PyTorchKR Papers

최신 논문

총 400편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2306.17450

GMM: Delving into Gradient Aware and Model Perceive Depth Mining for Monocular 3D Detection

Depth perception is a crucial component of monoc-ular 3D detection tasks that typically involve ill-posed problems. In light of the success of sample mining techniques in 2D object detection, we propose a simple yet effective mining strategy for improving depth perception in 3D object detection. Concretely, we introduce a plain metric to evaluate the quality of depth predictions, which chooses the mined sample for the model. Moreover, we propose a Gradient-aware and Model-perceive Mining strategy (GMM) for depth learning, which exploits the predicted depth quality for better depth learning through easy mining. GMM is a general strategy that can be readily applied to several state-of-the-art monocular 3D detectors, improving the accuracy of depth prediction. Extensive experiments on the nuScenes dataset demonstrate that the proposed methods significantly improve the performance of 3D object detection while outperforming other state-of-the-art sample mining techniques by a considerable margin. On the nuScenes benchmark, GMM achieved the state-of-the-art (42.1% mAP and 47.3% NDS) performance in monocular object detection.

arXiv:2306.08648

SimpleMapping: Real-Time Visual-Inertial Dense Mapping with Deep Multi-View Stereo

We present a real-time visual-inertial dense mapping method capable of performing incremental 3D mesh reconstruction with high quality using only sequential monocular images and inertial measurement unit (IMU) readings. 6-DoF camera poses are estimated by a robust feature-based visual-inertial odometry (VIO), which also generates noisy sparse 3D map points as a by-product. We propose a sparse point aided multi-view stereo neural network (SPA-MVSNet) that can effectively leverage the informative but noisy sparse points from the VIO system. The sparse depth from VIO is firstly completed by a single-view depth completion network. This dense depth map, although naturally limited in accuracy, is then used as a prior to guide our MVS network in the cost volume generation and regularization for accurate dense depth prediction. Predicted depth maps of keyframe images by the MVS network are incrementally fused into a global map using TSDF-Fusion. We extensively evaluate both the proposed SPA-MVSNet and the entire visual-inertial dense mapping system on several public datasets as well as our own dataset, demonstrating the system's impressive generalization capabilities and its ability to deliver high-quality 3D mesh reconstruction online. Our proposed dense mapping system achieves a 39.7% improvement in F-score over existing systems when evaluated on the challenging scenarios of the EuRoC dataset.

arXiv:2306.05682

Lightweight Monocular Depth Estimation via Token-Sharing Transformer

Depth estimation is an important task in various robotics systems and applications. In mobile robotics systems, monocular depth estimation is desirable since a single RGB camera can be deployable at a low cost and compact size. Due to its significant and growing needs, many lightweight monocular depth estimation networks have been proposed for mobile robotics systems. While most lightweight monocular depth estimation methods have been developed using convolution neural networks, the Transformer has been gradually utilized in monocular depth estimation recently. However, massive parameters and large computational costs in the Transformer disturb the deployment to embedded devices. In this paper, we present a Token-Sharing Transformer (TST), an architecture using the Transformer for monocular depth estimation, optimized especially in embedded devices. The proposed TST utilizes global token sharing, which enables the model to obtain an accurate depth prediction with high throughput in embedded devices. Experimental results show that TST outperforms the existing lightweight monocular depth estimation methods. On the NYU Depth v2 dataset, TST can deliver depth maps up to 63.4 FPS in NVIDIA Jetson nano and 142.6 FPS in NVIDIA Jetson TX2, with lower errors than the existing methods. Furthermore, TST achieves real-time depth estimation of high-resolution images on Jetson TX2 with competitive results.

arXiv:2305.12955

Gated Stereo: Joint Depth Estimation from Gated and Wide-Baseline Active Stereo Cues

