Recent advancements in language models have demonstrated its capacity of context understanding and generative representations. Leveraged by these developments, we propose a novel multimodal trajectory predictor based on a vision-language model, named VLMTraj, which fully takes advantage of the prior knowledge of multimodal large language models and the human-like reasoning across diverse modality information. The key idea of our model is to reframe the trajectory prediction task into a visual question answering format, using historical information as context and instructing the language model to make predictions in a conversational manner. Specifically, we transform all the inputs into a natural language style: historical trajectories are converted into text prompts, and scene images are described through image captioning. Additionally, visual features from input images are also transformed into tokens via a modality encoder and connector. The transformed data is then formatted to be used in a language model. Next, in order to guide the language model in understanding and reasoning high-level knowledge, such as scene context and social relationships between pedestrians, we introduce an auxiliary multi-task question and answers. For training, we first optimize a numerical tokenizer with the prompt data to effectively separate integer and decimal parts, allowing us to capture correlations between consecutive numbers in the language model. We then train our language model using all the visual question answering prompts. During model inference, we implement both deterministic and stochastic prediction methods through beam-search-based most-likely prediction and temperature-based multimodal generation. Our VLMTrajvalidates that the language-based model can be a powerful pedestrian trajectory predictor, and outperforms existing numerical-based predictor methods. Extensive experiments show that VLMTrajcan successfully understand social relationships and accurately extrapolate the multimodal futures on public pedestrian trajectory prediction benchmarks.

Accurate precipitation forecasting is crucial for early warnings of disasters, such as floods and landslides. Traditional forecasts rely on ground-based radar systems, which are space-constrained and have high maintenance costs. Consequently, most developing countries depend on a global numerical model with low resolution, instead of operating their own radar systems. To mitigate this gap, we propose the Neural Precipitation Model (NPM), which uses global-scale geostationary satellite imagery. NPM predicts precipitation for up to six hours, with an update every hour. We input three key channels to discriminate rain clouds: infrared radiation (at a wavelength of 10.5 µm), upper- (6.3 µm), and lower- (7.3 µm) level water vapor channels. Additionally, NPM introduces positional encoders to capture seasonal and temporal patterns, reflecting variations in precipitation. Our experimental results demonstrate that NPM can predict rainfall in real-time with a resolution of 2 km.

Modeling and reproducing crowd behaviors are important in various domains including psychology, robotics, transport engineering and virtual environments. Conventional methods have focused on synthesizing momentary scenes, which have difficulty in replicating the continuous nature of real-world crowds. In this paper, we introduce a novel method for automatically generating continuous, realistic crowd trajectories with heterogeneous behaviors and interactions among individuals. We first design a crowd emitter model. To do this, we obtain spatial layouts from single input images, including a segmentation map, appearance map, population density map and population probability, prior to crowd generation. The emitter then continually places individuals on the time-line by assigning independent behavior characteristics such as agents’ type, pace, and start/end positions using diffusion models. Next, our crowd simulator produces their long-term locomotions. To simulate diverse actions, it can augment their behaviors based on a Markov chain. As a result, our overall framework populates the scenes with heterogeneous crowd behaviors by alternating between the proposed emitter and simulator. Note that all the components in the proposed framework are user-controllable. Lastly, we propose a benchmark protocol to evaluate the realism and quality of the generated crowds in terms of the scene-level population dynamics and the individual-level trajectory accuracy. We demonstrate that our approach effectively models diverse crowd behavior patterns and generalizes well across different geographical environments. Code is publicly available at https://github.com/InhwanBae/CrowdES.

A concept of light-fields computed from multiple view images on regular grids has proven its benefit for scene representations, and supported realistic renderings of novel views and photographic effects such as refocusing and shallow depth of field. In spite of its effectiveness of light flow computations, obtaining light fields requires either computational costs or specialized devices like a bulky camera setup and a specialized microlens array. In an effort to broaden its benefit and applicability, in this paper, we propose a novel view synthesis method for light field generation from only single images, named inverse image-based rendering. Unlike previous attempts to implicitly rebuild 3D geometry or to explicitly represent objective scenes, our method reconstructs light flows in a space from image pixels, which behaves in the opposite way to image-based rendering. To accomplish this, we design a neural rendering pipeline to render a target ray in an arbitrary viewpoint. Our neural renderer first stores the light flow of source rays from the input image, then computes the relationships among them through cross-attention, and finally predicts the color of the target ray based on these relationships. After the rendering pipeline generates the first novel view from a single input image, the generated out-of-view contents are updated to the set of source rays. This procedure is iteratively performed while ensuring the consistent generation of occluded contents. We demonstrate that our inverse image-based rendering works well with various challenging datasets without any retraining or finetuning after once trained on synthetic dataset, and outperforms relevant state-of-the-art novel view synthesis methods.

