PyTorchKR Papers

최신 논문

총 2,547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2103.03510공식 코드 · Papers with Code

Variational Structured Attention Networks for Deep Visual Representation Learning

Convolutional neural networks have enabled major progress in addressing pixel-level prediction tasks such as semantic segmentation, depth estimation, surface normal prediction, and so on, benefiting from their powerful capabilities in visual representation learning. Typically, state-of-the-art models integrates attention mechanisms for improved deep feature representations. Recently, some works have demonstrated the significance of learning and combining both spatial- and channel-wise attentions for deep feature refinement. In this paper, we aim at effectively boosting previous approaches and propose a unified deep framework to jointly learn both spatial attention maps and channel attention vectors in a principled manner so as to structure the resulting attention tensors and model interactions between these two types of attentions. Specifically, we integrate the estimation and the interaction of the attentions within a probabilistic representation learning framework, leading to Variational STructured Attention networks (VISTA-Net). We implement the inference rules within the neural network, thus allowing for end-to-end learning of the probabilistic and the CNN front-end parameters. As demonstrated by our extensive empirical evaluation on six large-scale datasets for dense visual prediction, VISTA-Net outperforms the state-of-the-art in multiple continuous and discrete prediction tasks, thus confirming the benefit of the proposed approach in joint structured spatial-channel attention estimation for deep representation learning. The code is available at https://github.com/ygjwd12345/VISTA-Net.

arXiv:2103.03480

IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image

3D object detection from a single image is an important task in Autonomous Driving (AD), where various approaches have been proposed. However, the task is intrinsically ambiguous and challenging as single image depth estimation is already an ill-posed problem. In this paper, we propose an instance-aware approach to aggregate useful information for improving the accuracy of 3D object detection with the following contributions. First, an instance-aware feature aggregation (IAFA) module is proposed to collect local and global features for 3D bounding boxes regression. Second, we empirically find that the spatial attention module can be well learned by taking coarse-level instance annotations as a supervision signal. The proposed module has significantly boosted the performance of the baseline method on both 3D detection and 2D bird-eye's view of vehicle detection among all three categories. Third, our proposed method outperforms all single image-based approaches (even these methods trained with depth as auxiliary inputs) and achieves state-of-the-art 3D detection performance on the KITTI benchmark.

arXiv:2103.03435공식 코드 · Papers with Code

Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks

Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion, one requires extra models to generate superpixels and special operations such as graph convolution. In this paper, we propose a way to implicitly integrate a superpixel scheme into CNNs, which makes it easy to use superpixels with CNNs in an end-to-end fashion. Our proposed method hierarchically groups pixels at downsampling layers and generates superpixels. Our method can be plugged into many existing architectures without a change in their feed-forward path because our method does not use superpixels in the feed-forward path but use them to recover the lost resolution instead of bilinear upsampling. As a result, our method preserves detailed information such as object boundaries in the form of superpixels even when the model contains downsampling layers. We evaluate our method on several tasks such as semantic segmentation, superpixel segmentation, and monocular depth estimation, and confirm that it speeds up modern architectures and/or improves their prediction accuracy in these tasks.

arXiv:2103.03319공식 코드 · Papers with Code

Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos

A key challenge of learning a visual representation for the 3D high fidelity geometry of dressed humans lies in the limited availability of the ground truth data (e.g., 3D scanned models), which results in the performance degradation of 3D human reconstruction when applying to real-world imagery. We address this challenge by leveraging a new data resource: a number of social media dance videos that span diverse appearance, clothing styles, performances, and identities. Each video depicts dynamic movements of the body and clothes of a single person while lacking the 3D ground truth geometry. To learn a visual representation from these videos, we present a new self-supervised learning method to use the local transformation that warps the predicted local geometry of the person from an image to that of another image at a different time instant. This allows self-supervision by enforcing a temporal coherence over the predictions. In addition, we jointly learn the depths along with the surface normals that are highly responsive to local texture, wrinkle, and shade by maximizing their geometric consistency. Our method is end-to-end trainable, resulting in high fidelity depth estimation that predicts fine geometry faithful to the input real image. We further provide a theoretical bound of self-supervised learning via an uncertainty analysis that characterizes the performance of the self-supervised learning without training. We demonstrate that our method outperforms the state-of-the-art human depth estimation and human shape recovery approaches on both real and rendered images.

