PyTorchKR Papers

최신 논문

총 9,712편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2209.07922공식 코드 · Papers with Code

An Attention-guided Multistream Feature Fusion Network for Localization of Risky Objects in Driving Videos

Detecting dangerous traffic agents in videos captured by vehicle-mounted dashboard cameras (dashcams) is essential to facilitate safe navigation in a complex environment. Accident-related videos are just a minor portion of the driving video big data, and the transient pre-accident processes are highly dynamic and complex. Besides, risky and non-risky traffic agents can be similar in their appearance. These make risky object localization in the driving video particularly challenging. To this end, this paper proposes an attention-guided multistream feature fusion network (AM-Net) to localize dangerous traffic agents from dashcam videos. Two Gated Recurrent Unit (GRU) networks use object bounding box and optical flow features extracted from consecutive video frames to capture spatio-temporal cues for distinguishing dangerous traffic agents. An attention module coupled with the GRUs learns to attend to the traffic agents relevant to an accident. Fusing the two streams of features, AM-Net predicts the riskiness scores of traffic agents in the video. In supporting this study, the paper also introduces a benchmark dataset called Risky Object Localization (ROL). The dataset contains spatial, temporal, and categorical annotations with the accident, object, and scene-level attributes. The proposed AM-Net achieves a promising performance of 85.73% AUC on the ROL dataset. Meanwhile, the AM-Net outperforms current state-of-the-art for video anomaly detection by 6.3% AUC on the DoTA dataset. A thorough ablation study further reveals AM-Net's merits by evaluating the contributions of its different components.

arXiv:2209.07888

TwistSLAM++: Fusing multiple modalities for accurate dynamic semantic SLAM

Most classical SLAM systems rely on the static scene assumption, which limits their applicability in real world scenarios. Recent SLAM frameworks have been proposed to simultaneously track the camera and moving objects. However they are often unable to estimate the canonical pose of the objects and exhibit a low object tracking accuracy. To solve this problem we propose TwistSLAM++, a semantic, dynamic, SLAM system that fuses stereo images and LiDAR information. Using semantic information, we track potentially moving objects and associate them to 3D object detections in LiDAR scans to obtain their pose and size. Then, we perform registration on consecutive object scans to refine object pose estimation. Finally, object scans are used to estimate the shape of the object and constrain map points to lie on the estimated surface within the BA. We show on classical benchmarks that this fusion approach based on multimodal information improves the accuracy of object tracking.

arXiv:2209.07761공식 코드 · Papers with Code

Expansion and Shrinkage of Localization for Weakly-Supervised Semantic Segmentation

Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for weakly-supervised semantic segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To tackle with this issue, this paper proposes an Expansion and Shrinkage scheme based on the offset learning in the deformable convolution, to sequentially improve the recall and precision of the located object in the two respective stages. In the Expansion stage, an offset learning branch in a deformable convolution layer, referred as "expansion sampler" seeks for sampling increasingly less discriminative object regions, driven by an inverse supervision signal that maximizes image-level classification loss. The located more complete object in the Expansion stage is then gradually narrowed down to the final object region during the Shrinkage stage. In the Shrinkage stage, the offset learning branch of another deformable convolution layer, referred as "shrinkage sampler", is introduced to exclude the false positive background regions attended in the Expansion stage to improve the precision of the localization maps. We conduct various experiments on PASCAL VOC 2012 and MS COCO 2014 to well demonstrate the superiority of our method over other state-of-the-art methods for weakly-supervised semantic segmentation. Code will be made publicly available here https://github.com/TyroneLi/ESOL_WSSS.

arXiv:2209.07619

Hierarchical Superquadric Decomposition with Implicit Space Separation

We introduce a new method to reconstruct 3D objects using a set of volumetric primitives, i.e., superquadrics. The method hierarchically decomposes a target 3D object into pairs of superquadrics recovering finer and finer details. While such hierarchical methods have been studied before, we introduce a new way of splitting the object space using only properties of the predicted superquadrics. The method is trained and evaluated on the ShapeNet dataset. The results of our experiments suggest that reasonable reconstructions can be obtained with the proposed approach for a diverse set of objects with complex geometry.