We propose Gated Stereo, a high-resolution and long-range depth estimation technique that operates on active gated stereo images. Using active and high dynamic range passive captures, Gated Stereo exploits multi-view cues alongside time-of-flight intensity cues from active gating. To this end, we propose a depth estimation method with a monocular and stereo depth prediction branch which are combined in a final fusion stage. Each block is supervised through a combination of supervised and gated self-supervision losses. To facilitate training and validation, we acquire a long-range synchronized gated stereo dataset for automotive scenarios. We find that the method achieves an improvement of more than 50 % MAE compared to the next best RGB stereo method, and 74 % MAE to existing monocular gated methods for distances up to 160 m. Our code,models and datasets are available here.

arXiv:2305.07269

Meta-Optimization for Higher Model Generalizability in Single-Image Depth Prediction

Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied image classification in meta-learning, depth is pixel-level continuous range values, and mappings from each image to depth vary widely across environments. Thus no explicit task boundaries exist. We instead propose fine-grained task that treats each RGB-D pair as a task in our meta-optimization. We first show meta-learning on limited data induces much better prior (max +29.4\%). Using meta-learned weights as initialization for following supervised learning, without involving extra data or information, it consistently outperforms baselines without the method. Compared to most indoor-depth methods that only train/ test on a single dataset, we propose zero-shot cross-dataset protocols, closely evaluate robustness, and show consistently higher generalizability and accuracy by our meta-initialization. The work at the intersection of depth and meta-learning potentially drives both research streams to step closer to practical use.

arXiv:2305.01732

High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation

Accurate depth maps are essential in various applications, such as autonomous driving, scene reconstruction, point-cloud creation, etc. However, monocular-depth estimation (MDE) algorithms often fail to provide enough texture & sharpness, and also are inconsistent for homogeneous scenes. These algorithms mostly use CNN or vision transformer-based architectures requiring large datasets for supervised training. But, MDE algorithms trained on available depth datasets do not generalize well and hence fail to perform accurately in diverse real-world scenes. Moreover, the ground-truth depth maps are either lower resolution or sparse leading to relatively inconsistent depth maps. In general, acquiring a high-resolution ground truth dataset with pixel-level precision for accurate depth prediction is an expensive, and time-consuming challenge. In this paper, we generate a high-resolution synthetic depth dataset (HRSD) of dimension 1920 X 1080 from Grand Theft Auto (GTA-V), which contains 100,000 color images and corresponding dense ground truth depth maps. The generated datasets are diverse and have scenes from indoors to outdoors, from homogeneous surfaces to textures. For experiments and analysis, we train the DPT algorithm, a state-of-the-art transformer-based MDE algorithm on the proposed synthetic dataset, which significantly increases the accuracy of depth maps on different scenes by 9 %. Since the synthetic datasets are of higher resolution, we propose adding a feature extraction module in the transformer encoder and incorporating an attention-based loss, further improving the accuracy by 15 %.

arXiv:2304.13445

Neural-PBIR Reconstruction of Shape, Material, and Illumination

Reconstructing the shape and spatially varying surface appearances of a physical-world object as well as its surrounding illumination based on 2D images (e.g., photographs) of the object has been a long-standing problem in computer vision and graphics. In this paper, we introduce an accurate and highly efficient object reconstruction pipeline combining neural based object reconstruction and physics-based inverse rendering (PBIR). Our pipeline firstly leverages a neural SDF based shape reconstruction to produce high-quality but potentially imperfect object shape. Then, we introduce a neural material and lighting distillation stage to achieve high-quality predictions for material and illumination. In the last stage, initialized by the neural predictions, we perform PBIR to refine the initial results and obtain the final high-quality reconstruction of object shape, material, and illumination. Experimental results demonstrate our pipeline significantly outperforms existing methods quality-wise and performance-wise.

