We propose a novel multi-stage depth super-resolution network, which progressively reconstructs high-resolution depth maps from explicit and implicit high-frequency features. The former are extracted by an efficient transformer processing both local and global contexts, while the latter are obtained by projecting color images into the frequency domain. Both are combined together with depth features by means of a fusion strategy within a multi-stage and multi-scale framework. Experiments on the main benchmarks, such as NYUv2, Middlebury, DIML and RGBDD, show that our approach outperforms existing methods by a large margin (~20% on NYUv2 and DIML against the contemporary work DADA, with 16x upsampling), establishing a new state-of-the-art in the guided depth super-resolution task.
Guided depth super-resolution is a practical task where a low-resolution and noisy input depth map is restored to a high-resolution version, with the help of a high-resolution RGB guide image. Existing methods usually view this task as a generalized guided filtering problem that relies on designing explicit filters and objective functions, or a dense regression problem that directly predicts the target image via deep neural networks. These methods suffer from either model capability or interpretability. Inspired by the recent progress in implicit neural representation, we propose to formulate …
Computer Vision Group, Technical University of Munich（慕尼黑工业大学计算机视觉组）；Erasmus Mundus Masters in Vision and Robotics (VIBOT)（伊拉斯谟世界计划视觉与机器人硕士项目（VIBOT））
A novel depth super-resolution approach for RGB-D sensors is presented. It disambiguates depth super-resolution through high-resolution photometric clues and, symmetrically, it disambiguates uncalibrated photometric stereo through low-resolution depth cues. To this end, an RGB-D sequence is acquired from the same viewing angle, while illuminating the scene from various uncalibrated directions. This sequence is handled by a variational framework which fits high-resolution shape and reflectance, as well as lighting, to both the low-resolution depth measurements and the high-resolution RGB ones. …
The recent success of NeRF and other related implicit neural representation methods has opened a new path for continuous image representation, where pixel values no longer need to be looked up from stored discrete 2D arrays but can be inferred from neural network models on a continuous spatial domain. Although the recent work LIIF has demonstrated that such novel approaches can achieve good performance on the arbitrary-scale super-resolution task, their upscaled images frequently show structural distortion due to the inaccurate prediction of high-frequency textures. In this work, we propose Ul…
Depth image super-resolution is an extremely challenging task due to the information loss in sub-sampling. Deep convolutional neural network have been widely applied to color image super-resolution. Quite surprisingly, this success has not been matched to depth super-resolution. This is mainly due to the inherent difference between color and depth images. In this paper, we bridge up the gap and extend the success of deep convolutional neural network to depth super-resolution. The proposed deep depth super-resolution method learns the mapping from a low-resolution depth image to a high resoluti…
Beijing Jiaotong University（北京交通大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Recently, methods for neural surface representation and rendering, for example NeuS, have shown that learning neural implicit surfaces through volume rendering is becoming increasingly popular and making good progress. However, these methods still face some challenges. Existing methods lack a direct representation of depth information, which makes object reconstruction unrestricted by geometric features, resulting in poor reconstruction of objects with texture and color features. This is because existing methods only use surface normals to represent implicit surfaces without using depth inform…
Self-supervised depth estimation has made a great success in learning depth from unlabeled image sequences. While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and scene semantics, however, is less considered. This hinders the network to better understand the real geometry of the scene, since the contextual clues, contribute not only the latent representations of scene depth, but also the straight constraints for depth map. In this paper, we leverage the two benefits by proposing the implicit and explicit semantic guid…
Tianjin University（天津大学）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；The Chinese University of Hong Kong（香港中文大学）