arXiv:2103.02396

$S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation

Dense depth estimation plays a key role in multiple applications such as robotics, 3D reconstruction, and augmented reality. While sparse signal, e.g., LiDAR and Radar, has been leveraged as guidance for enhancing dense depth estimation, the improvement is limited due to its low density and imbalanced distribution. To maximize the utility from the sparse source, we propose $S^3$ technique, which expands the depth value from sparse cues while estimating the confidence of expanded region. The proposed $S^3$ can be applied to various guided depth estimation approaches and trained end-to-end at different stages, including input, cost volume and output. Extensive experiments demonstrate the effectiveness, robustness, and flexibility of the $S^3$ technique on LiDAR and Radar signal.

arXiv:2103.02451공식 코드 · Papers with Code

Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation

Dense depth estimation is essential to scene-understanding for autonomous driving. However, recent self-supervised approaches on monocular videos suffer from scale-inconsistency across long sequences. Utilizing data from the ubiquitously copresent global positioning systems (GPS), we tackle this challenge by proposing a dynamically-weighted GPS-to-Scale (g2s) loss to complement the appearance-based losses. We emphasize that the GPS is needed only during the multimodal training, and not at inference. The relative distance between frames captured through the GPS provides a scale signal that is independent of the camera setup and scene distribution, resulting in richer learned feature representations. Through extensive evaluation on multiple datasets, we demonstrate scale-consistent and -aware depth estimation during inference, improving the performance even when training with low-frequency GPS data.

arXiv:2103.01100공식 코드 · Papers with Code

Categorical Depth Distribution Network for Monocular 3D Object Detection

Monocular 3D object detection is a key problem for autonomous vehicles, as it provides a solution with simple configuration compared to typical multi-sensor systems. The main challenge in monocular 3D detection lies in accurately predicting object depth, which must be inferred from object and scene cues due to the lack of direct range measurement. Many methods attempt to directly estimate depth to assist in 3D detection, but show limited performance as a result of depth inaccuracy. Our proposed solution, Categorical Depth Distribution Network (CaDDN), uses a predicted categorical depth distribution for each pixel to project rich contextual feature information to the appropriate depth interval in 3D space. We then use the computationally efficient bird's-eye-view projection and single-stage detector to produce the final output bounding boxes. We design CaDDN as a fully differentiable end-to-end approach for joint depth estimation and object detection. We validate our approach on the KITTI 3D object detection benchmark, where we rank 1st among published monocular methods. We also provide the first monocular 3D detection results on the newly released Waymo Open Dataset. We provide a code release for CaDDN which is made available.

arXiv:2103.00853

ADAADepth: Adapting Data Augmentation and Attention for Self-Supervised Monocular Depth Estimation

Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learning accurate and robust depth. We propose a relational self-attention module that learns rich contextual features and further enhances depth results. We also optimize the auto-masking strategy across all losses by enforcing L1 regularisation over mask. Our novel progressive training strategy first learns depth at a lower resolution and then progresses to the original resolution with slight training. We utilise a ResNet18 encoder, learning features for prediction of both depth and pose. We evaluate our predicted depth on the standard KITTI driving dataset and achieve state-of-the-art results for monocular depth estimation whilst having significantly lower number of trainable parameters in our deep learning framework. We also evaluate our model on Make3D dataset showing better generalization than other methods.

arXiv:2103.00854

Vyākarana: A Colorless Green Benchmark for Syntactic Evaluation in Indic Languages

While there has been significant progress towards developing NLU resources for Indic languages, syntactic evaluation has been relatively less explored. Unlike English, Indic languages have rich morphosyntax, grammatical genders, free linear word-order, and highly inflectional morphology. In this paper, we introduce Vy\=akarana: a benchmark of Colorless Green sentences in Indic languages for syntactic evaluation of multilingual language models. The benchmark comprises four syntax-related tasks: PoS Tagging, Syntax Tree-depth Prediction, Grammatical Case Marking, and Subject-Verb Agreement. We use the datasets from the evaluation tasks to probe five multilingual language models of varying architectures for syntax in Indic languages. Due to its prevalence, we also include a code-switching setting in our experiments. Our results show that the token-level and sentence-level representations from the Indic language models (IndicBERT and MuRIL) do not capture the syntax in Indic languages as efficiently as the other highly multilingual language models. Further, our layer-wise probing experiments reveal that while mBERT, DistilmBERT, and XLM-R localize the syntax in middle layers, the Indic language models do not show such syntactic localization.

