Central to the looming paradigm shift toward data-intensive science, machine-learning techniques are becoming increasingly important. In particular, deep learning has proven to be both a major breakthrough and an extremely powerful tool in many fields. Shall we embrace deep learning as the key to everything? Or should we resist a black-box solution? These are controversial issues within the remote-sensing community. In this article, we analyze the challenges of using deep learning for remote-sensing data analysis, review recent advances, and provide resources we hope will make deep learning in remote sensing seem ridiculously simple. More importantly, we encourage remote-sensing scientists to bring their expertise into deep learning and use it as an implicit general model to tackle unprecedented, large-scale, influential challenges, such as climate change and urbanization.

/pdf/deep-learning-in-remote-sensing-a-comprehensive-review-and-3o9ov8r19z.pdf

Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources

Standing at the paradigm shift towards data-intensive science, machine learning techniques are becoming increasingly important. In particular, as a major breakthrough in the field, deep learning has proven as an extremely powerful tool in many fields. Shall we embrace deep learning as the key to all? Or, should we resist a 'black-box' solution? There are controversial opinions in the remote sensing community. In this article, we analyze the challenges of using deep learning for remote sensing data analysis, review the recent advances, and provide resources to make deep learning in remote sensing ridiculously simple to start with. More importantly, we advocate remote sensing scientists to bring their expertise into deep learning, and use it as an implicit general model to tackle unprecedented large-scale influential challenges, such as climate change and urbanization.

/pdf/deep-learning-in-remote-sensing-a-review-3epn5qlsfr.pdf

Deep learning in remote sensing: a review

IFCNN: A general image fusion framework based on convolutional neural network

We present a comprehensive overview of the stereoscopic Intel RealSense RGBD imaging systems. We discuss these systems' mode-of-operation, functional behavior and include models of their expected performance, shortcomings, and limitations. We provide information about the systems' optical characteristics, their correlation algorithms, and how these properties can affect different applications, including 3D reconstruction and gesture recognition. Our discussion covers the Intel RealSense R200 and RS400.

Intel(R) RealSense(TM) Stereoscopic Depth Cameras

We present a comprehensive overview of the stereoscopic Intel RealSense RGBD imaging systems We discuss these systems' mode-of-operation, functional behavior and include models of their expected performance, shortcomings, and limitations We provide information about the systems' optical characteristics, their correlation algorithms, and how these properties can affect different applications, including 3D reconstruction and gesture recognition Our discussion covers the Intel RealSense R200 and the Intel RealSense D400 (formally RS400)

Intel RealSense Stereoscopic Depth Cameras

Estimating the disparity and normal direction of one pixel simultaneously, instead of only disparity, also known as 3D label methods, can achieve much higher subpixel accuracy in the stereo matching problem. However, it is extremely difficult to assign an appropriate 3D label to each pixel from the continuous label space $\mathbb {R}^{3}$ while maintaining global consistency because of the infinite parameter space. In this paper, we propose a novel algorithm called PatchMatch-based superpixel cut to assign 3D labels of an image more accurately. In order to achieve robust and precise stereo matching between local windows, we develop a bilayer matching cost, where a bottom–up scheme is exploited to design the two layers. The bottom layer is employed to measure the similarity between small square patches locally by exploiting a pretrained convolutional neural network, and then, the top layer is developed to assemble the local matching costs in large irregular windows induced by the tangent planes of object surfaces. To optimize the spatial smoothness of local assignments, we propose a novel strategy to update 3D labels. In the procedure of optimization, both segmentation information and random refinement of PatchMatch are exploited to update candidate 3D label set for each pixel with high probability of achieving lower loss. Since pairwise energy of general candidate label sets violates the submodular property of graph cut, we propose a novel multilayer superpixel structure to group candidate label sets into candidate assignments, which thereby can be efficiently fused by $\alpha $ -expansion graph cut. Extensive experiments demonstrate that our method can achieve higher subpixel accuracy in different data sets, and currently ranks first on the new challenging Middlebury 3.0 benchmark among all the existing methods.

PMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching

Cost aggregation is one of the key steps in the stereo matching problem. In order to improve aggregation accuracy, we propose a cost-aggregation method that can embed minimum spanning tree (MST)-based support region filtering into PatchMatch 3D label search rather than aggregating on fixed size patches. However, directly combining PatchMatch label search and MST filtering is not straightforward, due to the extremely high complexity. Thus, we develop multiple MST structures for cost aggregation on plenty of 3D labels, and design the tree-level random search strategy to find possible 3D labels of each pixel. Extensive experiments show that our method reaches higher accuracy than the other existing cost-aggregation and global-optimization methods such as the 1D MST, the PatchMatch and the PatchMatch Filter, and currently ranks first on the Middlebury 3.0 benchmark.

