We propose Medial Atom Ray Fields (MARFs), a novel neural object representation that enables accurate differentiable surface rendering with a single network evaluation per camera ray. Existing neural ray fields struggle with multi-view consistency and representing surface discontinuities. MARFs address both using a medial shape representation, a dual representation of solid geometry that yields cheap geometrically grounded surface normals, in turn enabling computing analytical curvature despite the network having no second derivative. MARFs map a camera ray to multiple medial intersection candidates, subject to ray-sphere intersection testing. We illustrate how the learned medial shape quantities applies to sub-surface scattering, part segmentation, and aid representing a space of articulated shapes. Able to learn a space of shape priors, MARFs may prove useful for tasks like shape retrieval and shape completion, among others. Code and data can be found at https://github.com/pbsds/MARF.
Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. Moreover, we design a two-stage network named DMASNet with decomposed mask prediction and attentive shadow filling. Specifically, in the first stage, we decompose shadow mask prediction into box prediction and shape prediction. In the second stage, we attend to reference background shadow pixels to fill the foreground shadow. Abundant experiments prove that our DMASNet achieves better visual effects and generalizes well to real composite images.
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models. While click and brush interactions are both well explored in interactive image segmentation, the existing methods on videos focus on mask annotation and propagation. This paper presents SAM-PT, a novel method for point-centric interactive video segmentation, empowered by SAM and long-term point tracking. SAM-PT leverages robust and sparse point selection and propagation techniques for mask generation. Compared to traditional object-centric mask propagation strategies, we uniquely use point propagation to exploit local structure information agnostic to object semantics. We highlight the merits of point-based tracking through direct evaluation on the zero-shot open-world Unidentified Video Objects (UVO) benchmark. Our experiments on popular video object segmentation and multi-object segmentation tracking benchmarks, including DAVIS, YouTube-VOS, and BDD100K, suggest that a point-based segmentation tracker yields better zero-shot performance and efficient interactions. We release our code that integrates different point trackers and video segmentation benchmarks at https://github.com/SysCV/sam-pt.
The current approach for testing the robustness of object detectors suffers from serious deficiencies such as improper methods of performing out-of-distribution detection and using calibration metrics which do not consider both localisation and classification quality. In this work, we address these issues, and introduce the Self-Aware Object Detection (SAOD) task, a unified testing framework which respects and adheres to the challenges that object detectors face in safety-critical environments such as autonomous driving. Specifically, the SAOD task requires an object detector to be: robust to domain shift; obtain reliable uncertainty estimates for the entire scene; and provide calibrated confidence scores for the detections. We extensively use our framework, which introduces novel metrics and large scale test datasets, to test numerous object detectors in two different use-cases, allowing us to highlight critical insights into their robustness performance. Finally, we introduce a simple baseline for the SAOD task, enabling researchers to benchmark future proposed methods and move towards robust object detectors which are fit for purpose. Code is available at https://github.com/fiveai/saod
We present EgoCOL, an egocentric camera pose estimation method for open-world 3D object localization. Our method leverages sparse camera pose reconstructions in a two-fold manner, video and scan independently, to estimate the camera pose of egocentric frames in 3D renders with high recall and precision. We extensively evaluate our method on the Visual Query (VQ) 3D object localization Ego4D benchmark. EgoCOL can estimate 62% and 59% more camera poses than the Ego4D baseline in the Ego4D Visual Queries 3D Localization challenge at CVPR 2023 in the val and test sets, respectively. Our code is publicly available at https://github.com/BCV-Uniandes/EgoCOL
Multimodal Sarcasm Explanation (MuSE) is a new yet challenging task, which aims to generate a natural language sentence for a multimodal social post (an image as well as its caption) to explain why it contains sarcasm. Although the existing pioneer study has achieved great success with the BART backbone, it overlooks the gap between the visual feature space and the decoder semantic space, the object-level metadata of the image, as well as the potential external knowledge. To solve these limitations, in this work, we propose a novel mulTi-source sEmantic grAph-based Multimodal sarcasm explanation scheme, named TEAM. In particular, TEAM extracts the object-level semantic meta-data instead of the traditional global visual features from the input image. Meanwhile, TEAM resorts to ConceptNet to obtain the external related knowledge concepts for the input text and the extracted object meta-data. Thereafter, TEAM introduces a multi-source semantic graph that comprehensively characterize the multi-source (i.e., caption, object meta-data, external knowledge) semantic relations to facilitate the sarcasm reasoning. Extensive experiments on a public released dataset MORE verify the superiority of our model over cutting-edge methods.