arXiv:2209.07601

Towards Improving Calibration in Object Detection Under Domain Shift

With deep neural network based solution more readily being incorporated in real-world applications, it has been pressing requirement that predictions by such models, especially in safety-critical environments, be highly accurate and well-calibrated. Although some techniques addressing DNN calibration have been proposed, they are only limited to visual classification applications and in-domain predictions. Unfortunately, very little to no attention is paid towards addressing calibration of DNN-based visual object detectors, that occupy similar space and importance in many decision making systems as their visual classification counterparts. In this work, we study the calibration of DNN-based object detection models, particularly under domain shift. To this end, we first propose a new, plug-and-play, train-time calibration loss for object detection (coined as TCD). It can be used with various application-specific loss functions as an auxiliary loss function to improve detection calibration. Second, we devise a new implicit technique for improving calibration in self-training based domain adaptive detectors, featuring a new uncertainty quantification mechanism for object detection. We demonstrate TCD is capable of enhancing calibration with notable margins (1) across different DNN-based object detection paradigms both in in-domain and out-of-domain predictions, and (2) in different domain-adaptive detectors across challenging adaptation scenarios. Finally, we empirically show that our implicit calibration technique can be used in tandem with TCD during adaptation to further boost calibration in diverse domain shift scenarios.

arXiv:2209.07147공식 코드 · Papers with Code

One-Shot Transfer of Affordance Regions? AffCorrs!

In this work, we tackle one-shot visual search of object parts. Given a single reference image of an object with annotated affordance regions, we segment semantically corresponding parts within a target scene. We propose AffCorrs, an unsupervised model that combines the properties of pre-trained DINO-ViT's image descriptors and cyclic correspondences. We use AffCorrs to find corresponding affordances both for intra- and inter-class one-shot part segmentation. This task is more difficult than supervised alternatives, but enables future work such as learning affordances via imitation and assisted teleoperation.

arXiv:2209.06641

CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection

Existing deep learning-based 3D object detectors typically rely on the appearance of individual objects and do not explicitly pay attention to the rich contextual information of the scene. In this work, we propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework, which takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene at multiple levels to predict a set of object bounding-boxes along with their corresponding semantic labels. To this end, we propose to utilize a context enhancement network that captures the contextual information at different levels of granularity followed by a multi-stage refinement module to progressively refine the box positions and class predictions. Extensive experiments on the large-scale ScanNetV2 benchmark reveal the benefits of our proposed method, leading to an absolute improvement of 2.0% over the baseline. In addition to 3D object detection, we investigate the effectiveness of our CMR3D framework for the problem of 3D object counting. Our source code will be publicly released.

arXiv:2209.05946공식 코드 · Papers with Code

OmDet: Large-scale vision-language multi-dataset pre-training with multimodal detection network

The advancement of object detection (OD) in open-vocabulary and open-world scenarios is a critical challenge in computer vision. This work introduces OmDet, a novel language-aware object detection architecture, and an innovative training mechanism that harnesses continual learning and multi-dataset vision-language pre-training. Leveraging natural language as a universal knowledge representation, OmDet accumulates a "visual vocabulary" from diverse datasets, unifying the task as a language-conditioned detection framework. Our multimodal detection network (MDN) overcomes the challenges of multi-dataset joint training and generalizes to numerous training datasets without manual label taxonomy merging. We demonstrate superior performance of OmDet over strong baselines in object detection in the wild, open-vocabulary detection, and phrase grounding, achieving state-of-the-art results. Ablation studies reveal the impact of scaling the pre-training visual vocabulary, indicating a promising direction for further expansion to larger datasets. The effectiveness of our deep fusion approach is underscored by its ability to learn jointly from multiple datasets, enhancing performance through knowledge sharing.

arXiv:2209.05654

ComplETR: Reducing the cost of annotations for object detection in dense scenes with vision transformers

