本文提出少样本适配 CLIP 的单目深度估计方法，通过场景可选深度区间和可学习文本提示提升泛化性能，在 NYU V2 与 KITTI 上每场景仅用一张训练图，MARE 最高提升 10.6%。
摘要：
预训练的视觉-语言模型（VLM），例如 CLIP，已在一系列涉及视觉与语言模态融合的任务中展现出增强的性能。当 CLIP 用于深度估计任务时，从输入图像划分出的图像块可以与一系列深度信息的语义描述相结合，以获得相似度结果。随后，通过对与预定义语义描述相对应的深度值（称为深度区间，depth bins）进行加权和求和，得到粗略的深度估计。这种零样本方法规避了传统全监督深度估计方法在计算和时间上的高成本。然而，这种使用固定深度区间的方法可能无法有效泛化，因为来自不同场景的图像可能呈现出明显不同的深度分布。为应对这一挑战，我们提出了一种基于少样本的方法，该方法学习适配 VLM 以进行单目深度估计，从而在训练成本与泛化能力之间取得平衡。具体而言，该方法为不同场景分配不同的深度区间，模型可在推理期间对其进行选择。此外，我们引入可学习提示来预处理输入文本，将人类易于理解的文本转换为模型易于理解的向量，并进一步提升性能。尽管每个场景仅使用一张图像进行训练，我们在 NYU V2 和 KITTI 数据集上的大量实验结果表明，就 MARE 而言，本方法较此前最先进方法的性能提升最高达 10.6%。
英文摘要：
Pre-trained Vision-Language Models (VLMs), such as CLIP, have shown enhanced performance across a range of tasks that involve the integration of visual and linguistic modalities. When CLIP is used for depth estimation tasks, the patches, divided from the input images, can be combined with a series of semantic descriptions of the depth information to obtain similarity results. The coarse estimation of depth is then achieved by weighting and summing the depth values, called depth bins, corresponding to the predefined semantic descriptions. The zero-shot approach circumvents the computational and time-intensive nature of traditional fully-supervised depth estimation methods. However, this method, utilizing fixed depth bins, may not effectively generalize as images from different scenes may exhibit distinct depth distributions. To address this challenge, we propose a few-shot-based method which learns to adapt the VLMs for monocular depth estimation to balance training costs and generalization capabilities. Specifically, it assigns different depth bins for different scenes, which can be selected by the model during inference. Additionally, we incorporate learnable prompts to preprocess the input text to convert the easily human-understood text into easily model-understood vectors and further enhance the performance. With only one image per scene for training, our extensive experiment results on the NYU V2 and KITTI dataset demonstrate that our method outperforms the previous state-of-the-art method by up to 10.6\% in terms of MARE.
Carnegie Mellon University（卡内基梅隆大学）；Chinese Academy of Sciences（中国科学院）
We present a novel unsupervised learning framework for single view depth estimation using monocular videos. It is well known in 3D vision that enlarging the baseline can increase the depth estimation accuracy, and jointly optimizing a set of camera poses and landmarks is essential. In previous monocular unsupervised learning frameworks, only part of the photometric and geometric constraints within a sequence are used as supervisory signals. This may result in a short baseline and overfitting. Besides, previous works generally estimate a low resolution depth from a low resolution impute image. …
Lightweight Prompt-Guided CLIP Adaptation for Monocular Depth Estimation
School of Engineering Science, Simon Fraser University（西蒙弗雷泽大学工程科学学院）；School of Information Science and Technology, Eastern Institute of Technology（东方理工学院信息科学与技术学院）
Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
MoE Key Lab of Artificial Intelligence, AI Institute, Shanghai Jiao Tong University（人工智能 MOE 实验室，上海交通大学人工智能学院）；Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China（宁波数字孪生研究所，东技术研究所，宁波，中国）；Ningbo Key Laboratory of Spatial Intelligence and Digital Derivative, Ningbo, China（宁波空间智能与数字衍生关键实验室，宁波，中国）；University of Science and Technology of China（中国科学技术大学）；CASIA；Tsinghua University（清华大学）
Most monocular depth sensing methods use conventionally captured images that are created without considering scene content. In contrast, animal eyes have fast mechanical motions, called saccades, that control how the scene is imaged by the fovea, where resolution is highest. In this paper, we present the SaccadeCam framework for adaptively distributing resolution onto regions of interest in the scene. Our algorithm for adaptive resolution is a self-supervised network and we demonstrate results for end-to-end learning for monocular depth estimation. We also show preliminary results with a real …
Ewha W. University（梨花女子大学）；Yonsei University（延世大学）；Korea Aerospace University（韩国航空大学）；Korea University（高丽大学）
Self-supervised monocular depth estimation has become an appealing solution to the lack of ground truth labels, but its reconstruction loss often produces over-smoothed results across object boundaries and is incapable of handling occlusion explicitly. In this paper, we propose a new approach to leverage pseudo ground truth depth maps of stereo images generated from self-supervised stereo matching methods. The confidence map of the pseudo ground truth depth map is estimated to mitigate performance degeneration by inaccurate pseudo depth maps. To cope with the prediction error of the confidence…
