PyTorchKR Papers

최신 논문

총 2,267편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2403.18807공식 코드 · Papers with Code

ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation

In the absence of parallax cues, a learning-based single image depth estimation (SIDE) model relies heavily on shading and contextual cues in the image. While this simplicity is attractive, it is necessary to train such models on large and varied datasets, which are difficult to capture. It has been shown that using embeddings from pre-trained foundational models, such as CLIP, improves zero shot transfer in several applications. Taking inspiration from this, in our paper we explore the use of global image priors generated from a pre-trained ViT model to provide more detailed contextual information. We argue that the embedding vector from a ViT model, pre-trained on a large dataset, captures greater relevant information for SIDE than the usual route of generating pseudo image captions, followed by CLIP based text embeddings. Based on this idea, we propose a new SIDE model using a diffusion backbone which is conditioned on ViT embeddings. Our proposed design establishes a new state-of-the-art (SOTA) for SIDE on NYUv2 dataset, achieving Abs Rel error of 0.059 (14% improvement) compared to 0.069 by the current SOTA (VPD). And on KITTI dataset, achieving Sq Rel error of 0.139 (2% improvement) compared to 0.142 by the current SOTA (GEDepth). For zero-shot transfer with a model trained on NYUv2, we report mean relative improvement of (20%, 23%, 81%, 25%) over NeWCRFs on (Sun-RGBD, iBims1, DIODE, HyperSim) datasets, compared to (16%, 18%, 45%, 9%) by ZoeDepth. The project page is available at https://ecodepth-iitd.github.io

arXiv:2403.18762공식 코드 · Papers with Code

ModaLink: Unifying Modalities for Efficient Image-to-PointCloud Place Recognition

Place recognition is an important task for robots and autonomous cars to localize themselves and close loops in pre-built maps. While single-modal sensor-based methods have shown satisfactory performance, cross-modal place recognition that retrieving images from a point-cloud database remains a challenging problem. Current cross-modal methods transform images into 3D points using depth estimation for modality conversion, which are usually computationally intensive and need expensive labeled data for depth supervision. In this work, we introduce a fast and lightweight framework to encode images and point clouds into place-distinctive descriptors. We propose an effective Field of View (FoV) transformation module to convert point clouds into an analogous modality as images. This module eliminates the necessity for depth estimation and helps subsequent modules achieve real-time performance. We further design a non-negative factorization-based encoder to extract mutually consistent semantic features between point clouds and images. This encoder yields more distinctive global descriptors for retrieval. Experimental results on the KITTI dataset show that our proposed methods achieve state-of-the-art performance while running in real time. Additional evaluation on the HAOMO dataset covering a 17 km trajectory further shows the practical generalization capabilities. We have released the implementation of our methods as open source at: https://github.com/haomo-ai/ModaLink.git.

arXiv:2403.17301공식 코드 · Papers with Code

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving

Deep learning-based monocular depth estimation (MDE), extensively applied in autonomous driving, is known to be vulnerable to adversarial attacks. Previous physical attacks against MDE models rely on 2D adversarial patches, so they only affect a small, localized region in the MDE map but fail under various viewpoints. To address these limitations, we propose 3D Depth Fool (3D$^2$Fool), the first 3D texture-based adversarial attack against MDE models. 3D$^2$Fool is specifically optimized to generate 3D adversarial textures agnostic to model types of vehicles and to have improved robustness in bad weather conditions, such as rain and fog. Experimental results validate the superior performance of our 3D$^2$Fool across various scenarios, including vehicles, MDE models, weather conditions, and viewpoints. Real-world experiments with printed 3D textures on physical vehicle models further demonstrate that our 3D$^2$Fool can cause an MDE error of over 10 meters.

arXiv:2403.17931

Track Everything Everywhere Fast and Robustly

We propose a novel test-time optimization approach for efficiently and robustly tracking any pixel at any time in a video. The latest state-of-the-art optimization-based tracking technique, OmniMotion, requires a prohibitively long optimization time, rendering it impractical for downstream applications. OmniMotion is sensitive to the choice of random seeds, leading to unstable convergence. To improve efficiency and robustness, we introduce a novel invertible deformation network, CaDeX++, which factorizes the function representation into a local spatial-temporal feature grid and enhances the expressivity of the coupling blocks with non-linear functions. While CaDeX++ incorporates a stronger geometric bias within its architectural design, it also takes advantage of the inductive bias provided by the vision foundation models. Our system utilizes monocular depth estimation to represent scene geometry and enhances the objective by incorporating DINOv2 long-term semantics to regulate the optimization process. Our experiments demonstrate a substantial improvement in training speed (more than \textbf{10 times} faster), robustness, and accuracy in tracking over the SoTA optimization-based method OmniMotion.

