PyTorchKR Papers

최신 논문

총 2,549편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2301.08915공식 코드 · Papers with Code

Improving Deep Regression with Ordinal Entropy

In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon and provide a derivation to show that classification, with the cross-entropy loss, outperforms regression with a mean squared error loss in its ability to learn high-entropy feature representations. Based on the analysis, we propose an ordinal entropy loss to encourage higher-entropy feature spaces while maintaining ordinal relationships to improve the performance of regression tasks. Experiments on synthetic and real-world regression tasks demonstrate the importance and benefits of increasing entropy for regression.

arXiv:2301.08433

Unsupervised Light Field Depth Estimation via Multi-view Feature Matching with Occlusion Prediction

Depth estimation from light field (LF) images is a fundamental step for numerous applications. Recently, learning-based methods have achieved higher accuracy and efficiency than the traditional methods. However, it is costly to obtain sufficient depth labels for supervised training. In this paper, we propose an unsupervised framework to estimate depth from LF images. First, we design a disparity estimation network (DispNet) with a coarse-to-fine structure to predict disparity maps from different view combinations. It explicitly performs multi-view feature matching to learn the correspondences effectively. As occlusions may cause the violation of photo-consistency, we introduce an occlusion prediction network (OccNet) to predict the occlusion maps, which are used as the element-wise weights of photometric loss to solve the occlusion issue and assist the disparity learning. With the disparity maps estimated by multiple input combinations, we then propose a disparity fusion strategy based on the estimated errors with effective occlusion handling to obtain the final disparity map with higher accuracy. Experimental results demonstrate that our method achieves superior performance on both the dense and sparse LF images, and also shows better robustness and generalization on the real-world LF images compared to the other methods.

arXiv:2301.08414

FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation

The great potential of unsupervised monocular depth estimation has been demonstrated by many works due to low annotation cost and impressive accuracy comparable to supervised methods. To further improve the performance, recent works mainly focus on designing more complex network structures and exploiting extra supervised information, e.g., semantic segmentation. These methods optimize the models by exploiting the reconstructed relationship between the target and reference images in varying degrees. However, previous methods prove that this image reconstruction optimization is prone to get trapped in local minima. In this paper, our core idea is to guide the optimization with prior knowledge from pretrained Flow-Net. And we show that the bottleneck of unsupervised monocular depth estimation can be broken with our simple but effective framework named FG-Depth. In particular, we propose (i) a flow distillation loss to replace the typical photometric loss that limits the capacity of the model and (ii) a prior flow based mask to remove invalid pixels that bring the noise in training loss. Extensive experiments demonstrate the effectiveness of each component, and our approach achieves state-of-the-art results on both KITTI and NYU-Depth-v2 datasets.

arXiv:2301.08245

Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces

Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and effectively processing high-resolution images. Purposely, we propose a novel dataset that includes accurate and dense ground-truth labels at high resolution, featuring scenes containing several specular and transparent surfaces. Our acquisition pipeline leverages a novel deep space-time stereo framework, enabling easy and accurate labeling with sub-pixel precision. The dataset is composed of 606 samples collected in 85 different scenes, each sample includes both a high-resolution pair (12 Mpx) as well as an unbalanced stereo pair (Left: 12 Mpx, Right: 1.1 Mpx), typical of modern mobile devices that mount sensors with different resolutions. Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. The dataset is composed of a train set and two test sets, the latter devoted to the evaluation of stereo and monocular depth estimation networks. Our experiments highlight the open challenges and future research directions in this field.

arXiv:2301.08157

SoftEnNet: Symbiotic Monocular Depth Estimation and Lumen Segmentation for Colonoscopy Endorobots

Colorectal cancer is the third most common cause of cancer death worldwide. Optical colonoscopy is the gold standard for detecting colorectal cancer; however, about 25 percent of polyps are missed during the procedure. A vision-based autonomous endorobot can improve colonoscopy procedures significantly through systematic, complete screening of the colonic mucosa. The reliable robot navigation needed requires a three-dimensional understanding of the environment and lumen tracking to support autonomous tasks. We propose a novel multi-task model that simultaneously predicts dense depth and lumen segmentation with an ensemble of deep networks. The depth estimation sub-network is trained in a self-supervised fashion guided by view synthesis; the lumen segmentation sub-network is supervised. The two sub-networks are interconnected with pathways that enable information exchange and thereby mutual learning. As the lumen is in the image's deepest visual space, lumen segmentation helps with the depth estimation at the farthest location. In turn, the estimated depth guides the lumen segmentation network as the lumen location defines the farthest scene location. Unlike other environments, view synthesis often fails in the colon because of the deformable wall, textureless surface, specularities, and wide field of view image distortions, all challenges that our pipeline addresses. We conducted qualitative analysis on a synthetic dataset and quantitative analysis on a colon training model and real colonoscopy videos. The experiments show that our model predicts accurate scale-invariant depth maps and lumen segmentation from colonoscopy images in near real-time.