arXiv:2103.00369공식 코드 · Papers with Code

Towards Continual, Online, Self-Supervised Depth

Although depth extraction with passive sensors has seen remarkable improvement with deep learning, these approaches may fail to obtain correct depth if they are exposed to environments not observed during training. Online adaptation, where the neural network trains while deployed, with self-supervised learning provides a convenient solution as the network can learn from the scene where it is deployed without external supervision. However, online adaptation causes a neural network to forget the past. Thus, past training is wasted and the network is not able to provide good results if it observes past scenes. This work deals with practical online-adaptation where the input is online and temporally-correlated, and training is completely self-supervised. Regularization and replay-based methods without task boundaries are proposed to avoid catastrophic forgetting while adapting to online data. Effort has been made to make the proposed approach suitable for practical use. We apply our method to both structure-from-motion and stereo depth estimation. We evaluate our method on diverse public datasets that include outdoor, indoor and synthetic scenes. Qualitative and quantitative results with both structure-from-motion and stereo show superior forgetting as well as adaptation performance compared to recent methods. Furthermore, the proposed method incurs negligible overhead compared to fine-tuning for online adaptation, proving to be an adequate choice in terms of plasticity, stability and applicability. The proposed approach is more inline with the artificial general intelligence paradigm as the neural network learns continually with no supervision. Source code is available at https://github.com/umarKarim/cou_sfm and https://github.com/umarKarim/cou_stereo.

arXiv:2102.13588

3D Vessel Reconstruction in OCT-Angiography via Depth Map Estimation

Optical Coherence Tomography Angiography (OCTA) has been increasingly used in the management of eye and systemic diseases in recent years. Manual or automatic analysis of blood vessel in 2D OCTA images (en face angiograms) is commonly used in clinical practice, however it may lose rich 3D spatial distribution information of blood vessels or capillaries that are useful for clinical decision-making. In this paper, we introduce a novel 3D vessel reconstruction framework based on the estimation of vessel depth maps from OCTA images. First, we design a network with structural constraints to predict the depth of blood vessels in OCTA images. In order to promote the accuracy of the predicted depth map at both the overall structure- and pixel- level, we combine MSE and SSIM loss as the training loss function. Finally, the 3D vessel reconstruction is achieved by utilizing the estimated depth map and 2D vessel segmentation results. Experimental results demonstrate that our method is effective in the depth prediction and 3D vessel reconstruction for OCTA images.% results may be used to guide subsequent vascular analysis

arXiv:2102.13258공식 코드 · Papers with Code

Boundary-induced and scene-aggregated network for monocular depth prediction

Monocular depth prediction is an important task in scene understanding. It aims to predict the dense depth of a single RGB image. With the development of deep learning, the performance of this task has made great improvements. However, two issues remain unresolved: (1) The deep feature encodes the wrong farthest region in a scene, which leads to a distorted 3D structure of the predicted depth; (2) The low-level features are insufficient utilized, which makes it even harder to estimate the depth near the edge with sudden depth change. To tackle these two issues, we propose the Boundary-induced and Scene-aggregated network (BS-Net). In this network, the Depth Correlation Encoder (DCE) is first designed to obtain the contextual correlations between the regions in an image, and perceive the farthest region by considering the correlations. Meanwhile, the Bottom-Up Boundary Fusion (BUBF) module is designed to extract accurate boundary that indicates depth change. Finally, the Stripe Refinement module (SRM) is designed to refine the dense depth induced by the boundary cue, which improves the boundary accuracy of the predicted depth. Several experimental results on the NYUD v2 dataset and \xff{the iBims-1 dataset} illustrate the state-of-the-art performance of the proposed approach. And the SUN-RGBD dataset is employed to evaluate the generalization of our method. Code is available at https://github.com/XuefengBUPT/BS-Net.