Object detection on visible (RGB) and infrared (IR) images, as an emerging solution to facilitate robust detection for around-the-clock applications, has received extensive attention in recent years. With the help of IR images, object detectors have been more reliable and robust in practical applications by using RGB-IR combined information. However, existing methods still suffer from modality miscalibration and fusion imprecision problems. Since transformer has the powerful capability to model the pairwise correlations between different features, in this paper, we propose a novel Calibrated and Complementary Transformer called $\mathrm{C}^2$Former to address these two problems simultaneously. In $\mathrm{C}^2$Former, we design an Inter-modality Cross-Attention (ICA) module to obtain the calibrated and complementary features by learning the cross-attention relationship between the RGB and IR modality. To reduce the computational cost caused by computing the global attention in ICA, an Adaptive Feature Sampling (AFS) module is introduced to decrease the dimension of feature maps. Because $\mathrm{C}^2$Former performs in the feature domain, it can be embedded into existed RGB-IR object detectors via the backbone network. Thus, one single-stage and one two-stage object detector both incorporating our $\mathrm{C}^2$Former are constructed to evaluate its effectiveness and versatility. With extensive experiments on the DroneVehicle and KAIST RGB-IR datasets, we verify that our method can fully utilize the RGB-IR complementary information and achieve robust detection results. The code is available at https://github.com/yuanmaoxun/Calibrated-and-Complementary-Transformer-for-RGB-Infrared-Object-Detection.git.
Accurate and efficient segmentation of unknown objects in unstructured environments is essential for robotic manipulation. Unknown Object Instance Segmentation (UOIS), which aims to identify all objects in unknown categories and backgrounds, has become a key capability for various robotic tasks. However, existing methods struggle with over-segmentation and under-segmentation, leading to failures in manipulation tasks such as grasping. To address these challenges, we propose QuBER (Quadruple Boundary Error Refinement), a novel error-informed refinement approach for high-quality UOIS. QuBER first estimates quadruple boundary errors-true positive, true negative, false positive, and false negative pixels-at the instance boundaries of the initial segmentation. It then refines the segmentation using an error-guided fusion mechanism, effectively correcting both fine-grained and instance-level segmentation errors. Extensive evaluations on three public benchmarks demonstrate that QuBER outperforms state-of-the-art methods and consistently improves various UOIS methods while maintaining a fast inference time of less than 0.1 seconds. Furthermore, we show that QuBER improves the success rate of grasping target objects in cluttered environments. Code and supplementary materials are available at https://sites.google.com/view/uois-quber.
Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks. A common strategy for multi-scale feature extraction is adopting the classic top-down and bottom-up feature pyramid networks. However, these approaches suffer from the loss or degradation of feature information, impairing the fusion effect of non-adjacent levels. This paper proposes an asymptotic feature pyramid network (AFPN) to support direct interaction at non-adjacent levels. AFPN is initiated by fusing two adjacent low-level features and asymptotically incorporates higher-level features into the fusion process. In this way, the larger semantic gap between non-adjacent levels can be avoided. Given the potential for multi-object information conflicts to arise during feature fusion at each spatial location, adaptive spatial fusion operation is further utilized to mitigate these inconsistencies. We incorporate the proposed AFPN into both two-stage and one-stage object detection frameworks and evaluate with the MS-COCO 2017 validation and test datasets. Experimental evaluation shows that our method achieves more competitive results than other state-of-the-art feature pyramid networks. The code is available at \href{https://github.com/gyyang23/AFPN}{https://github.com/gyyang23/AFPN}.
Transfer learning aims to make the most of existing pre-trained models to achieve better performance on a new task in limited data scenarios. However, it is unclear which models will perform best on which task, and it is prohibitively expensive to try all possible combinations. If transferability estimation offers a computation-efficient approach to evaluate the generalisation ability of models, prior works focused exclusively on classification settings. To overcome this limitation, we extend transferability metrics to object detection. We design a simple method to extract local features corresponding to each object within an image using ROI-Align. We also introduce TLogME, a transferability metric taking into account the coordinates regression task. In our experiments, we compare TLogME to state-of-the-art metrics in the estimation of transfer performance of the Faster-RCNN object detector. We evaluate all metrics on source and target selection tasks, for real and synthetic datasets, and with different backbone architectures. We show that, over different tasks, TLogME using the local extraction method provides a robust correlation with transfer performance and outperforms other transferability metrics on local and global level features.