Annotating bounding boxes for object detection is expensive, time-consuming, and error-prone. In this work, we propose a DETR based framework called ComplETR that is designed to explicitly complete missing annotations in partially annotated dense scene datasets. This reduces the need to annotate every object instance in the scene thereby reducing annotation cost. ComplETR augments object queries in DETR decoder with patch information of objects in the image. Combined with a matching loss, it can effectively find objects that are similar to the input patch and complete the missing annotations. We show that our framework outperforms the state-of-the-art methods such as Soft Sampling and Unbiased Teacher by itself, while at the same time can be used in conjunction with these methods to further improve their performance. Our framework is also agnostic to the choice of the downstream object detectors; we show performance improvement for several popular detectors such as Faster R-CNN, Cascade R-CNN, CenterNet2, and Deformable DETR on multiple dense scene datasets.

arXiv:2209.05624공식 코드 · Papers with Code

Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features

We consider the problem of category-level 6D pose estimation from a single RGB image. Our approach represents an object category as a cuboid mesh and learns a generative model of the neural feature activations at each mesh vertex to perform pose estimation through differentiable rendering. A common problem of rendering-based approaches is that they rely on bounding box proposals, which do not convey information about the 3D rotation of the object and are not reliable when objects are partially occluded. Instead, we introduce a coarse-to-fine optimization strategy that utilizes the rendering process to estimate a sparse set of 6D object proposals, which are subsequently refined with gradient-based optimization. The key to enabling the convergence of our approach is a neural feature representation that is trained to be scale- and rotation-invariant using contrastive learning. Our experiments demonstrate an enhanced category-level 6D pose estimation performance compared to prior work, particularly under strong partial occlusion.

arXiv:2209.05612공식 코드 · Papers with Code

Articulated 3D Human-Object Interactions from RGB Videos: An Empirical Analysis of Approaches and Challenges

Human-object interactions with articulated objects are common in everyday life. Despite much progress in single-view 3D reconstruction, it is still challenging to infer an articulated 3D object model from an RGB video showing a person manipulating the object. We canonicalize the task of articulated 3D human-object interaction reconstruction from RGB video, and carry out a systematic benchmark of five families of methods for this task: 3D plane estimation, 3D cuboid estimation, CAD model fitting, implicit field fitting, and free-form mesh fitting. Our experiments show that all methods struggle to obtain high accuracy results even when provided ground truth information about the observed objects. We identify key factors which make the task challenging and suggest directions for future work on this challenging 3D computer vision task. Short video summary at https://www.youtube.com/watch?v=5tAlKBojZwc

arXiv:2209.05588공식 코드 · Papers with Code

CenterFormer: Center-based Transformer for 3D Object Detection

Query-based transformer has shown great potential in constructing long-range attention in many image-domain tasks, but has rarely been considered in LiDAR-based 3D object detection due to the overwhelming size of the point cloud data. In this paper, we propose CenterFormer, a center-based transformer network for 3D object detection. CenterFormer first uses a center heatmap to select center candidates on top of a standard voxel-based point cloud encoder. It then uses the feature of the center candidate as the query embedding in the transformer. To further aggregate features from multiple frames, we design an approach to fuse features through cross-attention. Lastly, regression heads are added to predict the bounding box on the output center feature representation. Our design reduces the convergence difficulty and computational complexity of the transformer structure. The results show significant improvements over the strong baseline of anchor-free object detection networks. CenterFormer achieves state-of-the-art performance for a single model on the Waymo Open Dataset, with 73.7% mAPH on the validation set and 75.6% mAPH on the test set, significantly outperforming all previously published CNN and transformer-based methods. Our code is publicly available at https://github.com/TuSimple/centerformer

arXiv:2209.05194

Graphing the Future: Activity and Next Active Object Prediction using Graph-based Activity Representations

We present a novel approach for the visual prediction of human-object interactions in videos. Rather than forecasting the human and object motion or the future hand-object contact points, we aim at predicting (a)the class of the on-going human-object interaction and (b) the class(es) of the next active object(s) (NAOs), i.e., the object(s) that will be involved in the interaction in the near future as well as the time the interaction will occur. Graph matching relies on the efficient Graph Edit distance (GED) method. The experimental evaluation of the proposed approach was conducted using two well-established video datasets that contain human-object interactions, namely the MSR Daily Activities and the CAD120. High prediction accuracy was obtained for both action prediction and NAO forecasting.