Nanjing University of Science and Technology（南京理工大学）
Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performance degradation when directly adopting a model trained on a fixed resolution to evaluate at other different resolutions. In this paper, we propose a resolution adaptive self-supervised monocular depth estimation method (RA-Depth) by learning the scale invariance of the scene depth. Specifically, we propose a simple yet efficient data augmentation method to generate images with arbitrary scales for the same scene. Then,…
Harbin Institute of Technology（哈尔滨工业大学）；Australian National University（澳大利亚国立大学）
Monocular depth estimation is a fundamental task in computer vision and has drawn increasing attention. Recently, some methods reformulate it as a classification-regression task to boost the model performance, where continuous depth is estimated via a linear combination of predicted probability distributions and discrete bins. In this paper, we present a novel framework called BinsFormer, tailored for the classification-regression-based depth estimation. It mainly focuses on two crucial components in the specific task: 1) proper generation of adaptive bins and 2) sufficient interaction between…
The advent of deep learning has brought an impressive advance to monocular depth estimation, e.g., supervised monocular depth estimation has been thoroughly investigated. However, the large amount of the RGB-to-depth dataset may not be always available since collecting accurate depth ground truth according to the RGB image is a time-consuming and expensive task. Although the network can be trained on an alternative dataset to overcome the dataset scale problem, the trained model is hard to generalize to the target domain due to the domain discrepancy. Adversarial domain alignment has demonstra…
University of Chinese Academy of Sciences（中国科学院大学）；Chongqing University（重庆大学）；KAUST（阿卜杜拉国王科技大学）
Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this paper, we propose an ACDNet based on the adaptively combined dilated convolution to predict the dense depth map for a monocular panoramic image. Specifically, we combine the convolution kernels with different dilations to extend the receptive field in the equirectangular projection. Meanwhile, we introduce an adaptive channel-wise fusion module to summarize the feature maps and …
East China University of Science and Technology（华东理工大学）
With the development of computational intelligence algorithms, unsupervised monocular depth and pose estimation framework, which is driven by warped photometric consistency, has shown great performance in the daytime scenario. While in some challenging environments, like night and rainy night, the essential photometric consistency hypothesis is untenable because of the complex lighting and reflection, so that the above unsupervised framework cannot be directly applied to these complex scenarios. In this paper, we investigate the problem of unsupervised monocular depth estimation in highly comp…
University of California, Los Angeles（加州大学洛杉矶分校）；Chung-Ang University（中央大学）
Supervised learning methods to infer (hypothesize) depth of a scene from a single image require costly per-pixel ground-truth. We follow a geometric approach that exploits abundant stereo imagery to learn a model to hypothesize scene structure without direct supervision. Although we train a network with stereo pairs, we only require a single image at test time to hypothesize disparity or depth. We propose a novel objective function that exploits the bilateral cyclic relationship between the left and right disparities and we introduce an adaptive regularization scheme that allows the network to…
NavInfo Europe（四维图新欧洲公司）；Eindhoven University of Technology（埃因霍温理工大学）
Self-supervised monocular depth estimation is a salient task for 3D scene understanding. Learned jointly with monocular ego-motion estimation, several methods have been proposed to predict accurate pixel-wise depth without using labeled data. Nevertheless, these methods focus on improving performance under ideal conditions without natural or digital corruptions. The general absence of occlusions is assumed even for object-specific depth estimation. These methods are also vulnerable to adversarial attacks, which is a pertinent concern for their reliable deployment in robots and autonomous drivi…
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major limitations. In this paper, we explore the learnable occlusion aware optical flow guided self-supervised depth and camera pose estimation by an adaptive cross weighted loss to address the above limitations. Firstly, we explore to train the learnable occlusion mask fused optical flow network by an occlusion-aware photometric loss with the temporally suppleme…