arXiv:2304.13030공식 코드 · Papers with Code

CompletionFormer: Depth Completion with Convolutions and Vision Transformers

Given sparse depths and the corresponding RGB images, depth completion aims at spatially propagating the sparse measurements throughout the whole image to get a dense depth prediction. Despite the tremendous progress of deep-learning-based depth completion methods, the locality of the convolutional layer or graph model makes it hard for the network to model the long-range relationship between pixels. While recent fully Transformer-based architecture has reported encouraging results with the global receptive field, the performance and efficiency gaps to the well-developed CNN models still exist because of its deteriorative local feature details. This paper proposes a Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct our depth completion model in a pyramidal structure. This hybrid architecture naturally benefits both the local connectivity of convolutions and the global context of the Transformer in one single model. As a result, our CompletionFormer outperforms state-of-the-art CNNs-based methods on the outdoor KITTI Depth Completion benchmark and indoor NYUv2 dataset, achieving significantly higher efficiency (nearly 1/3 FLOPs) compared to pure Transformer-based methods. Code is available at \url{https://github.com/youmi-zym/CompletionFormer}.

arXiv:2304.10719

FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving

Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous driving scenes utilizing inter-frame poses obtained from inertial measurements. In particular, we introduce a Full-Scale depth prediction network named FSNet. FSNet contains four important improvements over existing self-supervised models: (1) a multichannel output representation for stable training of depth prediction in driving scenarios, (2) an optical-flow-based mask designed for dynamic object removal, (3) a self-distillation training strategy to augment the training process, and (4) an optimization-based post-processing algorithm in test time, fusing the results from visual odometry. With this framework, robots and vehicles with only one well-calibrated camera can collect sequences of training image frames and camera poses, and infer accurate 3D depths of the environment without extra labeling work or 3D data. Extensive experiments on the KITTI dataset, KITTI-360 dataset and the nuScenes dataset demonstrate the potential of FSNet. More visualizations are presented in \url{https://sites.google.com/view/fsnet/home}

arXiv:2304.03560공식 코드 · Papers with Code

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

Self-supervised multi-frame depth estimation achieves high accuracy by computing matching costs of pixel correspondences between adjacent frames, injecting geometric information into the network. These pixel-correspondence candidates are computed based on the relative pose estimates between the frames. Accurate pose predictions are essential for precise matching cost computation as they influence the epipolar geometry. Furthermore, improved depth estimates can, in turn, be used to align pose estimates. Inspired by traditional structure-from-motion (SfM) principles, we propose the DualRefine model, which tightly couples depth and pose estimation through a feedback loop. Our novel update pipeline uses a deep equilibrium model framework to iteratively refine depth estimates and a hidden state of feature maps by computing local matching costs based on epipolar geometry. Importantly, we used the refined depth estimates and feature maps to compute pose updates at each step. This update in the pose estimates slowly alters the epipolar geometry during the refinement process. Experimental results on the KITTI dataset demonstrate competitive depth prediction and odometry prediction performance surpassing published self-supervised baselines.

arXiv:2303.18164

Single Image Depth Prediction Made Better: A Multivariate Gaussian Take

Neural-network-based single image depth prediction (SIDP) is a challenging task where the goal is to predict the scene's per-pixel depth at test time. Since the problem, by definition, is ill-posed, the fundamental goal is to come up with an approach that can reliably model the scene depth from a set of training examples. In the pursuit of perfect depth estimation, most existing state-of-the-art learning techniques predict a single scalar depth value per-pixel. Yet, it is well-known that the trained model has accuracy limits and can predict imprecise depth. Therefore, an SIDP approach must be mindful of the expected depth variations in the model's prediction at test time. Accordingly, we introduce an approach that performs continuous modeling of per-pixel depth, where we can predict and reason about the per-pixel depth and its distribution. To this end, we model per-pixel scene depth using a multivariate Gaussian distribution. Moreover, contrary to the existing uncertainty modeling methods -- in the same spirit, where per-pixel depth is assumed to be independent, we introduce per-pixel covariance modeling that encodes its depth dependency w.r.t all the scene points. Unfortunately, per-pixel depth covariance modeling leads to a computationally expensive continuous loss function, which we solve efficiently using the learned low-rank approximation of the overall covariance matrix. Notably, when tested on benchmark datasets such as KITTI, NYU, and SUN-RGB-D, the SIDP model obtained by optimizing our loss function shows state-of-the-art results. Our method's accuracy (named MG) is among the top on the KITTI depth-prediction benchmark leaderboard.