arXiv:2403.17915

Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos

Monocular depth estimation in endoscopy videos can enable assistive and robotic surgery to obtain better coverage of the organ and detection of various health issues. Despite promising progress on mainstream, natural image depth estimation, techniques perform poorly on endoscopy images due to a lack of strong geometric features and challenging illumination effects. In this paper, we utilize the photometric cues, i.e., the light emitted from an endoscope and reflected by the surface, to improve monocular depth estimation. We first create two novel loss functions with supervised and self-supervised variants that utilize a per-pixel shading representation. We then propose a novel depth refinement network (PPSNet) that leverages the same per-pixel shading representation. Finally, we introduce teacher-student transfer learning to produce better depth maps from both synthetic data with supervision and clinical data with self-supervision. We achieve state-of-the-art results on the C3VD dataset while estimating high-quality depth maps from clinical data. Our code, pre-trained models, and supplementary materials can be found on our project page: https://ppsnet.github.io/

arXiv:2403.17822공식 코드 · Papers with Code

DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing

High-fidelity 3D reconstruction of common indoor scenes is crucial for VR and AR applications. 3D Gaussian splatting, a novel differentiable rendering technique, has achieved state-of-the-art novel view synthesis results with high rendering speeds and relatively low training times. However, its performance on scenes commonly seen in indoor datasets is poor due to the lack of geometric constraints during optimization. In this work, we explore the use of readily accessible geometric cues to enhance Gaussian splatting optimization in challenging, ill-posed, and textureless scenes. We extend 3D Gaussian splatting with depth and normal cues to tackle challenging indoor datasets and showcase techniques for efficient mesh extraction. Specifically, we regularize the optimization procedure with depth information, enforce local smoothness of nearby Gaussians, and use off-the-shelf monocular networks to achieve better alignment with the true scene geometry. We propose an adaptive depth loss based on the gradient of color images, improving depth estimation and novel view synthesis results over various baselines. Our simple yet effective regularization technique enables direct mesh extraction from the Gaussian representation, yielding more physically accurate reconstructions of indoor scenes.

arXiv:2403.15787

Depth Estimation fusing Image and Radar Measurements with Uncertain Directions

This paper proposes a depth estimation method using radar-image fusion by addressing the uncertain vertical directions of sparse radar measurements. In prior radar-image fusion work, image features are merged with the uncertain sparse depths measured by radar through convolutional layers. This approach is disturbed by the features computed with the uncertain radar depths. Furthermore, since the features are computed with a fully convolutional network, the uncertainty of each depth corresponding to a pixel is spread out over its surrounding pixels. Our method avoids this problem by computing features only with an image and conditioning the features pixelwise with the radar depth. Furthermore, the set of possibly correct radar directions is identified with reliable LiDAR measurements, which are available only in the training stage. Our method improves training data by learning only these possibly correct radar directions, while the previous method trains raw radar measurements, including erroneous measurements. Experimental results demonstrate that our method can improve the quantitative and qualitative results compared with its base method using radar-image fusion.

arXiv:2403.16410

Spike-NeRF: Neural Radiance Field Based On Spike Camera

As a neuromorphic sensor with high temporal resolution, spike cameras offer notable advantages over traditional cameras in high-speed vision applications such as high-speed optical estimation, depth estimation, and object tracking. Inspired by the success of the spike camera, we proposed Spike-NeRF, the first Neural Radiance Field derived from spike data, to achieve 3D reconstruction and novel viewpoint synthesis of high-speed scenes. Instead of the multi-view images at the same time of NeRF, the inputs of Spike-NeRF are continuous spike streams captured by a moving spike camera in a very short time. To reconstruct a correct and stable 3D scene from high-frequency but unstable spike data, we devised spike masks along with a distinctive loss function. We evaluate our method qualitatively and numerically on several challenging synthetic scenes generated by blender with the spike camera simulator. Our results demonstrate that Spike-NeRF produces more visually appealing results than the existing methods and the baseline we proposed in high-speed scenes. Our code and data will be released soon.

