PyTorchKR Papers

최신 논문

총 2,547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2205.02930

FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras

In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner. A known issue of self-supervised depth estimation is that it suffers in low-light/over-exposure conditions and in large homogeneous regions. To tackle this issue, we propose a novel ordinal distillation loss that distills the ordinal information from a large teacher model. Such a teacher model, since having been trained on a large amount of diverse data, can capture the depth ordering information well, but lacks in preserving accurate scene geometry. Combined with self-supervised losses, we show that our model can not only generate reasonable depth maps in challenging environments but also better recover the scene geometry. We further leverage the fisheye cameras of an AR-Glasses device to collect an indoor dataset to facilitate evaluation.

arXiv:2205.02481

Exploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation

Multi-view depth estimation plays a critical role in reconstructing and understanding the 3D world. Recent learning-based methods have made significant progress in it. However, multi-view depth estimation is fundamentally a correspondence-based optimization problem, but previous learning-based methods mainly rely on predefined depth hypotheses to build correspondence as the cost volume and implicitly regularize it to fit depth prediction, deviating from the essence of iterative optimization based on stereo correspondence. Thus, they suffer unsatisfactory precision and generalization capability. In this paper, we are the first to explore more general image correlations to establish correspondences dynamically for depth estimation. We design a novel iterative multi-view depth estimation framework mimicking the optimization process, which consists of 1) a correlation volume construction module that models the pixel similarity between a reference image and source images as all-to-all correlations; 2) a flow-based depth initialization module that estimates the depth from the 2D optical flow; 3) a novel correlation-guided depth refinement module that reprojects points in different views to effectively fetch relevant correlations for further fusion and integrate the fused correlation for iterative depth update. Without predefined depth hypotheses, the fused correlations establish multi-view correspondence in an efficient way and guide the depth refinement heuristically. We conduct sufficient experiments on ScanNet, DeMoN, ETH3D, and 7Scenes to demonstrate the superiority of our method on multi-view depth estimation and its best generalization ability.

arXiv:2205.02361공식 코드 · Papers with Code

Creating a Forensic Database of Shoeprints from Online Shoe Tread Photos

Shoe tread impressions are one of the most common types of evidence left at crime scenes. However, the utility of such evidence is limited by the lack of databases of footwear prints that cover the large and growing number of distinct shoe models. Moreover, the database is preferred to contain the 3D shape, or depth, of shoe-tread photos so as to allow for extracting shoeprints to match a query (crime-scene) print. We propose to address this gap by leveraging shoe-tread photos collected by online retailers. The core challenge is to predict depth maps for these photos. As they do not have ground-truth 3D shapes allowing for training depth predictors, we exploit synthetic data that does. We develop a method termed ShoeRinsics that learns to predict depth by leveraging a mix of fully supervised synthetic data and unsupervised retail image data. In particular, we find domain adaptation and intrinsic image decomposition techniques effectively mitigate the synthetic-real domain gap and yield significantly better depth prediction. To validate our method, we introduce 2 validation sets consisting of shoe-tread image and print pairs and define a benchmarking protocol to quantify the quality of predicted depth. On this benchmark, ShoeRinsics outperforms existing methods of depth prediction and synthetic-to-real domain adaptation.

arXiv:2205.01399

Outdoor Monocular Depth Estimation: A Research Review

Depth estimation is an important task, applied in various methods and applications of computer vision. While the traditional methods of estimating depth are based on depth cues and require specific equipment such as stereo cameras and configuring input according to the approach being used, the focus at the current time is on a single source, or monocular, depth estimation. The recent developments in Convolution Neural Networks along with the integration of classical methods in these deep learning approaches have led to a lot of advancements in the depth estimation problem. The problem of outdoor depth estimation, or depth estimation in wild, is a very scarcely researched field of study. In this paper, we give an overview of the available datasets, depth estimation methods, research work, trends, challenges, and opportunities that exist for open research. To our knowledge, no openly available survey work provides a comprehensive collection of outdoor depth estimation techniques and research scope, making our work an essential contribution for people looking to enter this field of study.

arXiv:2205.00257

Unsupervised Visible-light Images Guided Cross-Spectrum Depth Estimation from Dual-Modality Cameras