arXiv:2303.16617공식 코드 · Papers with Code

NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination

Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. In order to achieve better decomposition, recent approaches attempt to model indirect illuminations reflected from different materials via Spherical Gaussians (SG), which, however, tends to blur the high-frequency reflection details. In this paper, we propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images, while considering near-field indirect illumination. In a nutshell, we introduce the Monte Carlo sampling based path tracing and cache the indirect illumination as neural radiance, enabling a physics-faithful and easy-to-optimize inverse rendering method. To enhance efficiency and practicality, we leverage SG to represent the smooth environment illuminations and apply importance sampling techniques. To supervise indirect illuminations from unobserved directions, we develop a novel radiance consistency constraint between implicit neural radiance and path tracing results of unobserved rays along with the joint optimization of materials and illuminations, thus significantly improving the decomposition performance. Extensive experiments demonstrate that our method outperforms the state-of-the-art on multiple synthetic and real datasets, especially in terms of inter-reflection decomposition.Our code and data are available at https://woolseyyy.github.io/nefii/.

arXiv:2303.09248

Cross-Dimensional Refined Learning for Real-Time 3D Visual Perception from Monocular Video

We present a novel real-time capable learning method that jointly perceives a 3D scene's geometry structure and semantic labels. Recent approaches to real-time 3D scene reconstruction mostly adopt a volumetric scheme, where a Truncated Signed Distance Function (TSDF) is directly regressed. However, these volumetric approaches tend to focus on the global coherence of their reconstructions, which leads to a lack of local geometric detail. To overcome this issue, we propose to leverage the latent geometric prior knowledge in 2D image features by explicit depth prediction and anchored feature generation, to refine the occupancy learning in TSDF volume. Besides, we find that this cross-dimensional feature refinement methodology can also be adopted for the semantic segmentation task by utilizing semantic priors. Hence, we proposed an end-to-end cross-dimensional refinement neural network (CDRNet) to extract both 3D mesh and 3D semantic labeling in real time. The experiment results show that this method achieves a state-of-the-art 3D perception efficiency on multiple datasets, which indicates the great potential of our method for industrial applications.

arXiv:2303.07662

Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domains

Transferring the absolute depth prediction capabilities of an estimator to a new domain is a task with significant real-world applications. This task is specifically challenging when images from the new domain are collected without ground-truth depth measurements, and possibly with sensors of different intrinsics. To overcome such limitations, a recent zero-shot solution was trained on an extensive training dataset and encoded the various camera intrinsics. Other solutions generated synthetic data with depth labels that matched the intrinsics of the new target data to enable depth-scale transfer between the domains. In this work we present an alternative solution that can utilize any existing synthetic or real dataset, that has a small number of images annotated with ground truth depth labels. Specifically, we show that self-supervised depth estimators result in up-to-scale predictions that are linearly correlated to their absolute depth values across the domain, a property that we model in this work using a single scalar. In addition, aligning the field-of-view of two datasets prior to training, results in a common linear relationship for both domains. We use this observed property to transfer the depth-scale from source datasets that have absolute depth labels to new target datasets that lack these measurements, enabling absolute depth predictions in the target domain. The suggested method was successfully demonstrated on the KITTI, DDAD and nuScenes datasets, while using other existing real or synthetic source datasets, that have a different field-of-view, other image style or structural content, achieving comparable or better accuracy than other existing methods that do not use target ground-truth depths.