arXiv:2403.16376

Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion

360 depth estimation has recently received great attention for 3D reconstruction owing to its omnidirectional field of view (FoV). Recent approaches are predominantly focused on cross-projection fusion with geometry-based re-projection: they fuse 360 images with equirectangular projection (ERP) and another projection type, e.g., cubemap projection to estimate depth with the ERP format. However, these methods suffer from 1) limited local receptive fields, making it hardly possible to capture large FoV scenes, and 2) prohibitive computational cost, caused by the complex cross-projection fusion module design. In this paper, we propose Elite360D, a novel framework that inputs the ERP image and icosahedron projection (ICOSAP) point set, which is undistorted and spatially continuous. Elite360D is superior in its capacity in learning a representation from a local-with-global perspective. With a flexible ERP image encoder, it includes an ICOSAP point encoder, and a Bi-projection Bi-attention Fusion (B2F) module (totally ~1M parameters). Specifically, the ERP image encoder can take various perspective image-trained backbones (e.g., ResNet, Transformer) to extract local features. The point encoder extracts the global features from the ICOSAP. Then, the B2F module captures the semantic- and distance-aware dependencies between each pixel of the ERP feature and the entire ICOSAP feature set. Without specific backbone design and obvious computational cost increase, Elite360D outperforms the prior arts on several benchmark datasets.

arXiv:2403.15551

Language-Based Depth Hints for Monocular Depth Estimation

Monocular depth estimation (MDE) is inherently ambiguous, as a given image may result from many different 3D scenes and vice versa. To resolve this ambiguity, an MDE system must make assumptions about the most likely 3D scenes for a given input. These assumptions can be either explicit or implicit. In this work, we demonstrate the use of natural language as a source of an explicit prior about the structure of the world. The assumption is made that human language encodes the likely distribution in depth-space of various objects. We first show that a language model encodes this implicit bias during training, and that it can be extracted using a very simple learned approach. We then show that this prediction can be provided as an explicit source of assumption to an MDE system, using an off-the-shelf instance segmentation model that provides the labels used as the input to the language model. We demonstrate the performance of our method on the NYUD2 dataset, showing improvement compared to the baseline and to random controls.

arXiv:2403.12981

Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision

Deep neural network (DNN) inference has become an important part of many data-center workloads. This has prompted focused efforts to design ever-faster deep learning accelerators such as GPUs and TPUs. However, an end-to-end DNN-based vision application contains more than just DNN inference, including input decompression, resizing, sampling, normalization, and data transfer. In this paper, we perform a thorough evaluation of computer vision inference requests performed on a throughput-optimized serving system. We quantify the performance impact of server overheads such as data movement, preprocessing, and message brokers between two DNNs producing outputs at different rates. Our empirical analysis encompasses many computer vision tasks including image classification, segmentation, detection, depth-estimation, and more complex processing pipelines with multiple DNNs. Our results consistently demonstrate that end-to-end application performance can easily be dominated by data processing and data movement functions (up to 56% of end-to-end latency in a medium-sized image, and $\sim$ 80% impact on system throughput in a large image), even though these functions have been conventionally overlooked in deep learning system design. Our work identifies important performance bottlenecks in different application scenarios, achieves 2.25$\times$ better throughput compared to prior work, and paves the way for more holistic deep learning system design.

arXiv:2403.14494

Learning to Project for Cross-Task Knowledge Distillation

Traditional knowledge distillation (KD) relies on a proficient teacher trained on the target task, which is not always available. In this setting, cross-task distillation can be used, enabling the use of any teacher model trained on a different task. However, many KD methods prove ineffective when applied to this cross-task setting. To address this limitation, we propose a simple modification: the use of an inverted projection. We show that this drop-in replacement for a standard projector is effective by learning to disregard any task-specific features which might degrade the student's performance. We find that this simple modification is sufficient for extending many KD methods to the cross-task setting, where the teacher and student tasks can be very different. In doing so, we obtain up to a 1.9% improvement in the cross-task setting compared to the traditional projection, at no additional cost. Our method can obtain significant performance improvements (up to 7%) when using even a randomly-initialised teacher on various tasks such as depth estimation, image translation, and semantic segmentation, despite the lack of any learned knowledge to transfer. To provide conceptual and analytical insights into this result, we show that using an inverted projection allows the distillation loss to be decomposed into a knowledge transfer and a spectral regularisation component. Through this analysis we are additionally able to propose a novel regularisation loss that allows teacher-free distillation, enabling performance improvements of up to 8.57% on ImageNet with no additional training costs.

arXiv:2403.13043공식 코드 · Papers with Code

When Do We Not Need Larger Vision Models?