arXiv:2102.10514

Progressive Depth Learning for Single Image Dehazing

The formulation of the hazy image is mainly dominated by the reflected lights and ambient airlight. Existing dehazing methods often ignore the depth cues and fail in distant areas where heavier haze disturbs the visibility. However, we note that the guidance of the depth information for transmission estimation could remedy the decreased visibility as distances increase. In turn, the good transmission estimation could facilitate the depth estimation for hazy images. In this paper, a deep end-to-end model that iteratively estimates image depths and transmission maps is proposed to perform an effective depth prediction for hazy images and improve the dehazing performance with the guidance of depth information. The image depth and transmission map are progressively refined to better restore the dehazed image. Our approach benefits from explicitly modeling the inner relationship of image depth and transmission map, which is especially effective for distant hazy areas. Extensive results on the benchmarks demonstrate that our proposed network performs favorably against the state-of-the-art dehazing methods in terms of depth estimation and haze removal.

arXiv:2102.09142공식 코드 · Papers with Code

Improved Point Transformation Methods For Self-Supervised Depth Prediction

Given stereo or egomotion image pairs, a popular and successful method for unsupervised learning of monocular depth estimation is to measure the quality of image reconstructions resulting from the learned depth predictions. Continued research has improved the overall approach in recent years, yet the common framework still suffers from several important limitations, particularly when dealing with points occluded after transformation to a novel viewpoint. While prior work has addressed this problem heuristically, this paper introduces a z-buffering algorithm that correctly and efficiently handles occluded points. Because our algorithm is implemented with operators typical of machine learning libraries, it can be incorporated into any existing unsupervised depth learning framework with automatic support for differentiation. Additionally, because points having negative depth after transformation often signify erroneously shallow depth predictions, we introduce a loss function to penalize this undesirable behavior explicitly. Experimental results on the KITTI data set show that the z-buffer and negative depth loss both improve the performance of a state of the art depth-prediction network.

arXiv:2102.09320공식 코드 · Papers with Code

Combining Events and Frames using Recurrent Asynchronous Multimodal Networks for Monocular Depth Prediction

Event cameras are novel vision sensors that report per-pixel brightness changes as a stream of asynchronous "events". They offer significant advantages compared to standard cameras due to their high temporal resolution, high dynamic range and lack of motion blur. However, events only measure the varying component of the visual signal, which limits their ability to encode scene context. By contrast, standard cameras measure absolute intensity frames, which capture a much richer representation of the scene. Both sensors are thus complementary. However, due to the asynchronous nature of events, combining them with synchronous images remains challenging, especially for learning-based methods. This is because traditional recurrent neural networks (RNNs) are not designed for asynchronous and irregular data from additional sensors. To address this challenge, we introduce Recurrent Asynchronous Multimodal (RAM) networks, which generalize traditional RNNs to handle asynchronous and irregular data from multiple sensors. Inspired by traditional RNNs, RAM networks maintain a hidden state that is updated asynchronously and can be queried at any time to generate a prediction. We apply this novel architecture to monocular depth estimation with events and frames where we show an improvement over state-of-the-art methods by up to 30% in terms of mean absolute depth error. To enable further research on multimodal learning with events, we release EventScape, a new dataset with events, intensity frames, semantic labels, and depth maps recorded in the CARLA simulator.

arXiv:2102.07989

LEAD: LiDAR Extender for Autonomous Driving

3D perception using sensors under vehicle industrial standard is the rigid demand in autonomous driving. MEMS LiDAR emerges with irresistible trend due to its lower cost, more robust, and meeting the mass-production standards. However, it suffers small field of view (FoV), slowing down the step of its population. In this paper, we propose LEAD, i.e., LiDAR Extender for Autonomous Driving, to extend the MEMS LiDAR by coupled image w.r.t both FoV and range. We propose a multi-stage propagation strategy based on depth distributions and uncertainty map, which shows effective propagation ability. Moreover, our depth outpainting/propagation network follows a teacher-student training fashion, which transfers depth estimation ability to depth completion network without any scale error passed. To validate the LiDAR extension quality, we utilize a high-precise laser scanner to generate a ground-truth dataset. Quantitative and qualitative evaluations show that our scheme outperforms SOTAs with a large margin. We believe the proposed LEAD along with the dataset would benefit the community w.r.t depth researches.