arXiv:2301.08243공식 코드 · Papers with Code

Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture

This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) sample target blocks with sufficiently large scale (semantic), and to (b) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/14 on ImageNet using 16 A100 GPUs in under 72 hours to achieve strong downstream performance across a wide range of tasks, from linear classification to object counting and depth prediction.

arXiv:2301.07668공식 코드 · Papers with Code

Behind the Scenes: Density Fields for Single View Reconstruction

Inferring a meaningful geometric scene representation from a single image is a fundamental problem in computer vision. Approaches based on traditional depth map prediction can only reason about areas that are visible in the image. Currently, neural radiance fields (NeRFs) can capture true 3D including color, but are too complex to be generated from a single image. As an alternative, we propose to predict implicit density fields. A density field maps every location in the frustum of the input image to volumetric density. By directly sampling color from the available views instead of storing color in the density field, our scene representation becomes significantly less complex compared to NeRFs, and a neural network can predict it in a single forward pass. The prediction network is trained through self-supervision from only video data. Our formulation allows volume rendering to perform both depth prediction and novel view synthesis. Through experiments, we show that our method is able to predict meaningful geometry for regions that are occluded in the input image. Additionally, we demonstrate the potential of our approach on three datasets for depth prediction and novel-view synthesis.

arXiv:2301.06715공식 코드 · Papers with Code

SwinDepth: Unsupervised Depth Estimation using Monocular Sequences via Swin Transformer and Densely Cascaded Network

Monocular depth estimation plays a critical role in various computer vision and robotics applications such as localization, mapping, and 3D object detection. Recently, learning-based algorithms achieve huge success in depth estimation by training models with a large amount of data in a supervised manner. However, it is challenging to acquire dense ground truth depth labels for supervised training, and the unsupervised depth estimation using monocular sequences emerges as a promising alternative. Unfortunately, most studies on unsupervised depth estimation explore loss functions or occlusion masks, and there is little change in model architecture in that ConvNet-based encoder-decoder structure becomes a de-facto standard for depth estimation. In this paper, we employ a convolution-free Swin Transformer as an image feature extractor so that the network can capture both local geometric features and global semantic features for depth estimation. Also, we propose a Densely Cascaded Multi-scale Network (DCMNet) that connects every feature map directly with another from different scales via a top-down cascade pathway. This densely cascaded connectivity reinforces the interconnection between decoding layers and produces high-quality multi-scale depth outputs. The experiments on two different datasets, KITTI and Make3D, demonstrate that our proposed method outperforms existing state-of-the-art unsupervised algorithms.

arXiv:2301.05871

Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes

Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the motion of dynamic objects. In this paper, we propose a novel Dyna-Depthformer framework, which predicts scene depth and 3D motion field jointly and aggregates multi-frame information with transformer. Our contributions are two-fold. First, we leverage multi-view correlation through a series of self- and cross-attention layers in order to obtain enhanced depth feature representation. Specifically, we use the perspective transformation to acquire the initial reference point, and use deformable attention to reduce the computational cost. Second, we propose a warping-based Motion Network to estimate the motion field of dynamic objects without using semantic prior. To improve the motion field predictions, we propose an iterative optimization strategy, together with a sparsity-regularized loss. The entire pipeline achieves end-to-end self-supervised training by constructing a minimum reprojection loss. Extensive experiments on the KITTI and Cityscapes benchmarks demonstrate the effectiveness of our method and show that our method outperforms state-of-the-art algorithms.

arXiv:2301.05845

${S}^{2}$Net: Accurate Panorama Depth Estimation on Spherical Surface

Monocular depth estimation is an ambiguous problem, thus global structural cues play an important role in current data-driven single-view depth estimation methods. Panorama images capture the complete spatial information of their surroundings utilizing the equirectangular projection which introduces large distortion. This requires the depth estimation method to be able to handle the distortion and extract global context information from the image. In this paper, we propose an end-to-end deep network for monocular panorama depth estimation on a unit spherical surface. Specifically, we project the feature maps extracted from equirectangular images onto unit spherical surface sampled by uniformly distributed grids, where the decoder network can aggregate the information from the distortion-reduced feature maps. Meanwhile, we propose a global cross-attention-based fusion module to fuse the feature maps from skip connection and enhance the ability to obtain global context. Experiments are conducted on five panorama depth estimation datasets, and the results demonstrate that the proposed method substantially outperforms previous state-of-the-art methods. All related codes will be open-sourced in the upcoming days.