Cross-spectrum depth estimation aims to provide a depth map in all illumination conditions with a pair of dual-spectrum images. It is valuable for autonomous vehicle applications when the vehicle is equipped with two cameras of different modalities. However, images captured by different-modality cameras can be photometrically quite different. Therefore, cross-spectrum depth estimation is a very challenging problem. Moreover, the shortage of large-scale open-source datasets also retards further research in this field. In this paper, we propose an unsupervised visible-light image guided cross-spectrum (i.e., thermal and visible-light, TIR-VIS in short) depth estimation framework given a pair of RGB and thermal images captured from a visible-light camera and a thermal one. We first adopt a base depth estimation network using RGB-image pairs. Then we propose a multi-scale feature transfer network to transfer features from the TIR-VIS domain to the VIS domain at the feature level to fit the trained depth estimation network. At last, we propose a cross-spectrum depth cycle consistency to improve the depth result of dual-spectrum image pairs. Meanwhile, we release a large dual-spectrum depth estimation dataset with visible-light and far-infrared stereo images captured in different scenes to the society. The experiment result shows that our method achieves better performance than the compared existing methods. Our datasets is available at https://github.com/whitecrow1027/VIS-TIR-Datasets.

arXiv:2205.00613공식 코드 · Papers with Code

MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queries

Accurate and consistent 3D tracking from multiple cameras is a key component in a vision-based autonomous driving system. It involves modeling 3D dynamic objects in complex scenes across multiple cameras. This problem is inherently challenging due to depth estimation, visual occlusions, appearance ambiguity, etc. Moreover, objects are not consistently associated across time and cameras. To address that, we propose an end-to-end \textbf{MU}lti-camera \textbf{TR}acking framework called MUTR3D. In contrast to prior works, MUTR3D does not explicitly rely on the spatial and appearance similarity of objects. Instead, our method introduces \textit{3D track query} to model spatial and appearance coherent track for each object that appears in multiple cameras and multiple frames. We use camera transformations to link 3D trackers with their observations in 2D images. Each tracker is further refined according to the features that are obtained from camera images. MUTR3D uses a set-to-set loss to measure the difference between the predicted tracking results and the ground truths. Therefore, it does not require any post-processing such as non-maximum suppression and/or bounding box association. MUTR3D outperforms state-of-the-art methods by 5.3 AMOTA on the nuScenes dataset. Code is available at: \url{https://github.com/a1600012888/MUTR3D}.

arXiv:2204.13892

SideRT: A Real-time Pure Transformer Architecture for Single Image Depth Estimation

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the locality of convolutions. Attention mechanisms or transformers originally designed for capturing long-range dependencies might be a better choice, but usually complicates architectures and could lead to a decrease in inference speed. In this work, we propose a pure transformer architecture called SideRT that can attain excellent predictions in real-time. In order to capture better global context, Cross-Scale Attention (CSA) and Multi-Scale Refinement (MSR) modules are designed to work collaboratively to fuse features of different scales efficiently. CSA modules focus on fusing features of high semantic similarities, while MSR modules aim to fuse features at corresponding positions. These two modules contain a few learnable parameters without convolutions, based on which a lightweight yet effective model is built. This architecture achieves state-of-the-art performances in real-time (51.3 FPS) and becomes much faster with a reasonable performance drop on a smaller backbone Swin-T (83.1 FPS). Furthermore, its performance surpasses the previous state-of-the-art by a large margin, improving AbsRel metric 6.9% on KITTI and 9.7% on NYU. To the best of our knowledge, this is the first work to show that transformer-based networks can attain state-of-the-art performance in real-time in the single image depth estimation field. Code will be made available soon.

arXiv:2204.13791

Depth Estimation with Simplified Transformer

Transformer and its variants have shown state-of-the-art results in many vision tasks recently, ranging from image classification to dense prediction. Despite of their success, limited work has been reported on improving the model efficiency for deployment in latency-critical applications, such as autonomous driving and robotic navigation. In this paper, we aim at improving upon the existing transformers in vision, and propose a method for self-supervised monocular Depth Estimation with Simplified Transformer (DEST), which is efficient and particularly suitable for deployment on GPU-based platforms. Through strategic design choices, our model leads to significant reduction in model size, complexity, as well as inference latency, while achieving superior accuracy as compared to state-of-the-art. We also show that our design generalize well to other dense prediction task without bells and whistles.

arXiv:2204.13420공식 코드 · Papers with Code

Semi-MoreGAN: A New Semi-supervised Generative Adversarial Network for Mixture of Rain Removal