arXiv:2102.07448공식 코드 · Papers with Code

OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving

Surround View fisheye cameras are commonly deployed in automated driving for 360\deg{} near-field sensing around the vehicle. This work presents a multi-task visual perception network on unrectified fisheye images to enable the vehicle to sense its surrounding environment. It consists of six primary tasks necessary for an autonomous driving system: depth estimation, visual odometry, semantic segmentation, motion segmentation, object detection, and lens soiling detection. We demonstrate that the jointly trained model performs better than the respective single task versions. Our multi-task model has a shared encoder providing a significant computational advantage and has synergized decoders where tasks support each other. We propose a novel camera geometry based adaptation mechanism to encode the fisheye distortion model both at training and inference. This was crucial to enable training on the WoodScape dataset, comprised of data from different parts of the world collected by 12 different cameras mounted on three different cars with different intrinsics and viewpoints. Given that bounding boxes is not a good representation for distorted fisheye images, we also extend object detection to use a polygon with non-uniformly sampled vertices. We additionally evaluate our model on standard automotive datasets, namely KITTI and Cityscapes. We obtain the state-of-the-art results on KITTI for depth estimation and pose estimation tasks and competitive performance on the other tasks. We perform extensive ablation studies on various architecture choices and task weighting methodologies. A short video at https://youtu.be/xbSjZ5OfPes provides qualitative results.

arXiv:2102.06685

Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance

Self-supervised depth estimation has made a great success in learning depth from unlabeled image sequences. While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and scene semantics, however, is less considered. This hinders the network to better understand the real geometry of the scene, since the contextual clues, contribute not only the latent representations of scene depth, but also the straight constraints for depth map. In this paper, we leverage the two benefits by proposing the implicit and explicit semantic guidance for accurate self-supervised depth estimation. We propose a Semantic-aware Spatial Feature Alignment (SSFA) scheme to effectively align implicit semantic features with depth features for scene-aware depth estimation. We also propose a semantic-guided ranking loss to explicitly constrain the estimated depth maps to be consistent with real scene contextual properties. Both semantic label noise and prediction uncertainty is considered to yield reliable depth supervisions. Extensive experimental results show that our method produces high quality depth maps which are consistently superior either on complex scenes or diverse semantic categories, and outperforms the state-of-the-art methods by a significant margin.

arXiv:2102.05607공식 코드 · Papers with Code

Exploiting Depth Information for Wildlife Monitoring

Camera traps are a proven tool in biology and specifically biodiversity research. However, camera traps including depth estimation are not widely deployed, despite providing valuable context about the scene and facilitating the automation of previously laborious manual ecological methods. In this study, we propose an automated camera trap-based approach to detect and identify animals using depth estimation. To detect and identify individual animals, we propose a novel method D-Mask R-CNN for the so-called instance segmentation which is a deep learning-based technique to detect and delineate each distinct object of interest appearing in an image or a video clip. An experimental evaluation shows the benefit of the additional depth estimation in terms of improved average precision scores of the animal detection compared to the standard approach that relies just on the image information. This novel approach was also evaluated in terms of a proof-of-concept in a zoo scenario using an RGB-D camera trap.

arXiv:2102.03550공식 코드 · Papers with Code

UniFuse: Unidirectional Fusion for 360$^{\circ}$ Panorama Depth Estimation

Learning depth from spherical panoramas is becoming a popular research topic because a panorama has a full field-of-view of the environment and provides a relatively complete description of a scene. However, applying well-studied CNNs for perspective images to the standard representation of spherical panoramas, i.e., the equirectangular projection, is suboptimal, as it becomes distorted towards the poles. Another representation is the cubemap projection, which is distortion-free but discontinued on edges and limited in the field-of-view. This paper introduces a new framework to fuse features from the two projections, unidirectionally feeding the cubemap features to the equirectangular features only at the decoding stage. Unlike the recent bidirectional fusion approach operating at both the encoding and decoding stages, our fusion scheme is much more efficient. Besides, we also designed a more effective fusion module for our fusion scheme. Experiments verify the effectiveness of our proposed fusion strategy and module, and our model achieves state-of-the-art performance on four popular datasets. Additional experiments show that our model also has the advantages of model complexity and generalization capability.The code is available at https://github.com/alibaba/UniFuse-Unidirectional-Fusion.