PyTorchKR Papers

최신 논문

총 2,267편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2405.10244공식 코드 · Papers with Code

Towards Task-Compatible Compressible Representations

We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount of information available in it. We interpret this issue using the predictive $\mathcal{V}$-information framework. In learnable scalable coding, previous work increased the utilization of side-information for input reconstruction by also rewarding input reconstruction when learning this shared representation. We evaluate the impact of this idea in the context of input reconstruction more rigorously and extended it to other computer vision tasks. We perform experiments using representations trained for object detection on COCO 2017 and depth estimation on the Cityscapes dataset, and use them to assist in image reconstruction and semantic segmentation tasks. The results show considerable improvements in the rate-distortion performance of the assisted tasks. Moreover, using the proposed representations, the performance of the base tasks are also improved. Results suggest that the proposed method induces simpler representations that are more compatible with downstream processes.

arXiv:2405.09964

KPNDepth: Depth Estimation of Lane Images under Complex Rainy Environment

Recent advancements in deep neural networks have improved depth estimation in clear, daytime driving scenarios. However, existing methods struggle with rainy conditions due to rain streaks and fog, which distort depth estimation. This paper introduces a novel dual-layer convolutional kernel prediction network for lane depth estimation in rainy environments. It predicts two sets of kernels to mitigate depth loss and rain streak artifacts. To address the scarcity of real rainy lane data, an image synthesis algorithm, RCFLane, is presented, creating a synthetic dataset called RainKITTI. Experiments show the framework's effectiveness in complex rainy conditions.

arXiv:2405.08911

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks

CLIP models perform remarkably well on zero-shot classification and retrieval tasks. But recent studies have shown that learnt representations in CLIP are not well suited for dense prediction tasks like object detection, semantic segmentation or depth estimation. More recently, multi-stage training methods for CLIP models was introduced to mitigate the weak performance of CLIP on downstream tasks. In this work, we find that simply improving the quality of captions in image-text datasets improves the quality of CLIP's visual representations, resulting in significant improvement on downstream dense prediction vision tasks. In fact, we find that CLIP pretraining with good quality captions can surpass recent supervised, self-supervised and weakly supervised pretraining methods. We show that when CLIP model with ViT-B/16 as image encoder is trained on well aligned image-text pairs it obtains 12.1% higher mIoU and 11.5% lower RMSE on semantic segmentation and depth estimation tasks over recent state-of-the-art Masked Image Modeling (MIM) pretraining methods like Masked Autoencoder (MAE). We find that mobile architectures also benefit significantly from CLIP pretraining. A recent mobile vision architecture, MCi2, with CLIP pretraining obtains similar performance as Swin-L, pretrained on ImageNet-22k for semantic segmentation task while being 6.1$\times$ smaller. Moreover, we show that improving caption quality results in $10\times$ data efficiency when finetuning for dense prediction tasks.

arXiv:2405.08672공식 코드 · Papers with Code

EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

Depth estimation plays a crucial role in various tasks within endoscopic surgery, including navigation, surface reconstruction, and augmented reality visualization. Despite the significant achievements of foundation models in vision tasks, including depth estimation, their direct application to the medical domain often results in suboptimal performance. This highlights the need for efficient adaptation methods to adapt these models to endoscopic depth estimation. We propose Endoscopic Depth Any Camera (EndoDAC) which is an efficient self-supervised depth estimation framework that adapts foundation models to endoscopic scenes. Specifically, we develop the Dynamic Vector-Based Low-Rank Adaptation (DV-LoRA) and employ Convolutional Neck blocks to tailor the foundational model to the surgical domain, utilizing remarkably few trainable parameters. Given that camera information is not always accessible, we also introduce a self-supervised adaptation strategy that estimates camera intrinsics using the pose encoder. Our framework is capable of being trained solely on monocular surgical videos from any camera, ensuring minimal training costs. Experiments demonstrate that our approach obtains superior performance even with fewer training epochs and unaware of the ground truth camera intrinsics. Code is available at https://github.com/BeileiCui/EndoDAC.

