Search

Reconstructing the high-fidelity surface from multi-view images, especially sparse images, is a critical and practical task that has attracted widespread attention in recent years. However, existing methods are impeded by the memory constraint or the requirement of ground-truth depths and cannot recover satisfactory geometric details. To this end, we propose SuRF, a new Surface-centric framework that incorporates a new Region sparsification based on a matching Field, achieving good trade-offs between performance, efficiency and scalability. To our knowledge, this is the first unsupervised method achieving end-to-end sparsification powered by the introduced matching field, which leverages the weight distribution to efficiently locate the boundary regions containing surface. Instead of predicting an SDF value for each voxel, we present a new region sparsification approach to sparse the volume by judging whether the voxel is inside the surface region. In this way, our model can exploit higher frequency features around the surface with less memory and computational consumption. Extensive experiments on multiple benchmarks containing complex large-scale scenes show that our reconstructions exhibit high-quality details and achieve new state-of-the-art performance, i.e., 46% improvements with 80% less memory consumption. Code is available at https://github.com/prstrive/SuRF., Comment: ECCV 2024 Accepted

Electrical manipulation of spin-polarized current is highly desirable yet tremendously challenging in developing ultracompact spintronic device technology. Here we propose a scheme to realize the all-electrical manipulation of spin-polarized current in an altermagnetic bilayer. Such a bilayer system can host layer-spin locking, in which one layer hosts a spin-polarized current while the other layer hosts a current with opposite spin polarization. An out-of-plane electric field breaks the layer degeneracy, leading to a gate-tunable spin-polarized current whose polarization can be fully reversed upon flipping the polarity of the electric field. Using first-principles calculations, we show that CrS bilayer with C-type antiferromagnetic exchange interaction exhibits a hidden layer-spin locking mechanism that enables the spin polarization of the transport current to be electrically manipulated via the layer degree of freedom. We demonstrate that sign-reversible spin polarization as high as 87% can be achieved at room temperature. This work presents the pioneering concept of layer-spintronics which synergizes altermagnetism and bilayer stacking to achieve efficient electrical control of spin., Comment: 20 pages, 5 figures

Recent years have witnessed substantial advancements in the field of 3D reconstruction from 2D images, particularly following the introduction of the neural radiance field (NeRF) technique. However, reconstructing a 3D high dynamic range (HDR) radiance field, which aligns more closely with real-world conditions, from 2D multi-exposure low dynamic range (LDR) images continues to pose significant challenges. Approaches to this issue fall into two categories: grid-based and implicit-based. Implicit methods, using multi-layer perceptrons (MLP), face inefficiencies, limited solvability, and overfitting risks. Conversely, grid-based methods require significant memory and struggle with image quality and long training times. In this paper, we introduce Gaussian Splatting-a recent, high-quality, real-time 3D reconstruction technique-into this domain. We further develop the High Dynamic Range Gaussian Splatting (HDR-GS) method, designed to address the aforementioned challenges. This method enhances color dimensionality by including luminance and uses an asymmetric grid for tone-mapping, swiftly and precisely converting pixel irradiance to color. Our approach improves HDR scene recovery accuracy and integrates a novel coarse-to-fine strategy to speed up model convergence, enhancing robustness against sparse viewpoints and exposure extremes, and preventing local optima. Extensive testing confirms that our method surpasses current state-of-the-art techniques in both synthetic and real-world scenarios. Code will be released at \url{https://github.com/WuJH2001/HDRGS}

The role of the delta isobar degrees of freedom in nucleon-nucleon scattering is revisited. We attempt to understand why the dimensionally regularized two-pion exchanges with the explicit delta isobar is much stronger than the ones with spectral function regularization. When the cutoff value of spectral function regularization is varied, the isoscalar central component exhibits a rather large cutoff variation. This reveals a surprisingly large numerical factor of the deltaful two-pion exchange potentials. The power counting is adjusted accordingly and we discuss the results and how to improve upon this finding., Comment: 16 pages, 6 figures