In self-supervised monocular depth estimation, the depth discontinuity and motion objects' artifacts are still challenging problems. Existing self-supervised methods usually utilize a single view to train the depth estimation network. Compared with static views, abundant dynamic properties between video frames are beneficial to refined depth estimation, especially for dynamic objects. In this work, we propose a novel self-supervised joint learning framework for depth estimation using consecutive frames from monocular and stereo videos. The main idea is using an implicit depth cue extractor whi…
National Tsing Hua University（国立清华大学）；MediaTek Inc.（联发科技股份有限公司）
Implicit neural representation has recently shown a promising ability in representing images with arbitrary resolutions. In this paper, we present a Local Implicit Transformer (LIT), which integrates the attention mechanism and frequency encoding technique into a local implicit image function. We design a cross-scale local attention block to effectively aggregate local features. To further improve representative power, we propose a Cascaded LIT (CLIT) that exploits multi-scale features, along with a cumulative training strategy that gradually increases the upsampling scales during training. We…
Is the center position fully capable of representing a pixel? There is nothing wrong to represent pixels with their centers in a discrete image representation, but it makes more sense to consider each pixel as the aggregation of signals from a local area in an image super-resolution (SR) context. Despite the great capability of coordinate-based implicit representation in the field of arbitrary-scale image SR, this area's nature of pixels is not fully considered. To this end, we propose integrated positional encoding (IPE), extending traditional positional encoding by aggregating frequency info…
Modern smartphones can continuously stream multi-megapixel RGB images at 60Hz, synchronized with high-quality 3D pose information and low-resolution LiDAR-driven depth estimates. During a snapshot photograph, the natural unsteadiness of the photographer's hands offers millimeter-scale variation in camera pose, which we can capture along with RGB and depth in a circular buffer. In this work we explore how, from a bundle of these measurements acquired during viewfinding, we can combine dense micro-baseline parallax cues with kilopixel LiDAR depth to distill a high-fidelity depth map. We take a t…
University of California, Berkeley（加州大学伯克利分校）；University of Toronto（多伦多大学）
Single-image super-resolution (SISR) is a canonical problem with diverse applications. Leading methods like SRGAN produce images that contain various artifacts, such as high-frequency noise, hallucinated colours and shape distortions, which adversely affect the realism of the result. In this paper, we propose an alternative approach based on an extension of the method of Implicit Maximum Likelihood Estimation (IMLE). We demonstrate greater effectiveness at noise reduction and preservation of the original colours and shapes, yielding more realistic super-resolved images.
University of Bonn（波恩大学）；Delft University of Technology（代尔夫特理工大学）
Novel view synthesis is required in many robotic applications, such as VR teleoperation and scene reconstruction. Existing methods are often too slow for these contexts, cannot handle dynamic scenes, and are limited by their explicit depth estimation stage, where incorrect depth predictions can lead to large projection errors. Our proposed method runs in real time on live streaming data and avoids explicit depth estimation by efficiently warping input images into the target frame for a range of assumed depth planes. The resulting plane sweep volume (PSV) is directly fed into our network, which…
Learning-based multi-view stereo (MVS) has by far centered around 3D convolution on cost volumes. Due to the high computation and memory consumption of 3D CNN, the resolution of output depth is often considerably limited. Different from most existing works dedicated to adaptive refinement of cost volumes, we opt to directly optimize the depth value along each camera ray, mimicking the range (depth) finding of a laser scanner. This reduces the MVS problem to ray-based depth optimization which is much more light-weight than full cost volume optimization. In particular, we propose RayMVSNet which…
SparseRecon: Neural Implicit Surface Reconstruction from Sparse Views with Feature and Depth Consistencies
School of Software, Tsinghua University（清华大学软件学院）；Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；China Telecom（中国电信）；Kuaishou Technology（快手科技）；Department of Computer Science, Wayne State University（韦恩州立大学计算机科学系）
Majority of the perception methods in robotics require depth information provided by RGB-D cameras. However, standard 3D sensors fail to capture depth of transparent objects due to refraction and absorption of light. In this paper, we introduce a new approach for depth completion of transparent objects from a single RGB-D image. Key to our approach is a local implicit neural representation built on ray-voxel pairs that allows our method to generalize to unseen objects and achieve fast inference speed. Based on this representation, we present a novel framework that can complete missing depth gi…