Monocular depth estimation (MDE) has attracted intense study due to its low cost and critical functions for robotic tasks such as localization, mapping and obstacle detection. Supervised approaches have led to great success with the advance of deep learning, but they rely on large quantities of ground-truth depth annotations that are expensive to acquire. Unsupervised domain adaptation (UDA) transfers knowledge from labeled source data to unlabeled target data, so as to relax the constraint of supervised learning. However, existing UDA approaches may not completely align the domain gap across …
Language as Prior, Vision as Calibration: Metric Scale Recovery for Monocular Depth Estimation
Hefei University of Technology, Hefei, Anhui, China（合肥工业大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, Anhui, China（人工智能研究所）；University of Science and Technology of China, Hefei, Anhui, China（中国科学技术大学）
Adaptive Depth-converted-Scale Convolution for Self-supervised Monocular Depth Estimation
School of Software, Shandong University（山东大学软件学院）；Shandong University-WeiHai Research Institute of Industrial Technology（山东大学威海工业技术研究院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；Key Laboratory of Machine Intelligence and System Control, Ministry of Education（教育部机器智能与系统控制重点实验室）；Institute of Microelectronics, Chinese Academy of Sciences（中国科学院微电子研究所）；Research Institute of Interdisciplinary Innovation, Zhejiang Lab（之江实验室跨学科创新研究院）
University of Sydney（悉尼大学）；University of Pittsburgh（匹兹堡大学）；Carnegie Mellon University（卡内基梅隆大学）
Supervised depth estimation has achieved high accuracy due to the advanced deep network architectures. Since the groundtruth depth labels are hard to obtain, recent methods try to learn depth estimation networks in an unsupervised way by exploring unsupervised cues, which are effective but less reliable than true labels. An emerging way to resolve this dilemma is to transfer knowledge from synthetic images with ground truth depth via domain adaptation techniques. However, these approaches overlook specific geometric structure of the natural images in the target domain (i.e., real data), which …
Recent advances in self-supervised learning havedemonstrated that it is possible to learn accurate monoculardepth reconstruction from raw video data, without using any 3Dground truth for supervision. However, in robotics applications,multiple views of a scene may or may not be available, depend-ing on the actions of the robot, switching between monocularand multi-view reconstruction. To address this mixed setting,we proposed a new approach that extends any off-the-shelfself-supervised monocular depth reconstruction system to usemore than one image at test time. Our method builds on astandard p…
New York University（纽约大学）；New York University Abu Dhabi（纽约大学阿布扎比分校）
Monocular depth estimation is a challenging task that aims to predict a corresponding depth map from a given single RGB image. Recent deep learning models have been proposed to predict the depth from the image by learning the alignment of deep features between the RGB image and the depth domains. In this paper, we present a novel approach, named Structure-Attentioned Memory Network, to more effectively transfer domain features for monocular depth estimation by taking into account the common structure regularities (e.g., repetitive structure patterns, planar surfaces, symmetries) in domain adap…
Simon Fraser University（西蒙菲莎大学）；Adobe Research（Adobe研究院）
Neural networks have shown great abilities in estimating depth from a single image. However, the inferred depth maps are well below one-megapixel resolution and often lack fine-grained details, which limits their practicality. Our method builds on our analysis on how the input resolution and the scene structure affects depth estimation performance. We demonstrate that there is a trade-off between a consistent scene structure and the high-frequency details, and merge low- and high-resolution estimations to take advantage of this duality using a simple depth merging network. We present a double …
Self-supervised learning of depth has been a highly studied topic of research as it alleviates the requirement of having ground truth annotations for predicting depth. Depth is learnt as an intermediate solution to the task of view synthesis, utilising warped photometric consistency. Although it gives good results when trained using stereo data, the predicted depth is still sensitive to noise, illumination changes and specular reflections. Also, occlusion can be tackled better by learning depth from a single camera. We propose ADAA, utilising depth augmentation as depth supervision for learnin…