The discovery of interface-enhanced superconductivity in single-layer FeSe/oxides has generated intensive research interests. Beyond the family of FeSe interfaced with various TiO$_2$ terminated oxides, high pairing temperature up to 80~K has been recently observed in FeSe interfaced with FeO$_x$-terminated LaFeO$_3$. Here we successfully extend the FeSe/FeO$_x$ superconducting interface to FeSe/NdFeO$_3$, by constructing 1uc-FeSe/6uc-NdFeO$_3$/Nb:SrTiO$_3$ heterostructures. Intriguingly, well-annealed FeSe/NdFeO$_3$ exhibits a low doping level of 0.038$\sim$0.046 ~e$^-/$Fe which deviates universally magic doping level (0.10$\sim$0.12 e$^-/\rm{Fe}$) and provides a new playground for studying the FeSe/oxide interface in the low electron-doped regime. Comparing it with thick FeSe films at the comparable electron doping level induced by surface potassium dosing, FeSe/NdFeO$_3$ shows a larger superconducting gap and the absence of a nematic gap, indicating an enhancement of the superconductivity and suppression of nematicity by the FeSe/FeO$_x$ interface. These results not only expand the FeSe/FeO$_x$ superconducting family but also enrich the current understanding on the roles of the oxide interface., Comment: 8 pages, 4 figures

Monolayer FeSe/TiO$_x$ and FeSe/FeO$_x$ interfaces exhibit significant superconductivity enhancement compared to bulk FeSe, with interfacial electron-phonon coupling (EPC) playing a crucial role. However, the reduced dimensionality in monolayer FeSe, which may drive superconducting fluctuations, complicates the understanding of the enhancement mechanisms. Here we construct a new superconducting interface: monolayer FeSe/SrVO$_3$/SrTiO$_3$, in which the itinerant electrons of highly metallic SrVO$_3$ films can screen all the high-energy Fuchs-Kliewer phonons, including those of SrTiO$_3$, making it the first FeSe/oxide system with screened interfacial EPC while maintaining the monolayer FeSe thickness. Despite comparable doping levels, the heavily electron-doped monolayer FeSe/SrVO$_3$ exhibits a lower pairing temperature ($T_\mathrm{g}$ $\sim$ 48 K) than FeSe/SrTiO$_3$ and FeSe/LaFeO$_3$. Our findings disentangle the contributions of interfacial EPC from dimensionality on enhancing $T_\mathrm{g}$ in FeSe/oxide interfaces, underscoring the importance of interfacial EPC in $T_\mathrm{g}$ enhancement. This FeSe/VO$_x$ interface also provides a platform for studying the interfacial superconductivity., Comment: Published in Nano Letters, 11 pages, 4 figures, 1 table

We discuss renormalization of chiral nuclear forces in the 3P0 channel of N N scattering at next- to-next-to leading order (N2LO) if the one-pion exchange is treated nonperturbatively at leading order. The matrix elements of the subleading contact potentials become nearly dependent of each other for the so-called exceptional ultraviolet momentum cutoff, making it difficult to determine the strengths of those contact potentials from the empirical phase shifts, as reported in Ref. [1]. We argue that this issue can be resolved by adjusting the strategy by which the low-energy constants are deduced from the data, thus making those exceptional cutoffs amenable to chiral effective field theory.

Combining the signed distance function (SDF) and differentiable volume rendering has emerged as a powerful paradigm for surface reconstruction from multi-view images without 3D supervision. However, current methods are impeded by requiring long-time per-scene optimizations and cannot generalize to new scenes. In this paper, we present GenS, an end-to-end generalizable neural surface reconstruction model. Unlike coordinate-based methods that train a separate network for each scene, we construct a generalized multi-scale volume to directly encode all scenes. Compared with existing solutions, our representation is more powerful, which can recover high-frequency details while maintaining global smoothness. Meanwhile, we introduce a multi-scale feature-metric consistency to impose the multi-view consistency in a more discriminative multi-scale feature space, which is robust to the failures of the photometric consistency. And the learnable feature can be self-enhanced to continuously improve the matching accuracy and mitigate aggregation ambiguity. Furthermore, we design a view contrast loss to force the model to be robust to those regions covered by few viewpoints through distilling the geometric prior from dense input to sparse input. Extensive experiments on popular benchmarks show that our model can generalize well to new scenes and outperform existing state-of-the-art methods even those employing ground-truth depth supervision. Code is available at https://github.com/prstrive/GenS., Comment: NeurIPS 2023 Accepted