Rain is one of the most common weather which can completely degrade the image quality and interfere with the performance of many computer vision tasks, especially under heavy rain conditions. We observe that: (i) rain is a mixture of rain streaks and rainy haze; (ii) the scene depth determines the intensity of rain streaks and the transformation into the rainy haze; (iii) most existing deraining methods are only trained on synthetic rainy images, and hence generalize poorly to the real-world scenes. Motivated by these observations, we propose a new SEMI-supervised Mixture Of rain REmoval Generative Adversarial Network (Semi-MoreGAN), which consists of four key modules: (I) a novel attentional depth prediction network to provide precise depth estimation; (ii) a context feature prediction network composed of several well-designed detailed residual blocks to produce detailed image context features; (iii) a pyramid depth-guided non-local network to effectively integrate the image context with the depth information, and produce the final rain-free images; and (iv) a comprehensive semi-supervised loss function to make the model not limited to synthetic datasets but generalize smoothly to real-world heavy rainy scenes. Extensive experiments show clear improvements of our approach over twenty representative state-of-the-arts on both synthetic and real-world rainy images.

arXiv:2204.11216공식 코드 · Papers with Code

RealNet: Combining Optimized Object Detection with Information Fusion Depth Estimation Co-Design Method on IoT

Depth Estimation and Object Detection Recognition play an important role in autonomous driving technology under the guidance of deep learning artificial intelligence. We propose a hybrid structure called RealNet: a co-design method combining the model-streamlined recognition algorithm, the depth estimation algorithm with information fusion, and deploying them on the Jetson-Nano for unmanned vehicles with monocular vision sensors. We use ROS for experiment. The method proposed in this paper is suitable for mobile platforms with high real-time request. Innovation of our method is using information fusion to compensate the problem of insufficient frame rate of output image, and improve the robustness of target detection and depth estimation under monocular vision.Object Detection is based on YOLO-v5. We have simplified the network structure of its DarkNet53 and realized a prediction speed up to 0.01s. Depth Estimation is based on the VNL Depth Estimation, which considers multiple geometric constraints in 3D global space. It calculates the loss function by calculating the deviation of the virtual normal vector VN and the label, which can obtain deeper depth information. We use PnP fusion algorithm to solve the problem of insufficient frame rate of depth map output. It solves the motion estimation depth from three-dimensional target to two-dimensional point based on corner feature matching, which is faster than VNL calculation. We interpolate VNL output and PnP output to achieve information fusion. Experiments show that this can effectively eliminate the jitter of depth information and improve robustness. At the control end, this method combines the results of target detection and depth estimation to calculate the target position, and uses a pure tracking control algorithm to track it.

arXiv:2204.11045공식 코드 · Papers with Code

Investigating Neural Architectures by Synthetic Dataset Design

Recent years have seen the emergence of many new neural network structures (architectures and layers). To solve a given task, a network requires a certain set of abilities reflected in its structure. The required abilities depend on each task. There is so far no systematic study of the real capacities of the proposed neural structures. The question of what each structure can and cannot achieve is only partially answered by its performance on common benchmarks. Indeed, natural data contain complex unknown statistical cues. It is therefore impossible to know what cues a given neural structure is taking advantage of in such data. In this work, we sketch a methodology to measure the effect of each structure on a network's ability, by designing ad hoc synthetic datasets. Each dataset is tailored to assess a given ability and is reduced to its simplest form: each input contains exactly the amount of information needed to solve the task. We illustrate our methodology by building three datasets to evaluate each of the three following network properties: a) the ability to link local cues to distant inferences, b) the translation covariance and c) the ability to group pixels with the same characteristics and share information among them. Using a first simplified depth estimation dataset, we pinpoint a serious nonlocal deficit of the U-Net. We then evaluate how to resolve this limitation by embedding its structure with nonlocal layers, which allow computing complex features with long-range dependencies. Using a second dataset, we compare different positional encoding methods and use the results to further improve the U-Net on the depth estimation task. The third introduced dataset serves to demonstrate the need for self-attention-like mechanisms for resolving more realistic depth estimation tasks.

arXiv:2204.10384공식 코드 · Papers with Code

Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems

Monocular depth estimation (MDE) aims to transform an RGB image of a scene into a pixelwise depth map from the same camera view. It is fundamentally ill-posed due to missing information: any single image can have been taken from many possible 3D scenes. Part of the MDE task is, therefore, to learn which visual cues in the image can be used for depth estimation, and how. With training data limited by cost of annotation or network capacity limited by computational power, this is challenging. In this work we demonstrate that explicitly injecting visual cue information into the model is beneficial for depth estimation. Following research into biological vision systems, we focus on semantic information and prior knowledge of object sizes and their relations, to emulate the biological cues of relative size, familiar size, and absolute size. We use state-of-the-art semantic and instance segmentation models to provide external information, and exploit language embeddings to encode relational information between classes. We also provide a prior on the average real-world size of objects. This external information overcomes the limitation in data availability, and ensures that the limited capacity of a given network is focused on known-helpful cues, therefore improving performance. We experimentally validate our hypothesis and evaluate the proposed model on the widely used NYUD2 indoor depth estimation benchmark. The results show improvements in depth prediction when the semantic information, size prior and instance size are explicitly provided along with the RGB images, and our method can be easily adapted to any depth estimation system.