arXiv:2405.08816

The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition

In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sensor malfunctions, and environmental unpredictability can severely impact the performance of autonomous systems. The 2024 RoboDrive Challenge was crafted to propel the development of driving perception technologies that can withstand and adapt to these real-world variabilities. Focusing on four pivotal tasks -- BEV detection, map segmentation, semantic occupancy prediction, and multi-view depth estimation -- the competition laid down a gauntlet to innovate and enhance system resilience against typical and atypical disturbances. This year's challenge consisted of five distinct tracks and attracted 140 registered teams from 93 institutes across 11 countries, resulting in nearly one thousand submissions evaluated through our servers. The competition culminated in 15 top-performing solutions, which introduced a range of innovative approaches including advanced data augmentation, multi-sensor fusion, self-supervised learning for error correction, and new algorithmic strategies to enhance sensor robustness. These contributions significantly advanced the state of the art, particularly in handling sensor inconsistencies and environmental variability. Participants, through collaborative efforts, pushed the boundaries of current technologies, showcasing their potential in real-world scenarios. Extensive evaluations and analyses provided insights into the effectiveness of these solutions, highlighting key trends and successful strategies for improving the resilience of driving perception systems. This challenge has set a new benchmark in the field, providing a rich repository of techniques expected to guide future research in this field.

arXiv:2405.06749

Ensuring UAV Safety: A Vision-only and Real-time Framework for Collision Avoidance Through Object Detection, Tracking, and Distance Estimation

In the last twenty years, unmanned aerial vehicles (UAVs) have garnered growing interest due to their expanding applications in both military and civilian domains. Detecting non-cooperative aerial vehicles with efficiency and estimating collisions accurately are pivotal for achieving fully autonomous aircraft and facilitating Advanced Air Mobility (AAM). This paper presents a deep-learning framework that utilizes optical sensors for the detection, tracking, and distance estimation of non-cooperative aerial vehicles. In implementing this comprehensive sensing framework, the availability of depth information is essential for enabling autonomous aerial vehicles to perceive and navigate around obstacles. In this work, we propose a method for estimating the distance information of a detected aerial object in real time using only the input of a monocular camera. In order to train our deep learning components for the object detection, tracking and depth estimation tasks we utilize the Amazon Airborne Object Tracking (AOT) Dataset. In contrast to previous approaches that integrate the depth estimation module into the object detector, our method formulates the problem as image-to-image translation. We employ a separate lightweight encoder-decoder network for efficient and robust depth estimation. In a nutshell, the object detection module identifies and localizes obstacles, conveying this information to both the tracking module for monitoring obstacle movement and the depth estimation module for calculating distances. Our approach is evaluated on the Airborne Object Tracking (AOT) dataset which is the largest (to the best of our knowledge) air-to-air airborne object dataset.

arXiv:2405.07847

SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling

We present SceneFactory, a workflow-centric and unified framework for incremental scene modeling, that conveniently supports a wide range of applications, such as (unposed and/or uncalibrated) multi-view depth estimation, LiDAR completion, (dense) RGB-D/RGB-L/Mono/Depth-only reconstruction and SLAM. The workflow-centric design uses multiple blocks as the basis for constructing different production lines. The supported applications, i.e., productions avoid redundancy in their designs. Thus, the focus is placed on each block itself for independent expansion. To support all input combinations, our implementation consists of four building blocks that form SceneFactory: (1) tracking, (2) flexion, (3) depth estimation, and (4) scene reconstruction. The tracking block is based on Mono SLAM and is extended to support RGB-D and RGB-LiDAR (RGB-L) inputs. Flexion is used to convert the depth image (untrackable) into a trackable image. For general-purpose depth estimation, we propose an unposed \& uncalibrated multi-view depth estimation model (U$^2$-MVD) to estimate dense geometry. U$^2$-MVD exploits dense bundle adjustment to solve for poses, intrinsics, and inverse depth. A semantic-aware ScaleCov step is then introduced to complete the multi-view depth. Relying on U$^2$-MVD, SceneFactory both supports user-friendly 3D creation (with just images) and bridges the applications of Dense RGB-D and Dense Mono. For high-quality surface and color reconstruction, we propose Dual-purpose Multi-resolutional Neural Points (DM-NPs) for the first surface accessible Surface Color Field design, where we introduce Improved Point Rasterization (IPR) for point cloud based surface query. ...