GEOcc: Geometrically Enhanced 3D Occupancy Network with Implicit-Explicit Depth Fusion and Contextual Self-Supervision
School of Computer Science and Technology, East China Normal University（华东师范大学计算机科学与技术学院）；School of Electronics, Information and Electrical Engineering, Shanghai Jiao Tong University（上海交通大学电子信息与电气工程学院）；School of Transportation and Traffic Engineering, Central South University（中南大学交通运输工程学院）
SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
Shandong University China；City University of Hong Kong China；Hong Kong University of Science；The University of Hong Kong China；Texas A\&M University USA；Shandong University；City University of Hong Kong；The University of Hong Kong；Texas A\&M University
Shenzhen Cloudream Technology Co., Ltd.（深圳云绘科技有限公司）；South China University of Technology（华南理工大学）；Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳））
In this paper, a novel deep-learning based framework is proposed to infer 3D human poses from a single image. Specifically, a two-phase approach is developed. We firstly utilize a generator with two branches for the extraction of explicit and implicit depth information respectively. During the training process, an adversarial scheme is also employed to further improve the performance. The implicit and explicit depth information with the estimated 2D joints generated by a widely used estimator, in the second step, are together fed into a deep 3D pose regressor for the final pose generation. Our…
Quantization has been applied to multiple domains in Deep Neural Networks (DNNs). We propose Depthwise Quantization (DQ) where $\textit{quantization}$ is applied to a decomposed sub-tensor along the $\textit{feature axis}$ of weak statistical dependence. The feature decomposition leads to an exponential increase in $\textit{representation capacity}$ with a linear increase in memory and parameter cost. In addition, DQ can be directly applied to existing encoder-decoder frameworks without modification of the DNN architecture. We use DQ in the context of Hierarchical Auto-Encoder and train end-to…
Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision
School of Remote Sensing Information Engineering, Wuhan University（遥感信息工程学院，武汉大学）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（测绘遥感信息工程国家重点实验室，武汉大学）
Sun Yat-sen University（中山大学）；National University of Defense Technology（国防科技大学）
Person re-identification (re-id) aims to match people across non-overlapping camera views. So far the RGB-based appearance is widely used in most existing works. However, when people appeared in extreme illumination or changed clothes, the RGB appearance-based re-id methods tended to fail. To overcome this problem, we propose to exploit depth information to provide more invariant body shape and skeleton information regardless of illumination and color change. More specifically, we exploit depth voxel covariance descriptor and further propose a locally rotation invariant depth shape descriptor …
School of Computing, Australian National University（澳大利亚国立大学计算学院）；School of EECS, The University of Queensland（昆士兰大学电气工程与计算机科学学院）；FreiNexus；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）
Korea Electronics Technology Institute (KETI)（韩国电子技术研究院（KETI））
We present an approach to generating 3D human models from images. The key to our framework is that we predict double-sided orthographic depth maps and color images from a single perspective projected image. Our framework consists of three networks. The first network predicts normal maps to recover geometric details such as wrinkles in the clothes and facial regions. The second network predicts shade-removed images for the front and back views by utilizing the predicted normal maps. The last multi-headed network takes both normal maps and shade-free images and predicts depth maps while selectiv…
The goal of this project is to learn a 3D shape representation that enables accurate surface reconstruction, compact storage, efficient computation, consistency for similar shapes, generalization across diverse shape categories, and inference from depth camera observations. Towards this end, we introduce Local Deep Implicit Functions (LDIF), a 3D shape representation that decomposes space into a structured set of learned implicit functions. We provide networks that infer the space decomposition and local deep implicit functions from a 3D mesh or posed depth image. During experiments, we find t…
Massachusetts Institute of Technology (MIT)（麻省理工学院）；The University of Maryland（马里兰大学）；Harvard University（哈佛大学）