3D cost aggregation with multiple minimum spanning trees for stereo matching.

We propose an audio-driven talking-head method to generate photo-realistic talking-head videos from a single reference image. In this work, we tackle two key challenges: (i) producing natural head motions that match speech prosody, and (ii) maintaining the appearance of a speaker in a large head motion while stabilizing the non-face regions. We first design a head pose predictor by modeling rigid 6D head movements with a motion-aware recurrent neural network (RNN). In this way, the predicted head poses act as the low-frequency holistic movements of a talking head, thus allowing our latter network to focus on detailed facial movement generation. To depict the entire image motions arising from audio, we exploit a keypoint based dense motion field representation. Then, we develop a motion field generator to produce the dense motion fields from input audio, head poses, and a reference image. As this keypoint based representation models the motions of facial regions, head, and backgrounds integrally, our method can better constrain the spatial and temporal consistency of the generated videos. Finally, an image generation network is employed to render photo-realistic talking-head videos from the estimated keypoint based motion fields and the input reference image. Extensive experiments demonstrate that our method produces videos with plausible head motions, synchronized facial expressions, and stable backgrounds and outperforms the state-of-the-art.

/pdf/audio2head-audio-driven-one-shot-talking-head-generation-kfhcmqbzdp.pdf

Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion

Many gait recognition methods first partition the human gait into N-parts and then combine them to establish part-based feature representations. Their gait recognition performance is often affected by partitioning strategies, which are empirically chosen in different datasets. However, we observe that strips as the basic component of parts are agnostic against different partitioning strategies. Motivated by this observation, we present a strip-based multi-level gait recognition network, named GaitStrip, to extract comprehensive gait information at different levels. To be specific, our high-level branch explores the context of gait sequences and our low-level one focuses on detailed posture changes. We introduce a novel StriP-Based feature extractor (SPB) to learn the strip-based feature representations by directly taking each strip of the human body as the basic unit. Moreover, we propose a novel multi-branch structure, called Enhanced Convolution Module (ECM), to extract different representations of gaits. ECM consists of the Spatial-Temporal feature extractor (ST), the Frame-Level feature extractor (FL) and SPB, and has two obvious advantages: First, each branch focuses on a specific representation, which can be used to improve the robustness of the network. Specifically, ST aims to extract spatial-temporal features of gait sequences, while FL is used to generate the feature representation of each frame. Second, the parameters of the ECM can be reduced in test by introducing a structural re-parameterization technique. Extensive experimental results demonstrate that our GaitStrip achieves state-of-the-art performance in both normal walking and complex conditions.

GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework

Recent popular Role-Playing Games (RPGs) saw the great success of character auto-creation systems. The bone-driven face model controlled by continuous parameters (like the position of bones) and discrete parameters (like the hairstyles) makes it possible for users to personalize and customize in-game characters. Previous in-game character auto-creation systems are mostly image-driven, where facial parameters are optimized so that the rendered character looks similar to the reference face photo. This paper proposes a novel text-to-parameter translation method (T2P) to achieve zero-shot text-driven game character auto-creation. With our method, users can create a vivid in-game character with arbitrary text description without using any reference photo or editing hundreds of parameters manually. In our method, taking the power of large-scale pre-trained multi-modal CLIP and neural rendering, T2P searches both continuous facial parameters and discrete facial parameters in a unified framework. Due to the discontinuous parameter representation, previous methods have difficulty in effectively learning discrete facial parameters. T2P, to our best knowledge, is the first method that can handle the optimization of both discrete and continuous parameters. Experimental results show that T2P can generate high-quality and vivid game characters with given text prompts. T2P outperforms other SOTA text-to-3D generation methods on both objective evaluations and subjective evaluations.

Lincheng Li

Papers

PMSC: PatchMatch-Based Superpixel Cut for Accurate Stereo Matching

3D cost aggregation with multiple minimum spanning trees for stereo matching.

Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion

GaitStrip: Gait Recognition via Effective Strip-based Feature Representations and Multi-Level Framework

Zero-Shot Text-to-Parameter Translation for Game Character Auto-Creation