Different from color correction and transfer, color grading involves adjusting colors for artistic or storytelling purposes in a video, which is used to establish a specific look or mood. However, due to the complexity of the process and the need for specialized editing skills, video color grading remains primarily the domain of professional colorists. In this paper, we present a reference-based video color grading framework. Our key idea is explicitly generating a look-up table (LUT) for color attribute alignment between reference scenes and input video via a diffusion model. As a training objective, we enforce that high-level features of the reference scenes like look, mood, and emotion should be similar to that of the input video. Our LUT-based approach allows for color grading without any loss of structural details in the whole video frames as well as achieving fast inference. We further build a pipeline to incorporate a user-preference via text prompts for low-level feature enhancement such as contrast and brightness, etc. Experimental results, including extensive user studies, demonstrate the effectiveness of our approach for video color grading. Codes are publicly available at https://github.com/seunghyuns98/VideoColorGrading.

Accurate video forecasting enables autonomous vehicles to anticipate hazards, robotics and surveillance systems to predict human intent, and environmental models to issue timely warnings for extreme weather events. However, existing methods remain limited: transformers rely on global attention with quadratic complexity, making them impractical for high-resolution, long-horizon video prediction, while convolutional and recurrent networks suffer from short-range receptive fields and vanishing gradients, losing key information over extended sequences. To overcome these challenges, we introduce VideoTitans, the first architecture to adapt the gradient-driven Titans memory—originally designed for language modelling to video prediction. VideoTitans integrates three core ideas: (i) a sliding-window attention core that scales linearly with sequence length and spatial resolution, (ii) an episodic memory that dynamically retains only informative tokens based on a gradient-based surprise signal, and (iii) a small set of persistent tokens encoding task-specific priors that stabilize training and enhance generalization. Extensive experiments on Moving-MNIST, Human3.6M, TrafficBJ and WeatherBench benchmarks show that VideoTitans consistently reduces computation (FLOPs) and achieves competitive visual fidelity compared to state-of-the-art recurrent, convolutional, and efficient-transformer methods. Comprehensive ablations confirm that each proposed component contributes significantly.

Language models have demonstrated impressive ability in context understanding and generative performance. Inspired by the recent success of language foundation models, in this paper, we propose LMTraj (Language-based Multimodal Trajectory predictor), which recasts the trajectory prediction task into a sort of question-answering problem. Departing from traditional numerical regression models, which treat the trajectory coordinate sequence as continuous signals, we consider them as discrete signals like text prompts. Specially, we first transform an input space for the trajectory coordinate into the natural language space. Here, the entire timeseries trajectories of pedestrians are converted into a text prompt, and scene images are described as text information through image captioning. The transformed numerical and image data are then wrapped into the question-answering template for use in a language model. Next, to guide the language model in understanding and reasoning high-level knowledge, such as scene context and social relationships between pedestrians, we introduce an auxiliary multi-task question and answering. We then train a numerical tokenizer with the prompt data. We encourage the tokenizer to separate the integer and decimal parts well, and leverage it to capture correlations between the consecutive numbers in the language model. Lastly, we train the language model using the numerical tokenizer and all of the question-answer prompts. Here, we propose a beam-search-based most-likely prediction and a temperature-based multimodal prediction to implement both deterministic and stochastic inferences. Applying our LMTraj, we show that the language-based model can be a powerful pedestrian trajectory predictor, and outperforms existing numerical-based predictor methods. Extensive experiments show that our LMTraj can successfully understand social relationships and accurately extrapolate the multimodal futures on the public pedestrian trajectory prediction benchmark. Code is publicly available at https://github.com/inhwanbae/LMTrajectory.