A knowledge search is a key process for inventions. However, there is inadequate quantitative modeling of dynamic knowledge search processes and associated search costs. In this study, agent-based and complex network methodologies were proposed to quantitatively describe the dynamic process of knowledge search for actual inventions. Prior knowledge networks (PKNs), the search space of historical patents, were constructed, representative search rules were formulated for R&D agents, and measures for knowledge search cost were designed to serve as search objectives. Simulation results in the field of photolithographic technology show that search costs differ significantly with different search rules. Familiarity and Degree rules significantly outperform BFS, DFS and Recency rules in terms of knowledge search costs, and are less affected by the size and density of PKNs. Interestingly, there is no significant correlation between the mean and variance of search costs and patent value, indicating that high-value patents are not particularly difficult to obtain. The implications for innovation theories and R&D practices are drawn from the models and results., Comment: 16 pages, 8 figures

Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper introduces a novel framework that makes fundamental contributions to both questions. Unlike leveraging images from 2D diffusion models for training, we propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Images from video generative models are more suitable for multi-view generation because the underlying network architecture that generates them employs a temporal module to enforce frame consistency. Moreover, the video data sets used to train these models are abundant and diverse, leading to a reduced train-finetuning domain gap. To enhance multi-view consistency, we introduce a 3D-Aware Denoising Sampling, which first employs a feed-forward reconstruction module to get an explicit global 3D model, and then adopts a sampling strategy that effectively involves images rendered from the global 3D model into the denoising sampling loop to improve the multi-view consistency of the final images. As a by-product, this module also provides a fast way to create 3D assets represented by 3D Gaussians within a few seconds. Our approach can generate 24 dense views and converges much faster in training than state-of-the-art approaches (4 GPU hours versus many thousand GPU hours) with comparable visual quality and consistency. By further fine-tuning, our approach outperforms existing state-of-the-art methods in both quantitative metrics and visual effects. Our project page is aigc3d.github.io/VideoMV., Comment: Project page: aigc3d.github.io/VideoMV/

The rapid development of deep learning techniques, improved computational power, and the availability of vast training data have led to significant advancements in pre-trained models and large language models (LLMs). Pre-trained models based on architectures such as BERT and Transformer, as well as LLMs like ChatGPT, have demonstrated remarkable language capabilities and found applications in Software engineering. Software engineering tasks can be divided into many categories, among which generative tasks are the most concern by researchers, where pre-trained models and LLMs possess powerful language representation and contextual awareness capabilities, enabling them to leverage diverse training data and adapt to generative tasks through fine-tuning, transfer learning, and prompt engineering. These advantages make them effective tools in generative tasks and have demonstrated excellent performance. In this paper, we present a comprehensive literature review of generative tasks in SE using pre-trained models and LLMs. We accurately categorize SE generative tasks based on software engineering methodologies and summarize the advanced pre-trained models and LLMs involved, as well as the datasets and evaluation metrics used. Additionally, we identify key strengths, weaknesses, and gaps in existing approaches, and propose potential research directions. This review aims to provide researchers and practitioners with an in-depth analysis and guidance on the application of pre-trained models and LLMs in generative tasks within SE.