arXiv:2204.09083

Photometric single-view dense 3D reconstruction in endoscopy

Visual SLAM inside the human body will open the way to computer-assisted navigation in endoscopy. However, due to space limitations, medical endoscopes only provide monocular images, leading to systems lacking true scale. In this paper, we exploit the controlled lighting in colonoscopy to achieve the first in-vivo 3D reconstruction of the human colon using photometric stereo on a calibrated monocular endoscope. Our method works in a real medical environment, providing both a suitable in-place calibration procedure and a depth estimation technique adapted to the colon's tubular geometry. We validate our method on simulated colonoscopies, obtaining a mean error of 7% on depth estimation, which is below 3 mm on average. Our qualitative results on the EndoMapper dataset show that the method is able to correctly estimate the colon shape in real human colonoscopies, paving the ground for true-scale monocular SLAM in endoscopy.

arXiv:2204.08563공식 코드 · Papers with Code

Cylin-Painting: Seamless {360\textdegree} Panoramic Image Outpainting and Beyond

Image outpainting gains increasing attention since it can generate the complete scene from a partial view, providing a valuable solution to construct {360\textdegree} panoramic images. As image outpainting suffers from the intrinsic issue of unidirectional completion flow, previous methods convert the original problem into inpainting, which allows a bidirectional flow. However, we find that inpainting has its own limitations and is inferior to outpainting in certain situations. The question of how they may be combined for the best of both has as yet remained under-explored. In this paper, we provide a deep analysis of the differences between inpainting and outpainting, which essentially depends on how the source pixels contribute to the unknown regions under different spatial arrangements. Motivated by this analysis, we present a Cylin-Painting framework that involves meaningful collaborations between inpainting and outpainting and efficiently fuses the different arrangements, with a view to leveraging their complementary benefits on a seamless cylinder. Nevertheless, straightforwardly applying the cylinder-style convolution often generates visually unpleasing results as it discards important positional information. To address this issue, we further present a learnable positional embedding strategy to incorporate the missing component of positional encoding into the cylinder convolution, which significantly improves the panoramic results. It is noted that while developed for image outpainting, the proposed algorithm can be effectively extended to other panoramic vision tasks, such as object detection, depth estimation, and image super-resolution. Code will be made available at \url{https://github.com/KangLiao929/Cylin-Painting}.

arXiv:2204.07616

Multi-Frame Self-Supervised Depth with Transformers

Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching for self-supervised monocular depth estimation, and propose a novel transformer architecture for cost volume generation. We use depth-discretized epipolar sampling to select matching candidates, and refine predictions through a series of self- and cross-attention layers. These layers sharpen the matching probability between pixel features, improving over standard similarity metrics prone to ambiguities and local minima. The refined cost volume is decoded into depth estimates, and the whole pipeline is trained end-to-end from videos using only a photometric objective. Experiments on the KITTI and DDAD datasets show that our DepthFormer architecture establishes a new state of the art in self-supervised monocular depth estimation, and is even competitive with highly specialized supervised single-frame architectures. We also show that our learned cross-attention network yields representations transferable across datasets, increasing the effectiveness of pre-training strategies. Project page: https://sites.google.com/tri.global/depthformer

arXiv:2204.07791

UAMD-Net: A Unified Adaptive Multimodal Neural Network for Dense Depth Completion

Depth prediction is a critical problem in robotics applications especially autonomous driving. Generally, depth prediction based on binocular stereo matching and fusion of monocular image and laser point cloud are two mainstream methods. However, the former usually suffers from overfitting while building cost volume, and the latter has a limited generalization due to the lack of geometric constraint. To solve these problems, we propose a novel multimodal neural network, namely UAMD-Net, for dense depth completion based on fusion of binocular stereo matching and the weak constrain from the sparse point clouds. Specifically, the sparse point clouds are converted to sparse depth map and sent to the multimodal feature encoder (MFE) with binocular image, constructing a cross-modal cost volume. Then, it will be further processed by the multimodal feature aggregator (MFA) and the depth regression layer. Furthermore, the existing multimodal methods ignore the problem of modal dependence, that is, the network will not work when a certain modal input has a problem. Therefore, we propose a new training strategy called Modal-dropout which enables the network to be adaptively trained with multiple modal inputs and inference with specific modal inputs. Benefiting from the flexible network structure and adaptive training method, our proposed network can realize unified training under various modal input conditions. Comprehensive experiments conducted on KITTI depth completion benchmark demonstrate that our method produces robust results and outperforms other state-of-the-art methods.