There are five types of trajectory prediction tasks: deterministic, stochastic, domain adaptation, momentary observation, and few-shot. These associated tasks are defined by various factors, such as the length of input paths, data split and pre-processing methods. Interestingly, even though they commonly take sequential coordinates of observations as input and infer future paths in the same coordinates as output, designing specialized architectures for each task is still necessary. For the other task, generality issues can lead to sub-optimal performances. In this paper, we propose SingularTrajectory, a diffusion-based universal trajectory prediction framework to reduce the performance gap across the five tasks. The core of SingularTrajectory is to unify a variety of human dynamics representations on the associated tasks. To do this, we first build a Singular space to project all types of motion patterns from each task into one embedding space. We next propose an adaptive anchor working in the Singular space. Unlike traditional fixed anchor methods that sometimes yield unacceptable paths, our adaptive anchor enables correct anchors, which are put into a wrong location, based on a traversability map. Finally, we adopt a diffusion-based predictor to further enhance the prototype paths using a cascaded denoising process. Our unified framework ensures the generality across various benchmark settings such as input modality, and trajectory lengths. Extensive experiments on five public benchmarks demonstrate that SingularTrajectory substantially outperforms existing models, highlighting its effectiveness in estimating general dynamics of human movements. Code is publicly available at https://github.com/inhwanbae/SingularTrajectory.

Most domain adaptation (DA) methods are based on either a convolutional neural networks (CNNs) or a vision transformers (ViTs). They align the distribution differences between domains as encoders without considering their unique characteristics. For instance, ViT excels in accuracy due to its superior ability to capture global representations, while CNN has an advantage in capturing local representations. This fact has led us to design a hybrid method to fully take advantage of both ViT and CNN, called Explicitly Class-specific Boundaries (ECB). ECB learns CNN on ViT to combine their distinct strengths. In particular, we leverage ViT's properties to explicitly find class-specific decision boundaries by maximizing the discrepancy between the out-puts of the two classifiers to detect target samples far from the source support. In contrast, the CNN encoder clusters target features based on the previously defined class-specific boundaries by minimizing the discrepancy between the prob-abilities of the two classifiers. Finally, ViT and CNN mutually exchange knowledge to improve the quality of pseudo labels and reduce the knowledge discrepancies of these models. Compared to conventional DA methods, our ECB achieves superior performance, which verifies its effectiveness in this hybrid model. The project website can be found here.

Dense depth maps have been used as a key element of visual perception tasks. There have been tremendous efforts to enhance the depth quality, ranging from optimization-based to learning-based methods. Despite the remarkable progress for a long time, their applicability in the real world is limited due to systematic measurement biases such as density, sensing pattern, and scan range. It is well-known that the biases make it difficult for these methods to achieve their generalization. We observe that learning a joint representation for input modalities (e.g., images and depth), which most recent methods adopt, is sensitive to the biases. In this work, we disentangle those modalities to mitigate the biases with prompt engineering. For this, we design a novel depth prompt module to allow the desirable feature representation according to new depth distributions from either sensor types or scene configurations. Our depth prompt can be embedded into foundation models for monocular depth estimation. Through this embedding process, our method helps the pretrained model to be free from restraint of depth scan range and to provide absolute scale depth maps. We demonstrate the effectiveness of our method through extensive evaluations. Source code is publicly available at https://github.com/JinhwiPark/DepthPrompting.

Since the widespread availability of cameras, black-and-white (BW)photography has been a popular choice for artistic and aesthetic expression. It highlights the main subject in varying tones of gray, creating various effects such as drama and contrast. However, producing BW photog-raphy often demands high-end cameras or photographic editing from experts. Even the experts prefer different styles depending on the subject or even the same subject when taking grayscale photos or converting color images to BW. It is thus questionable which approach is better. To imitate the artistic values of decolorized images, this paper introduces a deep metric learning framework with a novel subject-style specified proxy and a large-scale BW dataset. Our proxy-based decolorization utilizes a hierar-chical proxy-based loss and a hierarchical bilateral grid network to mimic the experts' retouching scheme. The proxy-based loss captures both expert-discriminative and class-sharing characteristics, while the hierarchical bilateral grid network enables imitating spatially-variant retouching by considering both global and local scene contexts. Our dataset, including color and BW images edited by three experts, demonstrates the scalability of our method, which can be further enhanced by constructing additional proxies from any set of BW photos like Internet downloaded figures. Our Experiments show that our framework successfully produce visually-pleasing BW images from color ones, as evaluated by user preference with respect to artistry and aesthetics. Code and dataset are publicly available at https://github.com/seunghyuns98IDecolorization.