Visual Autoregressive Modelling for Monocular Depth Estimation
Friedrich-Alexander University Erlangen-Nuremberg, Germany（埃朗根-纽伦堡弗里德里希-亚历山大大学）；Technical University of Munich, Germany（慕尼黑技术大学）；University of Surrey, United Kingdom（萨里大学）
Peking University（北京大学）；ShanghaiTech University（上海科技大学）；Baoji University of Arts and Science（宝鸡文理学院）
Besides image classification, Contrastive Language-Image Pre-training (CLIP) has accomplished extraordinary success for a wide range of vision tasks, including object-level and 3D space understanding. However, it's still challenging to transfer semantic knowledge learned from CLIP into more intricate tasks of quantified targets, such as depth estimation with geometric information. In this paper, we propose to apply CLIP for zero-shot monocular depth estimation, named DepthCLIP. We found that the patches of the input image could respond to a certain semantic distance token and then be projected…
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation
Deep Space Exploration Laboratory（深空探测实验室）；School of Information Science and Technology, University of Science and Technology of China（中国科学技术大学信息科学技术学院）；University of Science and Technology of China（中国科学技术大学）
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
Harbin Institute of Technology（哈尔滨工业大学）；City University of Hong Kong（香港城市大学）；The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）；Peng Cheng Laboratory（鹏城实验室）
Segmentation-Driven Monocular Shape from Polarization based on Physical Model
Key Laboratory of Photoelectronic Imaging Technology and System of Ministry of Education of China, School of Optics and Photonics, Beijing Institute of Technology（中国教育部光电成像技术与系统重点实验室，光学与 photonics 学院，北京理工大学）；National Key Laboratory of Scattering and Radiation, Beijing Institute of Environmental Features（散射与辐射国家重点实验室，北京环境特征研究院）
East China University of Science and Technology（华东理工大学）；Oklahoma State University（俄克拉荷马州立大学）
Monocular depth estimation is one of the fundamental tasks in environmental perception and has achieved tremendous progress in virtue of deep learning. However, the performance of trained models tends to degrade or deteriorate when employed on other new datasets due to the gap between different datasets. Though some methods utilize domain adaptation technologies to jointly train different domains and narrow the gap between them, the trained models cannot generalize to new domains that are not involved in training. To boost the transferability of depth estimation models, we propose an adversari…
Ulm University（乌尔姆大学）；DTU – Technical University of Denmark（丹麦技术大学）
Real-world perception systems in many cases build on hardware with limited resources to adhere to cost and power limitations of their carrying system. Deploying deep neural networks on resource-constrained hardware became possible with model compression techniques, as well as efficient and hardware-aware architecture design. However, model adaptation is additionally required due to the diverse operation environments. In this work, we address the problem of training deep neural networks on resource-constrained hardware in the context of visual domain adaptation. We select the task of monocular …
TATA Consultancy Services（塔塔咨询服务公司）；Queensland University of Technology（昆士兰科技大学）；Edge Hill University（边山大学）
In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. The state-of-the-art day-time depth estimation methods fail miserably when tested with night-time images due to a large domain shift between them. The usual photo metric losses used for training these networks may not work for night-time images due to the absence of uniform lighting which is commonly present in day-time images, making it a difficult problem to solve. We propose to solve …
Nagoya University（名古屋大学）；Kyoto Second Red Cross Hospital（京都第二红十字医院）；Sapporo-Minami-Sanjo Hospital（札幌南三条医院）；Sapporo-Kosei General Hospital（札幌厚生综合医院）；Keiwakai Nishioka Hospital（惠和会西冈医院）；National Institute of Informatics（国立信息学研究所）
We propose a depth estimation method from a single-shot monocular endoscopic image using Lambertian surface translation by domain adaptation and depth estimation using multi-scale edge loss. We employ a two-step estimation process including Lambertian surface translation from unpaired data and depth estimation. The texture and specular reflection on the surface of an organ reduce the accuracy of depth estimations. We apply Lambertian surface translation to an endoscopic image to remove these texture and reflections. Then, we estimate the depth by using a fully convolutional network (FCN). Duri…
No Pose Estimation? No Problem: Pose-Agnostic and Instance-Aware Test-Time Adaptation for Monocular Depth Estimation