arXiv:2209.04966

Multi-modal Streaming 3D Object Detection

Modern autonomous vehicles rely heavily on mechanical LiDARs for perception. Current perception methods generally require 360{\deg} point clouds, collected sequentially as the LiDAR scans the azimuth and acquires consecutive wedge-shaped slices. The acquisition latency of a full scan (~ 100ms) may lead to outdated perception which is detrimental to safe operation. Recent streaming perception works proposed directly processing LiDAR slices and compensating for the narrow field of view (FOV) of a slice by reusing features from preceding slices. These works, however, are all based on a single modality and require past information which may be outdated. Meanwhile, images from high-frequency cameras can support streaming models as they provide a larger FoV compared to a LiDAR slice. However, this difference in FoV complicates sensor fusion. To address this research gap, we propose an innovative camera-LiDAR streaming 3D object detection framework that uses camera images instead of past LiDAR slices to provide an up-to-date, dense, and wide context for streaming perception. The proposed method outperforms prior streaming models on the challenging NuScenes benchmark. It also outperforms powerful full-scan detectors while being much faster. Our method is shown to be robust to missing camera images, narrow LiDAR slices, and small camera-LiDAR miscalibration.

arXiv:2209.04796

Multiple Object Tracking in Recent Times: A Literature Review

Multiple object tracking gained a lot of interest from researchers in recent years, and it has become one of the trending problems in computer vision, especially with the recent advancement of autonomous driving. MOT is one of the critical vision tasks for different issues like occlusion in crowded scenes, similar appearance, small object detection difficulty, ID switching, etc. To tackle these challenges, as researchers tried to utilize the attention mechanism of transformer, interrelation of tracklets with graph convolutional neural network, appearance similarity of objects in different frames with the siamese network, they also tried simple IOU matching based CNN network, motion prediction with LSTM. To take these scattered techniques under an umbrella, we have studied more than a hundred papers published over the last three years and have tried to extract the techniques that are more focused on by researchers in recent times to solve the problems of MOT. We have enlisted numerous applications, possibilities, and how MOT can be related to real life. Our review has tried to show the different perspectives of techniques that researchers used overtimes and give some future direction for the potential researchers. Moreover, we have included popular benchmark datasets and metrics in this review.

arXiv:2209.05022공식 코드 · Papers with Code

PoseIt: A Visual-Tactile Dataset of Holding Poses for Grasp Stability Analysis

When humans grasp objects in the real world, we often move our arms to hold the object in a different pose where we can use it. In contrast, typical lab settings only study the stability of the grasp immediately after lifting, without any subsequent re-positioning of the arm. However, the grasp stability could vary widely based on the object's holding pose, as the gravitational torque and gripper contact forces could change completely. To facilitate the study of how holding poses affect grasp stability, we present PoseIt, a novel multi-modal dataset that contains visual and tactile data collected from a full cycle of grasping an object, re-positioning the arm to one of the sampled poses, and shaking the object. Using data from PoseIt, we can formulate and tackle the task of predicting whether a grasped object is stable in a particular held pose. We train an LSTM classifier that achieves 85% accuracy on the proposed task. Our experimental results show that multi-modal models trained on PoseIt achieve higher accuracy than using solely vision or tactile data and that our classifiers can also generalize to unseen objects and poses.