Estimating neural radiance fields (NeRFs) is able to generate novel views of a scene from known imagery. Recent approaches have afforded dramatic progress on small bounded regions of the scene. For an unbounded scene where cameras point in any direction and contents exist at any distance, certain mapping functions are used to represent it within a bounded space, yet they either work in object-centric scenes or focus on objects close to the camera. The goal of this paper is to understand how to design a proper mapping function that considers per-scene optimization, which remains unexplored. We first present a geometric understanding of existing mapping functions that express the relation between the bounded and unbounded scenes. Here, we exploit a stereographic projection method to explain failures of the mapping functions, where input ray samples are too sparse to account for scene geometry in unbounded regions. To overcome the failures, we propose a novel mapping function based on a $p$-norm distance, allowing to adaptively sample the rays by adjusting the $p$-value according to scene geometry, even in unbounded regions. To take the advantage of our mapping function, we also introduce a new ray parameterization to properly allocate ray samples in the geometry of unbounded regions. Through the incorporation of both the novel mapping function and the ray parameterization within existing NeRF frameworks, our method achieves state-of-the-art novel view synthesis results on a variety of challenging datasets.

In the face of escalating climate changes, typhoon intensities and their ensuing damage have surged. Accurate trajectory prediction is crucial for effective damage control. Traditional physics-based models, while comprehensive, are computationally intensive and rely heavily on the expertise of forecasters. Contemporary data-driven methods often rely on reanalysis data, which can be considered to be the closest to the true representation of weather conditions. However, reanalysis data is not produced in real-time and requires time for adjustment since prediction models are calibrated with observational data. This reanalysis data, such as ERA5, falls short in challenging real-world situations. Optimal preparedness necessitates predictions at least 72 hours in advance, beyond the capabilities of standard physics models. In response to these constraints, we present an approach that harnesses real-time Unified Model (UM) data, sidestepping the limitations of reanalysis data. Our model provides predictions at 6-hour intervals for up to 72 hours in advance and outperforms both state-of-the-art data-driven methods and numerical weather prediction models. In line with our efforts to mitigate adversities inflicted by \rthree{typhoons}, we release our preprocessed \textit{PHYSICS TRACK} dataset, which includes ERA5 reanalysis data, typhoon best-track, and UM forecast data.

3D Gaussian Splatting has shown fast and high-quality rendering results in static scenes by leveraging dense 3D prior and explicit representations. Unfortunately, the benefits of the prior and representation do not involve novel view synthesis for dynamic motions. Ironically, this is because the main barrier is the reliance on them, which requires increasing training and rendering times to account for dynamic motions. In this paper, we design Explicit 4D Gaussian Splatting (Ex4DGS). Our key idea is to firstly separate static and dynamic Gaussians during training, and to explicitly sample positions and rotations of the dynamic Gaussians at sparse timestamps. The sampled positions and rotations are then interpolated to represent both spatially and temporally continuous motions of objects in dynamic scenes as well as reducing computational cost. Additionally, we introduce a progressive training scheme and a point-backtracking technique that improves Ex4DGS's convergence. We initially train Ex4DGS using short timestamps and progressively extend timestamps, which makes it work well with a few point clouds. The point-backtracking is used to quantify the cumulative error of each Gaussian over time, enabling the detection and removal of erroneous Gaussians in dynamic scenes. Comprehensive experiments on various scenes demonstrate the state-of-the-art rendering quality from our method, achieving fast rendering of 62 fps on a single 2080Ti GPU.