arXiv:2204.07076

End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation

Monocular depth estimation is still an open challenge due to the ill-posed nature of the problem at hand. Deep learning based techniques have been extensively studied and proved capable of producing acceptable depth estimation accuracy even if the lack of meaningful and robust depth cues within single RGB input images severally limits their performance. Coded aperture-based methods using phase and amplitude masks encode strong depth cues within 2D images by means of depth-dependent Point Spread Functions (PSFs) at the price of a reduced image quality. In this paper, we propose a novel end-to-end learning approach for depth from diffracted rotation. A phase mask that produces a Rotating Point Spread Function (RPSF) as a function of defocus is jointly optimized with the weights of a depth estimation neural network. To this aim, we introduce a differentiable physical model of the aperture mask and exploit an accurate simulation of the camera imaging pipeline. Our approach requires a significantly less complex model and less training data, yet it is superior to existing methods in the task of monocular depth estimation on indoor benchmarks. In addition, we address the problem of image degradation by incorporating a non-blind and non-uniform image deblurring module to recover the sharp all-in-focus image from its RPSF-blurred counterpart.

arXiv:2204.06512

Does depth estimation help object detection?

Ground-truth depth, when combined with color data, helps improve object detection accuracy over baseline models that only use color. However, estimated depth does not always yield improvements. Many factors affect the performance of object detection when estimated depth is used. In this paper, we comprehensively investigate these factors with detailed experiments, such as using ground-truth vs. estimated depth, effects of different state-of-the-art depth estimation networks, effects of using different indoor and outdoor RGB-D datasets as training data for depth estimation, and different architectural choices for integrating depth to the base object detector network. We propose an early concatenation strategy of depth, which yields higher mAP than previous works' while using significantly fewer parameters.

arXiv:2204.05007

HiMODE: A Hybrid Monocular Omnidirectional Depth Estimation Model

Monocular omnidirectional depth estimation is receiving considerable research attention due to its broad applications for sensing 360{\deg} surroundings. Existing approaches in this field suffer from limitations in recovering small object details and data lost during the ground-truth depth map acquisition. In this paper, a novel monocular omnidirectional depth estimation model, namely HiMODE is proposed based on a hybrid CNN+Transformer (encoder-decoder) architecture whose modules are efficiently designed to mitigate distortion and computational cost, without performance degradation. Firstly, we design a feature pyramid network based on the HNet block to extract high-resolution features near the edges. The performance is further improved, benefiting from a self and cross attention layer and spatial/temporal patches in the Transformer encoder and decoder, respectively. Besides, a spatial residual block is employed to reduce the number of parameters. By jointly passing the deep features extracted from an input image at each backbone block, along with the raw depth maps predicted by the transformer encoder-decoder, through a context adjustment layer, our model can produce resulting depth maps with better visual quality than the ground-truth. Comprehensive ablation studies demonstrate the significance of each individual module. Extensive experiments conducted on three datasets; Stanford3D, Matterport3D, and SunCG, demonstrate that HiMODE can achieve state-of-the-art performance for 360{\deg} monocular depth estimation.

arXiv:2204.03636공식 코드 · Papers with Code

SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation

Depth estimation from images serves as the fundamental step of 3D perception for autonomous driving and is an economical alternative to expensive depth sensors like LiDAR. The temporal photometric constraints enables self-supervised depth estimation without labels, further facilitating its application. However, most existing methods predict the depth solely based on each monocular image and ignore the correlations among multiple surrounding cameras, which are typically available for modern self-driving vehicles. In this paper, we propose a SurroundDepth method to incorporate the information from multiple surrounding views to predict depth maps across cameras. Specifically, we employ a joint network to process all the surrounding views and propose a cross-view transformer to effectively fuse the information from multiple views. We apply cross-view self-attention to efficiently enable the global interactions between multi-camera feature maps. Different from self-supervised monocular depth estimation, we are able to predict real-world scales given multi-camera extrinsic matrices. To achieve this goal, we adopt the two-frame structure-from-motion to extract scale-aware pseudo depths to pretrain the models. Further, instead of predicting the ego-motion of each individual camera, we estimate a universal ego-motion of the vehicle and transfer it to each view to achieve multi-view ego-motion consistency. In experiments, our method achieves the state-of-the-art performance on the challenging multi-camera depth estimation datasets DDAD and nuScenes.