arXiv:2405.06241

MGS-SLAM: Monocular Sparse Tracking and Gaussian Mapping with Depth Smooth Regularization

This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results. However, in monocular scenarios, the Gaussian maps reconstructed lack geometric accuracy and exhibit weaker tracking capability. To address these limitations, we jointly optimize sparse visual odometry tracking and 3D Gaussian Splatting scene representation for the first time. We obtain depth maps on visual odometry keyframe windows using a fast Multi-View Stereo (MVS) network for the geometric supervision of Gaussian maps. Furthermore, we propose a depth smooth loss and Sparse-Dense Adjustment Ring (SDAR) to reduce the negative effect of estimated depth maps and preserve the consistency in scale between the visual odometry and Gaussian maps. We have evaluated our system across various synthetic and real-world datasets. The accuracy of our pose estimation surpasses existing methods and achieves state-of-the-art. Additionally, it outperforms previous monocular methods in terms of novel view synthesis and geometric reconstruction fidelities.

arXiv:2405.04579공식 코드 · Papers with Code

Tackling water table depth modeling via machine learning: From proxy observations to verifiability

Spatial patterns of water table depth (WTD) play a crucial role in shaping ecological resilience, hydrological connectivity, and human-centric systems. Generally, a large-scale (e.g., continental or global) continuous map of static WTD can be simulated using either physically-based (PB) or machine learning-based (ML) models. We construct three fine-resolution (500 m) ML simulations of WTD, using the XGBoost algorithm and more than 20 million real and proxy observations of WTD, across the United States and Canada. The three ML models were constrained using known physical relations between WTD's drivers and WTD and were trained by sequentially adding real and proxy observations of WTD. Through an extensive (pixel-by-pixel) evaluation across the study region and within ten major ecoregions of North America, we demonstrate that our models (corr=0.6-0.75) can more accurately predict unseen real and proxy observations of WTD compared to two available PB simulations of WTD (corr=0.21-0.40). However, we still argue that currently-available large-scale simulations of static WTD could be uncertain within data-scarce regions such as steep mountainous regions. We reason that biased observational data mainly collected from low-elevation floodplains and the over-flexibility of available models can negatively affect the verifiability of large-scale simulations of WTD. Ultimately, we thoroughly discuss future directions that may help hydrogeologists decide how to improve machine learning-based WTD estimations. In particular, we advocate for the use of proxy satellite data, the incorporation of physical laws, the implementation of better model verification standards, the development of novel globally-available emergent indices, and the collection of more reliable observations.

arXiv:2405.01558

Configurable Holography: Towards Display and Scene Adaptation

Emerging learned holography approaches have enabled faster and high-quality hologram synthesis, setting a new milestone toward practical holographic displays. However, these learned models require training a dedicated model for each set of display-scene parameters. To address this shortcoming, our work introduces a highly configurable learned model structure, synthesizing 3D holograms interactively while supporting diverse display-scene parameters. Our family of models relying on this structure can be conditioned continuously for varying novel scene parameters, including input images, propagation distances, volume depths, peak brightnesses, and novel display parameters of pixel pitches and wavelengths. Uniquely, our findings unearth a correlation between depth estimation and hologram synthesis tasks in the learning domain, leading to a learned model that unlocks accurate 3D hologram generation from 2D images across varied display-scene parameters. We validate our models by synthesizing high-quality 3D holograms in simulations and also verify our findings with two different holographic display prototypes. Moreover, our family of models can synthesize holograms with a 2x speed-up compared to the state-of-the-art learned holography approaches in the literature.