arXiv:2303.05050공식 코드 · Papers with Code

Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation

With the rapid advancements in autonomous driving and robot navigation, there is a growing demand for lifelong learning models capable of estimating metric (absolute) depth. Lifelong learning approaches potentially offer significant cost savings in terms of model training, data storage, and collection. However, the quality of RGB images and depth maps is sensor-dependent, and depth maps in the real world exhibit domain-specific characteristics, leading to variations in depth ranges. These challenges limit existing methods to lifelong learning scenarios with small domain gaps and relative depth map estimation. To facilitate lifelong metric depth learning, we identify three crucial technical challenges that require attention: i) developing a model capable of addressing the depth scale variation through scale-aware depth learning, ii) devising an effective learning strategy to handle significant domain gaps, and iii) creating an automated solution for domain-aware depth inference in practical applications. Based on the aforementioned considerations, in this paper, we present i) a lightweight multi-head framework that effectively tackles the depth scale imbalance, ii) an uncertainty-aware lifelong learning solution that adeptly handles significant domain gaps, and iii) an online domain-specific predictor selection method for real-time inference. Through extensive numerical studies, we show that the proposed method can achieve good efficiency, stability, and plasticity, leading the benchmarks by 8% to 15%.

arXiv:2303.01686

Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View

Multi-view 3D object detection (MV3D-Det) in Bird-Eye-View (BEV) has drawn extensive attention due to its low cost and high efficiency. Although new algorithms for camera-only 3D object detection have been continuously proposed, most of them may risk drastic performance degradation when the domain of input images differs from that of training. In this paper, we first analyze the causes of the domain gap for the MV3D-Det task. Based on the covariate shift assumption, we find that the gap mainly attributes to the feature distribution of BEV, which is determined by the quality of both depth estimation and 2D image's feature representation. To acquire a robust depth prediction, we propose to decouple the depth estimation from the intrinsic parameters of the camera (i.e. the focal length) through converting the prediction of metric depth to that of scale-invariant depth and perform dynamic perspective augmentation to increase the diversity of the extrinsic parameters (i.e. the camera poses) by utilizing homography. Moreover, we modify the focal length values to create multiple pseudo-domains and construct an adversarial training loss to encourage the feature representation to be more domain-agnostic. Without bells and whistles, our approach, namely DG-BEV, successfully alleviates the performance drop on the unseen target domain without impairing the accuracy of the source domain. Extensive experiments on various public datasets, including Waymo, nuScenes, and Lyft, demonstrate the generalization and effectiveness of our approach. To the best of our knowledge, this is the first systematic study to explore a domain generalization method for MV3D-Det.

arXiv:2303.01351

APARATE: Adaptive Adversarial Patch for CNN-based Monocular Depth Estimation for Autonomous Navigation

In recent times, monocular depth estimation (MDE) has experienced significant advancements in performance, largely attributed to the integration of innovative architectures, i.e., convolutional neural networks (CNNs) and Transformers. Nevertheless, the susceptibility of these models to adversarial attacks has emerged as a noteworthy concern, especially in domains where safety and security are paramount. This concern holds particular weight for MDE due to its critical role in applications like autonomous driving and robotic navigation, where accurate scene understanding is pivotal. To assess the vulnerability of CNN-based depth prediction methods, recent work tries to design adversarial patches against MDE. However, the existing approaches fall short of inducing a comprehensive and substantially disruptive impact on the vision system. Instead, their influence is partial and confined to specific local areas. These methods lead to erroneous depth predictions only within the overlapping region with the input image, without considering the characteristics of the target object, such as its size, shape, and position. In this paper, we introduce a novel adversarial patch named APARATE. This patch possesses the ability to selectively undermine MDE in two distinct ways: by distorting the estimated distances or by creating the illusion of an object disappearing from the perspective of the autonomous system. Notably, APARATE is designed to be sensitive to the shape and scale of the target object, and its influence extends beyond immediate proximity. APARATE, results in a mean depth estimation error surpassing $0.5$, significantly impacting as much as $99\%$ of the targeted region when applied to CNN-based MDE models. Furthermore, it yields a significant error of $0.34$ and exerts substantial influence over $94\%$ of the target region in the context of Transformer-based MDE.

