3D from a single RGB image is a challenging task and existing data driven methods do not generalize beyond the objects present in the carefully curated 3D interaction datasets. Capturing large-scale real data to learn strong interaction and 3D shape priors is very expensive due to the combinatorial nature of human-object interactions. In this paper, we propose ProciGen (Procedural interaction Generation), a method to procedurally generate datasets with both, plausible interaction and diverse object variation. We generate 1M+ human-object interaction pairs in 3D and leverage this large-scale data to train our HDM (Hierarchical Diffusion Model), a novel method to reconstruct interacting human and unseen objects, without any templates. Our HDM is an image-conditioned diffusion model that learns both realistic interaction and highly accurate human and object shapes. Experiments show that our HDM trained with ProciGen significantly outperforms prior methods that requires template meshes and that our dataset allows training methods with strong generalization ability to unseen object instances. Our code and data are released.
Regression loss design is an essential topic for oriented object detection. Due to the periodicity of the angle and the ambiguity of width and height definition, traditional L1-distance loss and its variants have been suffered from the metric discontinuity and the square-like problem. As a solution, the distribution based methods show significant advantages by representing oriented boxes as distributions. Differing from exploited the Gaussian distribution to get analytical form of distance measure, we propose a novel oriented regression loss, Wasserstein Distance(EWD) loss, to alleviate the square-like problem. Specifically, for the oriented box(OBox) representation, we choose a specially-designed distribution whose probability density function is only nonzero over the edges. On this basis, we develop Wasserstein distance as the measure. Besides, based on the edge representation of OBox, the EWD loss can be generalized to quadrilateral and polynomial regression scenarios. Experiments on multiple popular datasets and different detectors show the effectiveness of the proposed method.
Besides performance, efficiency is a key design driver of technologies supporting vehicular perception. Indeed, a well-balanced trade-off between performance and energy consumption is crucial for the sustainability of autonomous vehicles. In this context, the diversity of real-world contexts in which autonomous vehicles can operate motivates the need for empowering perception models with the capability to detect, characterize and identify newly appearing objects by themselves. In this manuscript we elaborate on this threefold conundrum (performance, efficiency and open-world learning) for object detection modeling tasks over image data collected from vehicular scenarios. Specifically, we show that well-performing and efficient models can be realized by virtue of Spiking Neural Networks (SNNs), reaching competitive levels of detection performance when compared to their non-spiking counterparts at dramatic energy consumption savings (up to 85%) and a slightly improved robustness against image noise. Our experiments herein offered also expose qualitatively the complexity of detecting new objects based on the preliminary results of a simple approach to discriminate potential object proposals in the captured image.
While the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach. Specifically, the pseudo-label method tends to amplify the inherent strengths of the detector while accentuating its weaknesses, which is manifested in the missed detection of pseudo-labels, particularly for small and tail category objects. To overcome these challenges, this paper proposes Mixed Pseudo Labels (MixPL), consisting of Mixup and Mosaic for pseudo-labeled data, to mitigate the negative impact of missed detections and balance the model's learning across different object scales. Additionally, the model's detection performance on tail categories is improved by resampling labeled data with relevant instances. Notably, MixPL consistently improves the performance of various detectors and obtains new state-of-the-art results with Faster R-CNN, FCOS, and DINO on COCO-Standard and COCO-Full benchmarks. Furthermore, MixPL also exhibits good scalability on large models, improving DINO Swin-L by 2.5% mAP and achieving nontrivial new records (60.2% mAP) on the COCO val2017 benchmark without extra annotations.
Visual object recognition -- the behavioral ability to rapidly and accurately categorize many visually encountered objects -- is core to primate cognition. This behavioral capability is algorithmically impressive because of the myriad identity-preserving viewpoints and scenes that dramatically change the visual image produced by the same object. Until recently, the brain mechanisms that support that capability were deeply mysterious. However, over the last decade, this scientific mystery has been illuminated by the discovery and development of brain-inspired, image-computable, artificial neural network (ANN) systems that rival primates in this behavioral feat. Apart from fundamentally changing the landscape of artificial intelligence (AI), modified versions of these ANN systems are the current leading scientific hypotheses of an integrated set of mechanisms in the primate ventral visual stream that support object recognition. What separates brain-mapped versions of these systems from prior conceptual models is that they are Sensory-computable, Mechanistic, Anatomically Referenced, and Testable (SMART). Here, we review and provide perspective on the brain mechanisms that the currently leading SMART models address. We review the empirical brain and behavioral alignment successes and failures of those current models. Given ongoing advances in neurobehavioral measurements and AI, we discuss the next frontiers for even more accurate mechanistic understanding. And we outline the likely applications of that SMART-model-based understanding.
A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets. While augmenting real scenes with virtual objects holds promise to improve both the diversity and quantity of the objects, it remains elusive due to the lack of an effective 3D object insertion method in complex real captured scenes. In this work, we study augmenting complex real indoor scenes with virtual objects for monocular 3D object detection. The main challenge is to automatically identify plausible physical properties for virtual assets (e.g., locations, appearances, sizes, etc.) in cluttered real scenes. To address this challenge, we propose a physically plausible indoor 3D object insertion approach to automatically copy virtual objects and paste them into real scenes. The resulting objects in scenes have 3D bounding boxes with plausible physical locations and appearances. In particular, our method first identifies physically feasible locations and poses for the inserted objects to prevent collisions with the existing room layout. Subsequently, it estimates spatially-varying illumination for the insertion location, enabling the immersive blending of the virtual objects into the original scene with plausible appearances and cast shadows. We show that our augmentation method significantly improves existing monocular 3D object models and achieves state-of-the-art performance. For the first time, we demonstrate that a physically plausible 3D object insertion, serving as a generative data augmentation technique, can lead to significant improvements for discriminative downstream tasks such as monocular 3D object detection. Project website: https://gyhandy.github.io/3D-Copy-Paste/
We address the problem of generating realistic 3D human-object interactions (HOIs) driven by textual prompts. To this end, we take a modular design and decompose the complex task into simpler sub-tasks. We first develop a dual-branch diffusion model (HOI-DM) to generate both human and object motions conditioned on the input text, and encourage coherent motions by a cross-attention communication module between the human and object motion generation branches. We also develop an affordance prediction diffusion model (APDM) to predict the contacting area between the human and object during the interactions driven by the textual prompt. The APDM is independent of the results by the HOI-DM and thus can correct potential errors by the latter. Moreover, it stochastically generates the contacting points to diversify the generated motions. Finally, we incorporate the estimated contacting points into the classifier-guidance to achieve accurate and close contact between humans and objects. To train and evaluate our approach, we annotate BEHAVE dataset with text descriptions. Experimental results on BEHAVE and OMOMO demonstrate that our approach produces realistic HOIs with various interactions and different types of objects.