Antiferromagnetic spintronics have attracted wide attention due to its great potential in constructing ultra-dense and ultra-fast antiferromagnetic memory that suits modern high-performance information technology. The electrical 180o switching of N\'eel vector is a long-term goal for developing electrical-controllable antiferromagnetic memory with opposite N\'eel vectors as binary "0" and "1". However, the state-of-art antiferromagnetic switching mechanisms have long been limited for 90o or 120o switching of N\'eel vector, which unavoidably require multiple writing channels that contradicts ultra-dense integration. Here, we propose a deterministic switching mechanism based on spin-orbit torque with asymmetric energy barrier, and experimentally achieve electrical 180o switching of spin-splitting antiferromagnet Mn5Si3. Such a 180o switching is read out by the N\'eel vector-induced anomalous Hall effect. Based on our writing and readout methods, we fabricate an antiferromagnet device with electrical-controllable high and low resistance states that accomplishes robust write and read cycles. Besides fundamental advance, our work promotes practical spin-splitting antiferromagnetic devices based on spin-splitting antiferromagnet., Comment: 19 pages, 4 figures

Device-free wireless sensing attracts enormous attentions since it senses the environment without additional devices. While cellular signals are good opportunistic radio sources, the influence of inter-cell interference (ICI) on wireless sensing has not been adequately addressed. In this letter, we first investigate the cause of ICI and its impact on wireless sensing. Then we propose an ICI-free channel estimation method by reconstructing the broadcast signals of adjacent cells and solving simultaneous equations. Wireless gesture recognition can be greatly benefited by ICI mitigation. Finally, we build a prototype system to receive the commercial 4G-LTE signals, and demonstrate the accuracies of wireless gesture recognition under various conditions.

Most theoretical analysis for lifetime distribution explains origins of specific distribution based on independent failure. We develop a unified framework encompassing different lifetime distribution for failure-coupled network systems. We find three types of system lifetime distributions emerged from competence between system size N and failure coupling strength $\phi$. System lifetime distribution can be describe by modified Weibull model, which degenerates into Gompertz model when N dominates and exponential distribution when $\phi$ dominates. We derive asymptotic lifetime distribution. Specially, we derive a fundamental equation of thermodynamics for failure-coupled systems. Our study will help design highly reliable systems.

IMPORTANCE The response effectiveness of different large language models (LLMs) and various individuals, including medical students, graduate students, and practicing physicians, in pediatric ophthalmology consultations, has not been clearly established yet. OBJECTIVE Design a 100-question exam based on pediatric ophthalmology to evaluate the performance of LLMs in highly specialized scenarios and compare them with the performance of medical students and physicians at different levels. DESIGN, SETTING, AND PARTICIPANTS This survey study assessed three LLMs, namely ChatGPT (GPT-3.5), GPT-4, and PaLM2, were assessed alongside three human cohorts: medical students, postgraduate students, and attending physicians, in their ability to answer questions related to pediatric ophthalmology. It was conducted by administering questionnaires in the form of test papers through the LLM network interface, with the valuable participation of volunteers. MAIN OUTCOMES AND MEASURES Mean scores of LLM and humans on 100 multiple-choice questions, as well as the answer stability, correlation, and response confidence of each LLM. RESULTS GPT-4 performed comparably to attending physicians, while ChatGPT (GPT-3.5) and PaLM2 outperformed medical students but slightly trailed behind postgraduate students. Furthermore, GPT-4 exhibited greater stability and confidence when responding to inquiries compared to ChatGPT (GPT-3.5) and PaLM2. CONCLUSIONS AND RELEVANCE Our results underscore the potential for LLMs to provide medical assistance in pediatric ophthalmology and suggest significant capacity to guide the education of medical students., Comment: 6 figures, 1 table

This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments., Comment: 11 pages, 4 figures, accepted at ICCV 2023 UNCV workshop

The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.