arXiv:2405.03659

A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

Novel view synthesis from a sparse set of input images is a challenging problem of great practical interest, especially when camera poses are absent or inaccurate. Direct optimization of camera poses and usage of estimated depths in neural radiance field algorithms usually do not produce good results because of the coupling between poses and depths, and inaccuracies in monocular depth estimation. In this paper, we leverage the recent 3D Gaussian splatting method to develop a novel construct-and-optimize method for sparse view synthesis without camera poses. Specifically, we construct a solution progressively by using monocular depth and projecting pixels back into the 3D world. During construction, we optimize the solution by detecting 2D correspondences between training views and the corresponding rendered images. We develop a unified differentiable pipeline for camera registration and adjustment of both camera poses and depths, followed by back-projection. We also introduce a novel notion of an expected surface in Gaussian splatting, which is critical to our optimization. These steps enable a coarse solution, which can then be low-pass filtered and refined using standard optimization methods. We demonstrate results on the Tanks and Temples and Static Hikes datasets with as few as three widely-spaced views, showing significantly better quality than competing methods, including those with approximate camera pose information. Moreover, our results improve with more views and outperform previous InstantNGP and Gaussian Splatting algorithms even when using half the dataset. Project page: https://raymondjiangkw.github.io/cogs.github.io/

arXiv:2405.02004

M${^2}$Depth: Self-supervised Two-Frame Multi-camera Metric Depth Estimation

This paper presents a novel self-supervised two-frame multi-camera metric depth estimation network, termed M${^2}$Depth, which is designed to predict reliable scale-aware surrounding depth in autonomous driving. Unlike the previous works that use multi-view images from a single time-step or multiple time-step images from a single camera, M${^2}$Depth takes temporally adjacent two-frame images from multiple cameras as inputs and produces high-quality surrounding depth. We first construct cost volumes in spatial and temporal domains individually and propose a spatial-temporal fusion module that integrates the spatial-temporal information to yield a strong volume presentation. We additionally combine the neural prior from SAM features with internal features to reduce the ambiguity between foreground and background and strengthen the depth edges. Extensive experimental results on nuScenes and DDAD benchmarks show M${^2}$Depth achieves state-of-the-art performance. More results can be found in https://heiheishuang.xyz/M2Depth .

arXiv:2405.02280공식 코드 · Papers with Code

DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

View-predictive generative models provide strong priors for lifting object-centric images and videos into 3D and 4D through rendering and score distillation objectives. A question then remains: what about lifting complete multi-object dynamic scenes? There are two challenges in this direction: First, rendering error gradients are often insufficient to recover fast object motion, and second, view predictive generative models work much better for objects than whole scenes, so, score distillation objectives cannot currently be applied at the scene level directly. We present DreamScene4D, the first approach to generate 3D dynamic scenes of multiple objects from monocular videos via 360-degree novel view synthesis. Our key insight is a "decompose-recompose" approach that factorizes the video scene into the background and object tracks, while also factorizing object motion into 3 components: object-centric deformation, object-to-world-frame transformation, and camera motion. Such decomposition permits rendering error gradients and object view-predictive models to recover object 3D completions and deformations while bounding box tracks guide the large object movements in the scene. We show extensive results on challenging DAVIS, Kubric, and self-captured videos with quantitative comparisons and a user preference study. Besides 4D scene generation, DreamScene4D obtains accurate 2D persistent point track by projecting the inferred 3D trajectories to 2D. We will release our code and hope our work will stimulate more research on fine-grained 4D understanding from videos.

arXiv:2405.01113

Domain-Transferred Synthetic Data Generation for Improving Monocular Depth Estimation