Department of Artificial Intelligence, Kyungpook National University（人工智能系，庆北国立大学）；Department of Electrical and Computer Engineering, Queen’s University（电气与计算机工程系，皇后大学）；Department of Information and Communications Engineering, Pukyong National University（信息与通信工程系，浦项国立大学）
Self-supervised monocular depth estimation has been widely studied recently. Most of the work has focused on improving performance on benchmark datasets, such as KITTI, but has offered a few experiments on generalization performance. In this paper, we investigate the backbone networks (e.g. CNNs, Transformers, and CNN-Transformer hybrid models) toward the generalization of monocular depth estimation. We first evaluate state-of-the-art models on diverse public datasets, which have never been seen during the network training. Next, we investigate the effects of texture-biased and shape-biased re…
RANGER: A Monocular Zero-Shot Semantic Navigation Framework through Visual Contextual Adaptation
Beihang University（北京航空航天大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Hangzhou International Innovation Institute, Beihang University（北京航空航天大学杭州国际创新研究院）
MagicHOI: Leveraging 3D Priors for Accurate Hand-object Reconstruction from Short Monocular Video Clips
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）；ETH Zürich（苏黎世联邦理工学院）；Max Planck Institute for Intelligent Systems（智能系统马克斯·普朗克研究所）
University of Washington（华盛顿大学）；Pacific States Marine Fisheries Commission（太平洋各州渔业委员会）；National Oceanic and Atmospheric Administration（美国国家海洋和大气管理局）
Monocular absolute 3D fish pose estimation allows for efficient fish length measurement in the longline fisheries, where fishes are under severe deformation during the catching process. This task is challenging since it requires locating absolute 3D fish keypoints based on a short monocular video clip. Unlike related works, which either require expensive 3D ground-truth data and/or multiple-view images to provide depth information, or are limited to rigid objects, we propose a novel frame-based method to estimate the absolute 3D fish pose and fish length from a single-view 2D segmentation mask…
University of Oxford（牛津大学）；University of Warwick（华威大学）
Machine learning techniques, namely convolutional neural networks (CNN) and regression forests, have recently shown great promise in performing 6-DoF localization of monocular images. However, in most cases image-sequences, rather only single images, are readily available. To this extent, none of the proposed learning-based approaches exploit the valuable constraint of temporal smoothness, often leading to situations where the per-frame error is larger than the camera motion. In this paper we propose a recurrent model for performing 6-DoF localization of video-clips. We find that, even by cons…
Recent automotive vision work has focused almost exclusively on processing forward-facing cameras. However, future autonomous vehicles will not be viable without a more comprehensive surround sensing, akin to a human driver, as can be provided by 360° panoramic cameras. We present an approach to adapt contemporary deep network architectures developed on conventional rectilinear imagery to work on equirectangular 360° panoramic imagery. To address the lack of annotated panoramic automotive datasets availability, we adapt a contemporary automotive dataset, via style and projection transformation…
The ultimate goal for an inference model is to be robust and functional in real life applications. However, training vs. test data domain gaps often negatively affect model performance. This issue is especially critical for the monocular 3D human pose estimation problem, in which 3D human data is often collected in a controlled lab setting. In this paper, we focus on alleviating the negative effect of domain shift in both appearance and pose space for 3D human pose estimation by presenting our adapted human pose (AHuP) approach. AHuP is built upon two key components: (1) semantically aware ada…
University of Michigan（密歇根大学）；DROP lab（DROP实验室）；Department of Naval Architecture and Marine Engineering（船舶与海洋工程系）
There has been much recent interest in deep learning methods for monocular image based object pose estimation. While object pose estimation is an important problem for autonomous robot interaction with the physical world, and the application space for monocular-based methods is expansive, there has been little work on applying these methods with fisheye imaging systems. Also, little exists in the way of annotated fisheye image datasets on which these methods can be developed and tested. The research landscape is even more sparse for object detection methods applied in the underwater domain, fi…