Consider the eigenvalue problem of a linear second order elliptic operator: \begin{equation} \nonumber -D\Delta \varphi -2\alpha\nabla m(x)\cdot \nabla\varphi+V(x)\varphi=\lambda\varphi\ \ \hbox{ in }\Omega, \end{equation} complemented by the Dirichlet boundary condition or the following general Robin boundary condition: $$ \frac{\partial\varphi}{\partial n}+\beta(x)\varphi=0 \ \ \hbox{ on }\partial\Omega, $$ where $\Omega\subset\mathbb{R}^N (N\geq1)$ is a bounded smooth domain, $n(x)$ is the unit exterior normal to $\partial\Omega$ at $x\in\partial\Omega$, $D>0$ and $\alpha>0$ are, respectively, the diffusion and advection coefficients, $m\in C^2(\overline\Omega),\,V\in C(\overline\Omega)$, $\beta\in C(\partial\Omega)$ are given functions, and $\beta$ allows to be positive, sign-changing or negative. In \cite{PZZ2019}, the asymptotic behavior of the principal eigenvalue of the above eigenvalue problem as $D\to0$ or $D\to\infty$ was studied. In this paper, when $N\geq2$, under proper conditions on the advection function $m$, we establish the asymptotic behavior of the principal eigenvalue as $\alpha\to\infty$, and when $N=1$, we obtain a complete characterization for such asymptotic behavior provided $m'$ changes sign at most finitely many times. Our results complement or improve those in \cite{BHN2005,CL2008,PZ2018} and also partially answer some questions raised in \cite{BHN2005}., Comment: 36 pages. Comments are welcome

This paper addresses the problem of traversing through unknown, tilted, and narrow gaps for quadrotors using Deep Reinforcement Learning (DRL). Previous learning-based methods relied on accurate knowledge of the environment, including the gap's pose and size. In contrast, we integrate onboard sensing and detect the gap from a single onboard camera. The training problem is challenging for two reasons: a precise and robust whole-body planning and control policy is required for variable-tilted and narrow gaps, and an effective Sim2Real method is needed to successfully conduct real-world experiments. To this end, we propose a learning framework for agile gap traversal flight, which successfully trains the vehicle to traverse through the center of the gap at an approximate attitude to the gap with aggressive tilted angles. The policy trained only in a simulation environment can be transferred into different domains with fine-tuning while maintaining the success rate. Our proposed framework, which integrates onboard sensing and a neural network controller, achieves a success rate of 84.51% in real-world experiments, with gap orientations up to 60deg. To the best of our knowledge, this is the first paper that performs the learning-based variable-tilted narrow gap traversal flight in the real world, without prior knowledge of the environment.

The emergent superconductivity at the LaAlO3/KTaO3 interfaces exhibits a mysterious dependence on the KTaO3 crystallographic orientations. Here we show, by soft X-ray angle-resolved photoemission spectroscopy, that the interfacial superconductivity is contributed by mobile electrons with unexpected quasi-three-dimensional character, beyond the "two-dimensional electron gas" scenario in describing oxide interfaces. At differently-oriented interfaces, the quasi-three-dimensional electron gas ubiquitously exists and spatially overlaps with the small q Fuchs-Kliewer surface phonons. Intriguingly, electrons and the Fuchs-Kliewer phonons couple with different strengths depending on the interfacial orientations, and the stronger coupling correlates with the higher superconducting transition temperature. Our results provide a natural explanation for the orientation-dependent superconductivity, and the first evidence that interfacial orientations can affect electron-phonon coupling strength over several nanometers, which may have profound implications for the applications of oxide interfaces in general.

In this paper, we are concerned with two SIS epidemic reaction-diffusion models with mass action infection mechanism of the form $SI$, and study the spatial profile of population distribution as the movement rate of the infected individuals is restricted to be small. For the model with a constant total population number, our results show that the susceptible population always converges to a positive constant which is indeed the minimum of the associated risk function, and the infected population either concentrates at the isolated highest-risk points or aggregates only on the highest-risk intervals once the highest-risk locations contain at least one interval. In sharp contrast, for the model with a varying total population number which is caused by the recruitment of the susceptible individuals and death of the infected individuals, our results reveal that the susceptible population converges to a positive function which is non-constant unless the associated risk function is constant, and the infected population may concentrate only at some isolated highest-risk points, or aggregate at least in a neighborhood of the highest-risk locations or occupy the whole habitat, depending on the behavior of the associated risk function and even its smoothness at the highest-risk locations. Numerical simulations are performed to support and complement our theoretical findings., Comment: All comments are welcomed. 29 pages,16 figures