For 3D object manipulation, methods that build an explicit 3D representation perform better than those relying only on camera images. But using explicit 3D representations like voxels comes at large computing cost, adversely affecting scalability. In this work, we propose RVT, a multi-view transformer for 3D manipulation that is both scalable and accurate. Some key features of RVT are an attention mechanism to aggregate information across views and re-rendering of the camera input from virtual views around the robot workspace. In simulations, we find that a single RVT model works well across 18 RLBench tasks with 249 task variations, achieving 26% higher relative success than the existing state-of-the-art method (PerAct). It also trains 36X faster than PerAct for achieving the same performance and achieves 2.3X the inference speed of PerAct. Further, RVT can perform a variety of manipulation tasks in the real world with just a few ($\sim$10) demonstrations per task. Visual results, code, and trained model are provided at https://robotic-view-transformer.github.io/.
Blood cell detection is a typical small-scale object detection problem in computer vision. In this paper, we propose a CST-YOLO model for blood cell detection based on YOLOv7 architecture and enhance it with the CNN-Swin Transformer (CST), which is a new attempt at CNN-Transformer fusion. We also introduce three other useful modules: Weighted Efficient Layer Aggregation Networks (W-ELAN), Multiscale Channel Split (MCS), and Concatenate Convolutional Layers (CatConv) in our CST-YOLO to improve small-scale object detection precision. Experimental results show that the proposed CST-YOLO achieves 92.7%, 95.6%, and 91.1% [email omitted], respectively, on three blood cell datasets, outperforming state-of-the-art object detectors, e.g., RT-DETR, YOLOv5, and YOLOv7. Our code is available at https://github.com/mkang315/CST-YOLO.
Most recent 6D object pose methods use 2D optical flow to refine their results. However, the general optical flow methods typically do not consider the target's 3D shape information during matching, making them less effective in 6D object pose estimation. In this work, we propose a shape-constraint recurrent matching framework for 6D object pose estimation. We first compute a pose-induced flow based on the displacement of 2D reprojection between the initial pose and the currently estimated pose, which embeds the target's 3D shape implicitly. Then we use this pose-induced flow to construct the correlation map for the following matching iterations, which reduces the matching space significantly and is much easier to learn. Furthermore, we use networks to learn the object pose based on the current estimated flow, which facilitates the computation of the pose-induced flow for the next iteration and yields an end-to-end system for object pose. Finally, we optimize the optical flow and object pose simultaneously in a recurrent manner. We evaluate our method on three challenging 6D object pose datasets and show that it outperforms the state of the art significantly in both accuracy and efficiency.
We introduce the task of open-vocabulary 3D instance segmentation. Current approaches for 3D instance segmentation can typically only recognize object categories from a pre-defined closed set of classes that are annotated in the training datasets. This results in important limitations for real-world applications where one might need to perform tasks guided by novel, open-vocabulary queries related to a wide variety of objects. Recently, open-vocabulary 3D scene understanding methods have emerged to address this problem by learning queryable features for each point in the scene. While such a representation can be directly employed to perform semantic segmentation, existing methods cannot separate multiple object instances. In this work, we address this limitation, and propose OpenMask3D, which is a zero-shot approach for open-vocabulary 3D instance segmentation. Guided by predicted class-agnostic 3D instance masks, our model aggregates per-mask features via multi-view fusion of CLIP-based image embeddings. Experiments and ablation studies on ScanNet200 and Replica show that OpenMask3D outperforms other open-vocabulary methods, especially on the long-tail distribution. Qualitative experiments further showcase OpenMask3D's ability to segment object properties based on free-form queries describing geometry, affordances, and materials.
Deep learning-based object detectors have driven notable progress in multi-object tracking algorithms. Yet, current tracking methods mainly focus on simple, regular motion patterns in pedestrians or vehicles. This leaves a gap in tracking algorithms for targets with nonlinear, irregular motion, like athletes. Additionally, relying on the Kalman filter in recent tracking algorithms falls short when object motion defies its linear assumption. To overcome these issues, we propose a novel online and robust multi-object tracking approach named deep ExpansionIoU (Deep-EIoU), which focuses on multi-object tracking for sports scenarios. Unlike conventional methods, we abandon the use of the Kalman filter and leverage the iterative scale-up ExpansionIoU and deep features for robust tracking in sports scenarios. This approach achieves superior tracking performance without adopting a more robust detector, all while keeping the tracking process in an online fashion. Our proposed method demonstrates remarkable effectiveness in tracking irregular motion objects, achieving a score of 77.2% HOTA on the SportsMOT dataset and 85.4% HOTA on the SoccerNet-Tracking dataset. It outperforms all previous state-of-the-art trackers on various large-scale multi-object tracking benchmarks, covering various kinds of sports scenarios. The code and models are available at https://github.com/hsiangwei0903/Deep-EIoU.