Graph Neural Networks (GNNs) have been studied through the lens of expressive power and generalization. However, their optimization properties are less well understood. We take the first step towards analyzing GNN training by studying the gradient dynamics of GNNs. First, we analyze linearized GNNs and prove that despite the non-convexity of training, convergence to a global minimum at a linear rate is guaranteed under mild assumptions that we validate on real-world graphs. Second, we study what may affect the GNNs' training speed. Our results show that the training of GNNs is implicitly accel…
Incremental Joint Learning of Depth, Pose and Implicit Scene Representation on Monocular Camera in Large-scale Scenes
Institute of Medical Robotics and Department of Automation, Shanghai Jiao Tong University（上海交通大学医学机器人研究所和自动化系）；Key Laboratory of System Control and Information Processing, Ministry of Education, Shanghai（系统控制与信息处理重点实验室，教育部，上海）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）
NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising
Institute of Medical Robotics and Department of Automation, Shanghai Jiao Tong University（上海交通大学医疗机器人研究所和自动化系）；Key Laboratory of System Control and Information Processing, Ministry of Education, Shang hai 200240, China（教育部系统控制与信息处理重点实验室，上海200240，中国）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电子与电气工程学院）
We propose a novel implicit feature refinement module for high-quality instance segmentation. Existing image/video instance segmentation methods rely on explicitly stacked convolutions to refine instance features before the final prediction. In this paper, we first give an empirical comparison of different refinement strategies,which reveals that the widely-used four consecutive convolutions are not necessary. As an alternative, weight-sharing convolution blocks provides competitive performance. When such block is iterated for infinite times, the block output will eventually convergeto an equi…
Unsupervised Monocular Depth Estimation Based on Hierarchical Feature-Guided Diffusion
School of Information Science and Technology, ShanghaiTech University（信息科学与技术学院，上海科技大学）；Bionic Vision System Laboratory, State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences（生物视觉系统实验室，传感技术国家重点实验室，微系统与信息工程研究所，中国科学院）；University of Chinese Academy of Sciences（中国科学院大学）；Xiongan Institute of Innovation（雄安创新研究院）；University of Science and Technology of China（中国科学技术大学）
In this paper, we investigate a new optimization framework for multi-view 3D shape reconstructions. Recent differentiable rendering approaches have provided breakthrough performances with implicit shape representations though they can still lack precision in the estimated geometries. On the other hand multi-view stereo methods can yield pixel wise geometric accuracy with local depth predictions along viewing rays. Our approach bridges the gap between the two strategies with a novel volumetric shape representation that is implicit but parameterized with pixel depths to better materialize the sh…
National Taiwan University（国立台湾大学）；Mobile Drive Technology（移动驱动科技公司）
Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary super…
Estimating a 3D human pose has proven to be a challenging task, primarily because of the complexity of the human body joints, occlusions, and variability in lighting conditions. In this paper, we introduce a higher-order graph convolutional framework with initial residual connections for 2D-to-3D pose estimation. Using multi-hop neighborhoods for node feature aggregation, our model is able to capture the long-range dependencies between body joints. Moreover, our approach leverages residual connections, which are integrated by design in our network architecture, ensuring that the learned featur…
HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fields
University of Stuttgart（斯图加特大学）；Huawei Munich Research Center（华为慕尼黑研究中心）；Central Media Technology Institute, Huawei 2012 Laboratories（华为2012实验室中央媒体技术研究院）；Technical University of Munich（慕尼黑工业大学）
ViBA: Implicit Bundle Adjustment with Geometric and Temporal Consistency for Robust Visual Matching
GNSS Research Center, Wuhan University（武汉大学卫星导航定位技术研究中心）；Electronic Information School, Wuhan University（武汉大学电子信息学院）；Hubei Technology Innovation Center for Spatiotemporal Information and Positioning Navigation（湖北省时空信息与定位导航技术创新中心）；Hubei Luojia Laboratory（湖北珞珈实验室）
We present a simple yet effective general-purpose framework for modeling 3D shapes by leveraging recent advances in 2D image generation using CNNs. Using just a single depth image of the object, we can output a dense multi-view depth map representation of 3D objects. Our simple encoder-decoder framework, comprised of a novel identity encoder and class-conditional viewpoint generator, generates 3D consistent depth maps. Our experimental results demonstrate the two-fold advantage of our approach. First, we can directly borrow architectures that work well in the 2D image domain to 3D. Second, we …