With the wide application of stereo images in various fields, the research on stereo image compression (SIC) attracts extensive attention from academia and industry. The core of SIC is to fully explore the mutual information between the left and right images and reduce redundancy between views as much as possible. In this paper, we propose DispSIC, an end-to-end trainable deep neural network, in which we jointly train a stereo matching model to assist in the image compression task. Based on the stereo matching results (i.e. disparity), the right image can be easily warped to the left view, and only the residuals between the left and right views are encoded for the left image. A three-branch auto-encoder architecture is adopted in DispSIC, which encodes the right image, the disparity map and the residuals respectively. During training, the whole network can learn how to adaptively allocate bitrates to these three parts, achieving better rate-distortion performance at the cost of a lower disparity map bitrates. Moreover, we propose a conditional entropy model with aligned cross-view priors for SIC, which takes the warped latents of the right image as priors to improve the accuracy of the probability estimation for the left image. Experimental results demonstrate that our proposed method achieves superior performance compared to other existing SIC methods on the KITTI and InStereo2K datasets both quantitatively and qualitatively., Comment: 10 pages, 8 figures, published to ACM Multimedia 2022

Renormalization of proton-proton fusion is studied in the framework of chiral effective field theory. Strict perturbative treatment of subleading corrections is applied in the analysis. Possible enhancement of two-nucleon contact axial current operators is the focus of the study. We find evidence that supports a previous proposal in the literature to promote one of the contact axial current operators., Comment: Matches the published version

Layer-polarized anomalous Hall effect (LP-AHE) is an attractive phenomenon in condensed-matter physics from the standpoints of both fundamental interest and device applications. The current LP-AHE research is based on the extrinsic paradigm of using external electric fields, in which the generation and control of LP-AHE are not straightforward. Here, we propose a novel mechanism that realizes intrinsic LP-AHE in bilayer lattices, through the mediation of sliding physics and Berry curvature. Moreover, this mechanism could render the LP-AHE in a controllable and reversable fashion. We analyze the symmetry requirements for a system to host such intrinsic LP-AHE. Its validity is further demonstrated in a real material of bilayer MnBi2Te4. By stacking with broken inversion symmetry, the layer-locked Berry curvature enables the intrinsic LP-AHE in bilayer MnBi2Te4, and the switchable control of its LP-AHE is achieved by sliding ferroelectricity. Our work opens a significant new direction for LP-AHE and two-dimensional (2D) materials research.

We calculate the deuteron charge, electric quadrupole, and magnetic form factors up to next-to-next-to-leading order in chiral effective field theory, treating subleading corrections, especially that of chiral nuclear forces, in perturbation theory. We examine the power counting based on naive dimensional analysis by investigating the ultraviolet cutoff variation of these form factors. We find that the N${}^2$LO magnetic form factor shows significant cutoff dependence, suggesting the contact current operator responsible be enhanced. After promotion to N${}^2$LO, it indeed renormalizes the magnetic form factor. This is in agreement with a previous work based on renormalization-group analysis. For the charge and quadrupole moments, perturbative calculation allows us to study how they scale with multiple low-energy parameters such as the pion mass, deuteron binding momentum, and momentum transfer., Comment: Matches the published version

Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent shortcomings, e.g., regression methods tend to overfit due to the indirect learning cost volume, and classification methods cannot directly infer the exact depth due to its discrete prediction. In this paper, we propose a novel representation, termed Unification, to unify the advantages of regression and classification. It can directly constrain the cost volume like classification methods, but also realize the sub-pixel depth prediction like regression methods. To excavate the potential of unification, we design a new loss function named Unified Focal Loss, which is more uniform and reasonable to combat the challenge of sample imbalance. Combining these two unburdened modules, we present a coarse-to-fine framework, that we call UniMVSNet. The results of ranking first on both DTU and Tanks and Temples benchmarks verify that our model not only performs the best but also has the best generalization ability., Comment: CVPR 2022 Accepted