A major obstacle to the development of effective monocular depth estimation algorithms is the difficulty in obtaining high-quality depth data that corresponds to collected RGB images. Collecting this data is time-consuming and costly, and even data collected by modern sensors has limited range or resolution, and is subject to inconsistencies and noise. To combat this, we propose a method of data generation in simulation using 3D synthetic environments and CycleGAN domain transfer. We compare this method of data generation to the popular NYUDepth V2 dataset by training a depth estimation model based on the DenseDepth structure using different training sets of real and simulated data. We evaluate the performance of the models on newly collected images and LiDAR depth data from a Husky robot to verify the generalizability of the approach and show that GAN-transformed data can serve as an effective alternative to real-world data, particularly in depth estimation.

arXiv:2405.00630

Depth Priors in Removal Neural Radiance Fields

Neural Radiance Fields (NeRF) have achieved impressive results in 3D reconstruction and novel view generation. A significant challenge within NeRF involves editing reconstructed 3D scenes, such as object removal, which demands consistency across multiple views and the synthesis of high-quality perspectives. Previous studies have integrated depth priors, typically sourced from LiDAR or sparse depth estimates from COLMAP, to enhance NeRF's performance in object removal. However, these methods are either expensive or time-consuming. This paper proposes a new pipeline that leverages SpinNeRF and monocular depth estimation models like ZoeDepth to enhance NeRF's performance in complex object removal with improved efficiency. A thorough evaluation of COLMAP's dense depth reconstruction on the KITTI dataset is conducted to demonstrate that COLMAP can be viewed as a cost-effective and scalable alternative for acquiring depth ground truth compared to traditional methods like LiDAR. This serves as the basis for evaluating the performance of monocular depth estimation models to determine the best one for generating depth priors for SpinNeRF. The new pipeline is tested in various scenarios involving 3D reconstruction and object removal, and the results indicate that our pipeline significantly reduces the time required for the acquisition of depth priors for object removal and enhances the fidelity of the synthesized views, suggesting substantial potential for building high-fidelity digital twin systems with increased efficiency in the future.

arXiv:2404.19758

Invisible Stitch: Generating Smooth 3D Scenes with Depth Inpainting

3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Most prior work in this area generates scenes by iteratively stitching newly generated frames with existing geometry. These works often depend on pre-trained monocular depth estimators to lift the generated images into 3D, fusing them with the existing scene representation. These approaches are then often evaluated via a text metric, measuring the similarity between the generated images and a given text prompt. In this work, we make two fundamental contributions to the field of 3D scene generation. First, we note that lifting images to 3D with a monocular depth estimation model is suboptimal as it ignores the geometry of the existing scene. We thus introduce a novel depth completion model, trained via teacher distillation and self-training to learn the 3D fusion process, resulting in improved geometric coherence of the scene. Second, we introduce a new benchmarking scheme for scene generation methods that is based on ground truth geometry, and thus measures the quality of the structure of the scene.

arXiv:2404.17883공식 코드 · Papers with Code

Underwater Variable Zoom: Depth-Guided Perception Network for Underwater Image Enhancement

Underwater scenes intrinsically involve degradation problems owing to heterogeneous ocean elements. Prevailing underwater image enhancement (UIE) methods stick to straightforward feature modeling to learn the mapping function, which leads to limited vision gain as it lacks more explicit physical cues (e.g., depth). In this work, we investigate injecting the depth prior into the deep UIE model for more precise scene enhancement capability. To this end, we present a novel depth-guided perception UIE framework, dubbed underwater variable zoom (UVZ). Specifically, UVZ resorts to a two-stage pipeline. First, a depth estimation network is designed to generate critical depth maps, combined with an auxiliary supervision network introduced to suppress estimation differences during training. Second, UVZ parses near-far scenarios by harnessing the predicted depth maps, enabling local and non-local perceiving in different regions. Extensive experiments on five benchmark datasets demonstrate that UVZ achieves superior visual gain and delivers promising quantitative metrics. Besides, UVZ is confirmed to exhibit good generalization in some visual tasks, especially in unusual lighting conditions. The code, models and results are available at: https://github.com/WindySprint/UVZ.