arXiv:2209.05432

Self-supervised Wide Baseline Visual Servoing via 3D Equivariance

One of the challenging input settings for visual servoing is when the initial and goal camera views are far apart. Such settings are difficult because the wide baseline can cause drastic changes in object appearance and cause occlusions. This paper presents a novel self-supervised visual servoing method for wide baseline images which does not require 3D ground truth supervision. Existing approaches that regress absolute camera pose with respect to an object require 3D ground truth data of the object in the forms of 3D bounding boxes or meshes. We learn a coherent visual representation by leveraging a geometric property called 3D equivariance-the representation is transformed in a predictable way as a function of 3D transformation. To ensure that the feature-space is faithful to the underlying geodesic space, a geodesic preserving constraint is applied in conjunction with the equivariance. We design a Siamese network that can effectively enforce these two geometric properties without requiring 3D supervision. With the learned model, the relative transformation can be inferred simply by following the gradient in the learned space and used as feedback for closed-loop visual servoing. Our method is evaluated on objects from the YCB dataset, showing meaningful outperformance on a visual servoing task, or object alignment task with respect to state-of-the-art approaches that use 3D supervision. Ours yields more than 35% average distance error reduction and more than 90% success rate with 3cm error tolerance.

arXiv:2209.04061

im2nerf: Image to Neural Radiance Field in the Wild

We propose im2nerf, a learning framework that predicts a continuous neural object representation given a single input image in the wild, supervised by only segmentation output from off-the-shelf recognition methods. The standard approach to constructing neural radiance fields takes advantage of multi-view consistency and requires many calibrated views of a scene, a requirement that cannot be satisfied when learning on large-scale image data in the wild. We take a step towards addressing this shortcoming by introducing a model that encodes the input image into a disentangled object representation that contains a code for object shape, a code for object appearance, and an estimated camera pose from which the object image is captured. Our model conditions a NeRF on the predicted object representation and uses volume rendering to generate images from novel views. We train the model end-to-end on a large collection of input images. As the model is only provided with single-view images, the problem is highly under-constrained. Therefore, in addition to using a reconstruction loss on the synthesized input view, we use an auxiliary adversarial loss on the novel rendered views. Furthermore, we leverage object symmetry and cycle camera pose consistency. We conduct extensive quantitative and qualitative experiments on the ShapeNet dataset as well as qualitative experiments on Open Images dataset. We show that in all cases, im2nerf achieves the state-of-the-art performance for novel view synthesis from a single-view unposed image in the wild.

arXiv:2209.04300공식 코드 · Papers with Code

Towards Confidence-guided Shape Completion for Robotic Applications

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only provide incomplete information due to limited workspaces, clutter or object self-occlusion. In recent years, deep learning architectures for shape completion have begun taking traction as effective means of inferring a complete 3D object representation from partial visual data. Nevertheless, most of the existing state-of-the-art approaches provide a fixed output resolution in the form of voxel grids, strictly related to the size of the neural network output stage. While this is enough for some tasks, e.g. obstacle avoidance in navigation, grasping and manipulation require finer resolutions and simply scaling up the neural network outputs is computationally expensive. In this paper, we address this limitation by proposing an object shape completion method based on an implicit 3D representation providing a confidence value for each reconstructed point. As a second contribution, we propose a gradient-based method for efficiently sampling such implicit function at an arbitrary resolution, tunable at inference time. We experimentally validate our approach by comparing reconstructed shapes with ground truths, and by deploying our shape completion algorithm in a robotic grasping pipeline. In both cases, we compare results with a state-of-the-art shape completion approach.

arXiv:2209.04183

Generative Deformable Radiance Fields for Disentangled Image Synthesis of Topology-Varying Objects

3D-aware generative models have demonstrated their superb performance to generate 3D neural radiance fields (NeRF) from a collection of monocular 2D images even for topology-varying object categories. However, these methods still lack the capability to separately control the shape and appearance of the objects in the generated radiance fields. In this paper, we propose a generative model for synthesizing radiance fields of topology-varying objects with disentangled shape and appearance variations. Our method generates deformable radiance fields, which builds the dense correspondence between the density fields of the objects and encodes their appearances in a shared template field. Our disentanglement is achieved in an unsupervised manner without introducing extra labels to previous 3D-aware GAN training. We also develop an effective image inversion scheme for reconstructing the radiance field of an object in a real monocular image and manipulating its shape and appearance. Experiments show that our method can successfully learn the generative model from unstructured monocular images and well disentangle the shape and appearance for objects (e.g., chairs) with large topological variance. The model trained on synthetic data can faithfully reconstruct the real object in a given single image and achieve high-quality texture and shape editing results.