Scaling up the size of vision models has been the de facto standard to obtain more powerful visual representations. In this work, we discuss the point beyond which larger vision models are not necessary. First, we demonstrate the power of Scaling on Scales (S$^2$), whereby a pre-trained and frozen smaller vision model (e.g., ViT-B or ViT-L), run over multiple image scales, can outperform larger models (e.g., ViT-H or ViT-G) on classification, segmentation, depth estimation, Multimodal LLM (MLLM) benchmarks, and robotic manipulation. Notably, S$^2$ achieves state-of-the-art performance in detailed understanding of MLLM on the V* benchmark, surpassing models such as GPT-4V. We examine the conditions under which S$^2$ is a preferred scaling approach compared to scaling on model size. While larger models have the advantage of better generalization on hard examples, we show that features of larger vision models can be well approximated by those of multi-scale smaller models. This suggests most, if not all, of the representations learned by current large pre-trained models can also be obtained from multi-scale smaller models. Our results show that a multi-scale smaller model has comparable learning capacity to a larger model, and pre-training smaller models with S$^2$ can match or even exceed the advantage of larger models. We release a Python package that can apply S$^2$ on any vision model with one line of code: https://github.com/bfshi/scaling_on_scales.

arXiv:2403.13788공식 코드 · Papers with Code

DepthFM: Fast Monocular Depth Estimation with Flow Matching

Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth estimation as a direct transport between image and depth distributions. We are the first to explore flow matching in this field, and we demonstrate that its interpolation trajectories enhance both training and sampling efficiency while preserving high performance. While generative models typically require extensive training data, we mitigate this dependency by integrating external knowledge from a pre-trained image diffusion model, enabling effective transfer even across differing objectives. To further boost our model performance, we employ synthetic data and utilize image-depth pairs generated by a discriminative model on an in-the-wild image dataset. As a generative model, our model can reliably estimate depth confidence, which provides an additional advantage. Our approach achieves competitive zero-shot performance on standard benchmarks of complex natural scenes while improving sampling efficiency and only requiring minimal synthetic data for training.

arXiv:2403.12953

FutureDepth: Learning to Predict the Future Improves Video Depth Estimation

In this paper, we propose a novel video depth estimation approach, FutureDepth, which enables the model to implicitly leverage multi-frame and motion cues to improve depth estimation by making it learn to predict the future at training. More specifically, we propose a future prediction network, F-Net, which takes the features of multiple consecutive frames and is trained to predict multi-frame features one time step ahead iteratively. In this way, F-Net learns the underlying motion and correspondence information, and we incorporate its features into the depth decoding process. Additionally, to enrich the learning of multiframe correspondence cues, we further leverage a reconstruction network, R-Net, which is trained via adaptively masked auto-encoding of multiframe feature volumes. At inference time, both F-Net and R-Net are used to produce queries to work with the depth decoder, as well as a final refinement network. Through extensive experiments on several benchmarks, i.e., NYUDv2, KITTI, DDAD, and Sintel, which cover indoor, driving, and open-domain scenarios, we show that FutureDepth significantly improves upon baseline models, outperforms existing video depth estimation methods, and sets new state-of-the-art (SOTA) accuracy. Furthermore, FutureDepth is more efficient than existing SOTA video depth estimation models and has similar latencies when comparing to monocular models

arXiv:2403.12431

Geometric Constraints in Deep Learning Frameworks: A Survey

Stereophotogrammetry is an emerging technique of scene understanding. Its origins go back to at least the 1800s when people first started to investigate using photographs to measure the physical properties of the world. Since then, thousands of approaches have been explored. The classic geometric techniques of Shape from Stereo is built on using geometry to define constraints on scene and camera geometry and then solving the non-linear systems of equations. More recent work has taken an entirely different approach, using end-to-end deep learning without any attempt to explicitly model the geometry. In this survey, we explore the overlap for geometric-based and deep learning-based frameworks. We compare and contrast geometry enforcing constraints integrated into a deep learning framework for depth estimation or other closely related problems. We present a new taxonomy for prevalent geometry enforcing constraints used in modern deep learning frameworks. We also present insightful observations and potential future research directions.