arXiv:2301.03178

Deep Planar Parallax for Monocular Depth Estimation

Recent research has highlighted the utility of Planar Parallax Geometry in monocular depth estimation. However, its potential has yet to be fully realized because networks rely heavily on appearance for depth prediction. Our in-depth analysis reveals that utilizing flow-pretrain can optimize the network's usage of consecutive frame modeling, leading to substantial performance enhancement. Additionally, we propose Planar Position Embedding (PPE) to handle dynamic objects that defy static scene assumptions and to tackle slope variations that are challenging to differentiate. Comprehensive experiments on autonomous driving datasets, namely KITTI and the Waymo Open Dataset (WOD), prove that our Planar Parallax Network (PPNet) significantly surpasses existing learning-based methods in performance.

arXiv:2301.03169공식 코드 · Papers with Code

A Study on the Generality of Neural Network Structures for Monocular Depth Estimation

Monocular depth estimation has been widely studied, and significant improvements in performance have been recently reported. However, most previous works are evaluated on a few benchmark datasets, such as KITTI datasets, and none of the works provide an in-depth analysis of the generalization performance of monocular depth estimation. In this paper, we deeply investigate the various backbone networks (e.g.CNN and Transformer models) toward the generalization of monocular depth estimation. First, we evaluate state-of-the-art models on both in-distribution and out-of-distribution datasets, which have never been seen during network training. Then, we investigate the internal properties of the representations from the intermediate layers of CNN-/Transformer-based models using synthetic texture-shifted datasets. Through extensive experiments, we observe that the Transformers exhibit a strong shape-bias rather than CNNs, which have a strong texture-bias. We also discover that texture-biased models exhibit worse generalization performance for monocular depth estimation than shape-biased models. We demonstrate that similar aspects are observed in real-world driving datasets captured under diverse environments. Lastly, we conduct a dense ablation study with various backbone networks which are utilized in modern strategies. The experiments demonstrate that the intrinsic locality of the CNNs and the self-attention of the Transformers induce texture-bias and shape-bias, respectively.

arXiv:2301.02229공식 코드 · Papers with Code

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek to unify the output space of visual tasks, so that we can also build a unified model for visual tasks. To this end, we demonstrate a single unified model that simultaneously handles two typical visual tasks of instance segmentation and depth estimation, which have discrete/fixed-length and continuous/varied-length outputs, respectively. We propose several new techniques that take into account the particularity of visual tasks: 1) Soft token. We employ soft token to represent the task output. Unlike hard tokens in the common VQ-VAE which are assigned one-hot to discrete codebooks/vocabularies, the soft token is assigned softly to the codebook embeddings. Soft token can improve the accuracy of both the next token inference and decoding of the task output; 2) Mask augmentation. Many visual tasks have corruption, undefined or invalid values in label annotations, i.e., occluded area of depth maps. We show that a mask augmentation technique can greatly benefit these tasks. With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well. Particularly, we achieve 0.279 RMSE on the specific task of NYUv2 depth estimation, setting a new record on this benchmark. The general-purpose task-solver, dubbed AiT, is available at \url{https://github.com/SwinTransformer/AiT}.

arXiv:2301.02092

DepthP+P: Metric Accurate Monocular Depth Estimation using Planar and Parallax

Current self-supervised monocular depth estimation methods are mostly based on estimating a rigid-body motion representing camera motion. These methods suffer from the well-known scale ambiguity problem in their predictions. We propose DepthP+P, a method that learns to estimate outputs in metric scale by following the traditional planar parallax paradigm. We first align the two frames using a common ground plane which removes the effect of the rotation component in the camera motion. With two neural networks, we predict the depth and the camera translation, which is easier to predict alone compared to predicting it together with rotation. By assuming a known camera height, we can then calculate the induced 2D image motion of a 3D point and use it for reconstructing the target image in a self-supervised monocular approach. We perform experiments on the KITTI driving dataset and show that the planar parallax approach, which only needs to predict camera translation, can be a metrically accurate alternative to the current methods that rely on estimating 6DoF camera motion.

arXiv:2301.01057

BS3D: Building-scale 3D Reconstruction from RGB-D Images

Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems. Existing datasets often include small environments, have incomplete ground truth, or lack important sensor data, such as depth and infrared images. We propose an easy-to-use framework for acquiring building-scale 3D reconstruction using a consumer depth camera. Unlike complex and expensive acquisition setups, our system enables crowd-sourcing, which can greatly benefit data-hungry algorithms. Compared to similar systems, we utilize raw depth maps for odometry computation and loop closure refinement which results in better reconstructions. We acquire a building-scale 3D dataset (BS3D) and demonstrate its value by training an improved monocular depth estimation model. As a unique experiment, we benchmark visual-inertial odometry methods using both color and active infrared images.