Soft object manipulation tasks in domestic scenes pose a significant challenge for existing robotic skill learning techniques due to their complex dynamics and variable shape characteristics. Since learning new manipulation skills from human demonstration is an effective way for robot applications, developing prior knowledge of the representation and dynamics of soft objects is necessary. In this regard, we propose a pre-trained soft object manipulation skill learning model, namely SoftGPT, that is trained using large amounts of exploration data, consisting of a three-dimensional heterogeneous graph representation and a GPT-based dynamics model. For each downstream task, a goal-oriented policy agent is trained to predict the subsequent actions, and SoftGPT generates the consequences of these actions. Integrating these two approaches establishes a thinking process in the robot's mind that provides rollout for facilitating policy learning. Our results demonstrate that leveraging prior knowledge through this thinking process can efficiently learn various soft object manipulation skills, with the potential for direct learning from human demonstrations.
Online unsupervised video object segmentation (UVOS) uses the previous frames as its input to automatically separate the primary object(s) from a streaming video without using any further manual annotation. A major challenge is that the model has no access to the future and must rely solely on the history, i.e., the segmentation mask is predicted from the current frame as soon as it is captured. In this work, a novel contrastive motion clustering algorithm with an optical flow as its input is proposed for the online UVOS by exploiting the common fate principle that visual elements tend to be perceived as a group if they possess the same motion pattern. We build a simple and effective auto-encoder to iteratively summarize non-learnable prototypical bases for the motion pattern, while the bases in turn help learn the representation of the embedding network. Further, a contrastive learning strategy based on a boundary prior is developed to improve foreground and background feature discrimination in the representation learning stage. The proposed algorithm can be optimized on arbitrarily-scale data i.e., frame, clip, dataset) and performed in an online fashion. Experiments on $\textit{DAVIS}_{\textit{16}}$, $\textit{FBMS}$, and $\textit{SegTrackV2}$ datasets show that the accuracy of our method surpasses the previous state-of-the-art (SoTA) online UVOS method by a margin of 0.8%, 2.9%, and 1.1%, respectively. Furthermore, by using an online deep subspace clustering to tackle the motion grouping, our method is able to achieve higher accuracy at $3\times$ faster inference time compared to SoTA online UVOS method, and making a good trade-off between effectiveness and efficiency. Our code is available at https://github.com/xilin1991/ClusterNet.
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained visual understanding that is best described by natural language. We propose a unified model, and demonstrate how our end-to-end approach is more accurate and temporally coherent than a multi-stage pipeline combining state-of-the-art detection, tracking, and captioning models. Moreover, we propose a training strategy based on a mixture of disjoint tasks, which allows us to leverage diverse, large-scale datasets which supervise different parts of our model. Although each pretraining task only provides weak supervision, they are complementary and, when combined, result in noteworthy zero-shot ability and serve as strong initialization for additional finetuning to further improve accuracy. We carefully design new metrics capturing all components of our task, and show how we can repurpose existing video grounding datasets (e.g. VidSTG and VLN) for our new task. We show that our model improves upon a number of strong baselines for this new task. Furthermore, we can apply our model to the task of spatial grounding, outperforming prior state-of-the-art on VidSTG and VLN, without explicitly training for it. Code is available at https://github.com/google-research/scenic/tree/main/scenic/projects/densevoc.
Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across the video, and instead process all the tokens in the video. In this paper, we investigate how we can use knowledge of objects to design better video models, namely to process fewer tokens and to improve recognition accuracy. This is in contrast to prior works which either drop tokens at the cost of accuracy, or increase accuracy whilst also increasing the computation required. First, we propose an object-guided token sampling strategy that enables us to retain a small fraction of the input tokens with minimal impact on accuracy. And second, we propose an object-aware attention module that enriches our feature representation with object information and improves overall accuracy. Our resulting framework achieves better performance when using fewer tokens than strong baselines. In particular, we match our baseline with 30%, 40%, and 60% of the input tokens on SomethingElse, Something-something v2, and Epic-Kitchens, respectively. When we use our model to process the same number of tokens as our baseline, we improve by 0.6 to 4.2 points on these datasets.
Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this paper, we present a general and effective prediction mimicking distillation scheme, called CrossKD, which delivers the intermediate features of the student's detection head to the teacher's detection head. The resulting cross-head predictions are then forced to mimic the teacher's predictions. This manner relieves the student's head from receiving contradictory supervision signals from the annotations and the teacher's predictions, greatly improving the student's detection performance. Moreover, as mimicking the teacher's predictions is the target of KD, CrossKD offers more task-oriented information in contrast with feature imitation. On MS COCO, with only prediction mimicking losses applied, our CrossKD boosts the average precision of GFL ResNet-50 with 1x training schedule from 40.2 to 43.7, outperforming all existing KD methods. In addition, our method also works well when distilling detectors with heterogeneous backbones. Code is available at https://github.com/jbwang1997/CrossKD.