arXiv:2403.11848

GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection

Integrating LiDAR and camera information into Bird's-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing methods are susceptible to the inaccurate calibration relationship between LiDAR and the camera sensor. Such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a robust fusion framework called Graph BEV. Addressing errors caused by inaccurate point cloud projection, we introduce a Local Align module that employs neighbor-aware depth features via Graph matching. Additionally, we propose a Global Align module to rectify the misalignment between LiDAR and camera BEV features. Our Graph BEV framework achieves state-of-the-art performance, with an mAP of 70.1\%, surpassing BEV Fusion by 1.6\% on the nuscenes validation set. Importantly, our Graph BEV outperforms BEV Fusion by 8.3\% under conditions with misalignment noise.

arXiv:2403.10840공식 코드 · Papers with Code

MSI-NeRF: Linking Omni-Depth with View Synthesis through Multi-Sphere Image aided Generalizable Neural Radiance Field

Panoramic observation using fisheye cameras is significant in virtual reality (VR) and robot perception. However, panoramic images synthesized by traditional methods lack depth information and can only provide three degrees-of-freedom (3DoF) rotation rendering in VR applications. To fully preserve and exploit the parallax information within the original fisheye cameras, we introduce MSI-NeRF, which combines deep learning omnidirectional depth estimation and novel view synthesis. We construct a multi-sphere image as a cost volume through feature extraction and warping of the input images. We further build an implicit radiance field using spatial points and interpolated 3D feature vectors as input, which can simultaneously realize omnidirectional depth estimation and 6DoF view synthesis. Leveraging the knowledge from depth estimation task, our method can learn scene appearance by source view supervision only. It does not require novel target views and can be trained conveniently on existing panorama depth estimation datasets. Our network has the generalization ability to reconstruct unknown scenes efficiently using only four images. Experimental results show that our method outperforms existing methods in both depth estimation and novel view synthesis tasks.

arXiv:2403.10662공식 코드 · Papers with Code

SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images

This research paper presents an innovative multi-task learning framework that allows concurrent depth estimation and semantic segmentation using a single camera. The proposed approach is based on a shared encoder-decoder architecture, which integrates various techniques to improve the accuracy of the depth estimation and semantic segmentation task without compromising computational efficiency. Additionally, the paper incorporates an adversarial training component, employing a Wasserstein GAN framework with a critic network, to refine model's predictions. The framework is thoroughly evaluated on two datasets - the outdoor Cityscapes dataset and the indoor NYU Depth V2 dataset - and it outperforms existing state-of-the-art methods in both segmentation and depth estimation tasks. We also conducted ablation studies to analyze the contributions of different components, including pre-training strategies, the inclusion of critics, the use of logarithmic depth scaling, and advanced image augmentations, to provide a better understanding of the proposed framework. The accompanying source code is accessible at \url{https://github.com/PardisTaghavi/SwinMTL}.

arXiv:2403.11515

SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications

Monocular depth estimation (MDE) has advanced significantly, primarily through the integration of convolutional neural networks (CNNs) and more recently, Transformers. However, concerns about their susceptibility to adversarial attacks have emerged, especially in safety-critical domains like autonomous driving and robotic navigation. Existing approaches for assessing CNN-based depth prediction methods have fallen short in inducing comprehensive disruptions to the vision system, often limited to specific local areas. In this paper, we introduce SSAP (Shape-Sensitive Adversarial Patch), a novel approach designed to comprehensively disrupt monocular depth estimation (MDE) in autonomous navigation applications. Our patch is crafted to selectively undermine MDE in two distinct ways: by distorting estimated distances or by creating the illusion of an object disappearing from the system's perspective. Notably, our patch is shape-sensitive, meaning it considers the specific shape and scale of the target object, thereby extending its influence beyond immediate proximity. Furthermore, our patch is trained to effectively address different scales and distances from the camera. Experimental results demonstrate that our approach induces a mean depth estimation error surpassing 0.5, impacting up to 99% of the targeted region for CNN-based MDE models. Additionally, we investigate the vulnerability of Transformer-based MDE models to patch-based attacks, revealing that SSAP yields a significant error of 0.59 and exerts substantial influence over 99% of the target region on these models.