arXiv:2303.01196

STDepthFormer: Predicting Spatio-temporal Depth from Video with a Self-supervised Transformer Model

In this paper, a self-supervised model that simultaneously predicts a sequence of future frames from video-input with a novel spatial-temporal attention (ST) network is proposed. The ST transformer network allows constraining both temporal consistency across future frames whilst constraining consistency across spatial objects in the image at different scales. This was not the case in prior works for depth prediction, which focused on predicting a single frame as output. The proposed model leverages prior scene knowledge such as object shape and texture similar to single-image depth inference methods, whilst also constraining the motion and geometry from a sequence of input images. Apart from the transformer architecture, one of the main contributions with respect to prior works lies in the objective function that enforces spatio-temporal consistency across a sequence of output frames rather than a single output frame. As will be shown, this results in more accurate and robust depth sequence forecasting. The model achieves highly accurate depth forecasting results that outperform existing baselines on the KITTI benchmark. Extensive ablation studies were performed to assess the effectiveness of the proposed techniques. One remarkable result of the proposed model is that it is implicitly capable of forecasting the motion of objects in the scene, rather than requiring complex models involving multi-object detection, segmentation and tracking.

arXiv:2302.10062

An evaluation of deep learning models for predicting water depth evolution in urban floods

In this technical report we compare different deep learning models for prediction of water depth rasters at high spatial resolution. Efficient, accurate, and fast methods for water depth prediction are nowadays important as urban floods are increasing due to higher rainfall intensity caused by climate change, expansion of cities and changes in land use. While hydrodynamic models models can provide reliable forecasts by simulating water depth at every location of a catchment, they also have a high computational burden which jeopardizes their application to real-time prediction in large urban areas at high spatial resolution. Here, we propose to address this issue by using data-driven techniques. Specifically, we evaluate deep learning models which are trained to reproduce the data simulated by the CADDIES cellular-automata flood model, providing flood forecasts that can occur at different future time horizons. The advantage of using such models is that they can learn the underlying physical phenomena a priori, preventing manual parameter setting and computational burden. We perform experiments on a dataset consisting of two catchments areas within Switzerland with 18 simpler, short rainfall patterns and 4 long, more complex ones. Our results show that the deep learning models present in general lower errors compared to the other methods, especially for water depths $>0.5m$. However, when testing on more complex rainfall events or unseen catchment areas, the deep models do not show benefits over the simpler ones.

arXiv:2302.06556공식 코드 · Papers with Code

VA-DepthNet: A Variational Approach to Single Image Depth Prediction

We introduce VA-DepthNet, a simple, effective, and accurate deep neural network approach for the single-image depth prediction (SIDP) problem. The proposed approach advocates using classical first-order variational constraints for this problem. While state-of-the-art deep neural network methods for SIDP learn the scene depth from images in a supervised setting, they often overlook the invaluable invariances and priors in the rigid scene space, such as the regularity of the scene. The paper's main contribution is to reveal the benefit of classical and well-founded variational constraints in the neural network design for the SIDP task. It is shown that imposing first-order variational constraints in the scene space together with popular encoder-decoder-based network architecture design provides excellent results for the supervised SIDP task. The imposed first-order variational constraint makes the network aware of the depth gradient in the scene space, i.e., regularity. The paper demonstrates the usefulness of the proposed approach via extensive evaluation and ablation analysis over several benchmark datasets, such as KITTI, NYU Depth V2, and SUN RGB-D. The VA-DepthNet at test time shows considerable improvements in depth prediction accuracy compared to the prior art and is accurate also at high-frequency regions in the scene space. At the time of writing this paper, our method -- labeled as VA-DepthNet, when tested on the KITTI depth-prediction evaluation set benchmarks, shows state-of-the-art results, and is the top-performing published approach.