arXiv:2212.14397공식 코드 · Papers with Code

AttEntropy: On the Generalization Ability of Supervised Semantic Segmentation Transformers to New Objects in New Domains

In addition to impressive performance, vision transformers have demonstrated remarkable abilities to encode information they were not trained to extract. For example, this information can be used to perform segmentation or single-view depth estimation even though the networks were only trained for image recognition. We show that a similar phenomenon occurs when explicitly training transformers for semantic segmentation in a supervised manner for a set of categories: Once trained, they provide valuable information even about categories absent from the training set. This information can be used to segment objects from these never-seen-before classes in domains as varied as road obstacles, aircraft parked at a terminal, lunar rocks, and maritime hazards.

arXiv:2212.12645

HandsOff: Labeled Dataset Generation With No Additional Human Annotations

Recent work leverages the expressive power of generative adversarial networks (GANs) to generate labeled synthetic datasets. These dataset generation methods often require new annotations of synthetic images, which forces practitioners to seek out annotators, curate a set of synthetic images, and ensure the quality of generated labels. We introduce the HandsOff framework, a technique capable of producing an unlimited number of synthetic images and corresponding labels after being trained on less than 50 pre-existing labeled images. Our framework avoids the practical drawbacks of prior work by unifying the field of GAN inversion with dataset generation. We generate datasets with rich pixel-wise labels in multiple challenging domains such as faces, cars, full-body human poses, and urban driving scenes. Our method achieves state-of-the-art performance in semantic segmentation, keypoint detection, and depth estimation compared to prior dataset generation approaches and transfer learning baselines. We additionally showcase its ability to address broad challenges in model development which stem from fixed, hand-annotated datasets, such as the long-tail problem in semantic segmentation. Project page: austinxu87.github.io/handsoff.

arXiv:2212.12324

Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography

Modern mobile burst photography pipelines capture and merge a short sequence of frames to recover an enhanced image, but often disregard the 3D nature of the scene they capture, treating pixel motion between images as a 2D aggregation problem. We show that in a ''long-burst'', forty-two 12-megapixel RAW frames captured in a two-second sequence, there is enough parallax information from natural hand tremor alone to recover high-quality scene depth. To this end, we devise a test-time optimization approach that fits a neural RGB-D representation to long-burst data and simultaneously estimates scene depth and camera motion. Our plane plus depth model is trained end-to-end, and performs coarse-to-fine refinement by controlling which multi-resolution volume features the network has access to at what time during training. We validate the method experimentally, and demonstrate geometrically accurate depth reconstructions with no additional hardware or separate data pre-processing and pose-estimation steps.

arXiv:2212.11741

Depth Estimation maps of lidar and stereo images

This paper as technology report is focusing on evaluation and performance about depth estimations based on lidar data and stereo images(front left and front right). The lidar 3d cloud data and stereo images are provided by ford. In addition, this paper also will explain some details about optimization for depth estimation performance. And some reasons why not use machine learning to do depth estimation, replaced by pure mathmatics to do stereo depth estimation. The structure of this paper is made of by following:(1) Performance: to discuss and evaluate about depth maps created from stereo images and 3D cloud points, and relationships analysis for alignment and errors;(2) Depth estimation by stereo images: to explain the methods about how to use stereo images to estimate depth;(3)Depth estimation by lidar: to explain the methods about how to use 3d cloud datas to estimate depth;In summary, this report is mainly to show the performance of depth maps and their approaches, analysis for them.

arXiv:2212.11684공식 코드 · Papers with Code

Scene-aware Egocentric 3D Human Pose Estimation

Egocentric 3D human pose estimation with a single head-mounted fisheye camera has recently attracted attention due to its numerous applications in virtual and augmented reality. Existing methods still struggle in challenging poses where the human body is highly occluded or is closely interacting with the scene. To address this issue, we propose a scene-aware egocentric pose estimation method that guides the prediction of the egocentric pose with scene constraints. To this end, we propose an egocentric depth estimation network to predict the scene depth map from a wide-view egocentric fisheye camera while mitigating the occlusion of the human body with a depth-inpainting network. Next, we propose a scene-aware pose estimation network that projects the 2D image features and estimated depth map of the scene into a voxel space and regresses the 3D pose with a V2V network. The voxel-based feature representation provides the direct geometric connection between 2D image features and scene geometry, and further facilitates the V2V network to constrain the predicted pose based on the estimated scene geometry. To enable the training of the aforementioned networks, we also generated a synthetic dataset, called EgoGTA, and an in-the-wild dataset based on EgoPW, called EgoPW-Scene. The experimental results of our new evaluation sequences show that the predicted 3D egocentric poses are accurate and physically plausible in terms of human-scene interaction, demonstrating that our method outperforms the state-of-the-art methods both quantitatively and qualitatively.