arXiv:2404.00149공식 코드 · Papers with Code

VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection

Monocular 3D object detection poses a significant challenge in 3D scene understanding due to its inherently ill-posed nature in monocular depth estimation. Existing methods heavily rely on supervised learning using abundant 3D labels, typically obtained through expensive and labor-intensive annotation on LiDAR point clouds. To tackle this problem, we propose a novel weakly supervised 3D object detection framework named VSRD (Volumetric Silhouette Rendering for Detection) to train 3D object detectors without any 3D supervision but only weak 2D supervision. VSRD consists of multi-view 3D auto-labeling and subsequent training of monocular 3D object detectors using the pseudo labels generated in the auto-labeling stage. In the auto-labeling stage, we represent the surface of each instance as a signed distance field (SDF) and render its silhouette as an instance mask through our proposed instance-aware volumetric silhouette rendering. To directly optimize the 3D bounding boxes through rendering, we decompose the SDF of each instance into the SDF of a cuboid and the residual distance field (RDF) that represents the residual from the cuboid. This mechanism enables us to optimize the 3D bounding boxes in an end-to-end manner by comparing the rendered instance masks with the ground truth instance masks. The optimized 3D bounding boxes serve as effective training data for 3D object detection. We conduct extensive experiments on the KITTI-360 dataset, demonstrating that our method outperforms the existing weakly supervised 3D object detection methods. The code is available at https://github.com/skmhrk1209/VSRD.

arXiv:2404.17335

A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillation

Depth estimation is crucial for interpreting complex environments, especially in areas such as autonomous vehicle navigation and robotics. Nonetheless, obtaining accurate depth readings from event camera data remains a formidable challenge. Event cameras operate differently from traditional digital cameras, continuously capturing data and generating asynchronous binary spikes that encode time, location, and light intensity. Yet, the unique sampling mechanisms of event cameras render standard image based algorithms inadequate for processing spike data. This necessitates the development of innovative, spike-aware algorithms tailored for event cameras, a task compounded by the irregularity, continuity, noise, and spatial and temporal characteristics inherent in spiking data.Harnessing the strong generalization capabilities of transformer neural networks for spatiotemporal data, we propose a purely spike-driven spike transformer network for depth estimation from spiking camera data. To address performance limitations with Spiking Neural Networks (SNN), we introduce a novel single-stage cross-modality knowledge transfer framework leveraging knowledge from a large vision foundational model of artificial neural networks (ANN) (DINOv2) to enhance the performance of SNNs with limited data. Our experimental results on both synthetic and real datasets show substantial improvements over existing models, with notable gains in Absolute Relative and Square Relative errors (49% and 39.77% improvements over the benchmark model Spike-T, respectively). Besides accuracy, the proposed model also demonstrates reduced power consumptions, a critical factor for practical applications.

arXiv:2404.15506공식 코드 · Papers with Code

Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation

We introduce Metric3D v2, a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image, which is crucial for metric 3D recovery. While depth and normal are geometrically related and highly complimentary, they present distinct challenges. SoTA monocular depth methods achieve zero-shot generalization by learning affine-invariant depths, which cannot recover real-world metrics. Meanwhile, SoTA normal estimation methods have limited zero-shot performance due to the lack of large-scale labeled data. To tackle these issues, we propose solutions for both metric depth estimation and surface normal estimation. For metric depth estimation, we show that the key to a zero-shot single-view model lies in resolving the metric ambiguity from various camera models and large-scale data training. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problem and can be effortlessly plugged into existing monocular models. For surface normal estimation, we propose a joint depth-normal optimization module to distill diverse data knowledge from metric depth, enabling normal estimators to learn beyond normal labels. Equipped with these modules, our depth-normal models can be stably trained with over 16 million of images from thousands of camera models with different-type annotations, resulting in zero-shot generalization to in-the-wild images with unseen camera settings. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images, paving the way for plausible single-image metrology. Our project page is at https://JUGGHM.github.io/Metric3Dv2.