Consistent depth estimation across diverse scenes and sensors is a crucial challenge in computer vision, especially when deploying machine learning models in the real world. Traditional methods depend heavily on extensive pixel-wise labeled data, which is costly and labor-intensive to acquire, and frequently have difficulty in scale issues on various depth sensors. In response, we define Universal Depth Completion (UniDC) problem. We also present a baseline architecture, a simple yet effective approach tailored to estimate scene depth across a wide range of sensors and environments using minimal labeled data. Our approach addresses two primary challenges: generalizable knowledge of unseen scene configurations and strong adaptation to arbitrary depth sensors with various specifications. To enhance versatility in the wild, we utilize a foundation model for monocular depth estimation that provides a comprehensive understanding of 3D structures in scenes. Additionally, for fast adaptation to off-the-shelf sensors, we generate a pixel-wise affinity map based on the knowledge from the foundation model. We then adjust depth information from arbitrary sensors to the monocular depth along with the constructed affinity. Furthermore, to boost up both the adaptability and generality, we embed the learned features into hyperbolic space, which builds implicit hierarchical structures of 3D data from fewer examples. Extensive experiments demonstrate the proposed method's superior generalization capabilities for UniDC problem over state-of-the-art depth completion. Source code is publicly available at https://github.com/JinhwiPark/UniDC.

Urban safety plays an essential role in the quality of citizens' lives and in the sustainable development of cities. In recent years, researchers have attempted to apply machine learning techniques to identify the role of location-specific attributes in the development of urban safety. However, existing studies have mainly relied on limited images (e.g., map images, single- or four-directional images) of areas based on a relatively large geographical unit and have narrowly focused on severe crime rates, which limits their predictive performance and implications for urban safety. In this work, we propose a novel method that predicts "deviance," which includes formal deviant crimes (e.g., murders) and informal deviant behaviors (e.g., loud parties at night). To do this, we first collect a large-scale geo-tagged dataset consisting of incident report data for seven metropolitan cities, along with corresponding sequential images around incident sites obtained from Google Street View. We then design a convolutional neural network that learns spatio-temporal visual attributes of deviant streets. Experimental results show that our framework is able to reliably recognize real-world deviance in various cities. Furthermore, we analyze which visual attribute is important for deviance identification and severity estimation with respect to social science as well as activated feature maps in the neural network.

Predicting the trajectories of pedestrians in crowded conditions is an important task for applications like autonomous navigation systems. Previous studies have tackled this problem using two strategies. They (1) infer all future steps recursively, or (2) predict the potential destinations of pedestrians at once and interpolate the intermediate steps to arrive there. However, these strategies often suffer from the accumulated errors of the recursive inference, or restrictive assumptions about social relations in the intermediate path. In this paper, we present a graph convolutional network-based trajectory prediction. Firstly, we propose a control point prediction that divides the future path into three sections and infers the intermediate destinations of pedestrians to reduce the accumulated error. To do this, we construct multi-relational weighted graphs to account for their physical and complex social relations. We then introduce a trajectory refinement step based on a spatio-temporal and multi-relational graph. By considering the social interactions between neighbors, better prediction results are achievable. In experiments, the proposed network achieves state-of-the-art performance on various real-world trajectory prediction benchmarks.

Understanding the informative structures of scenes is essential for low-level vision tasks. Unfortunately, it is difficult to obtain a concrete visual definition of the informative structures because influences of visual features are task-specific. In this paper, we propose a single general neural network architecture for extracting task-specific structure guidance for scenes. To do this, we first analyze traditional spectral clustering methods, which computes a set of eigenvectors to model a segmented graph forming small compact structures on image domains. We then unfold the traditional graph-partitioning problem into a learnable network, named Scene Structure Guidance Network (SSGNet), to represent the task-specific informative structures. The SSGNet yields a set of coefficients of eigenvectors that produces explicit feature representations of image structures. In addition, our SSGNet is light-weight (56K parameters), and can be used as a plug-and-play module for off-the-shelf architectures. We optimize the SSGNet without any supervision by proposing two novel training losses that enforce task-specific scene structure generation during training. Our main contribution is to show that such a simple network can achieve state-of-the-art results for several low-level vision applications including joint upsampling and image denoising. We also demonstrate that our SSGNet generalizes well on unseen datasets, compared to existing methods which use structural embedding frameworks. Our source codes are available at https://github.com/jsshin98/SSGNet.

High-quality 3D human body reconstruction requires high-fidelity and large-scale training data and appropriate network design that effectively exploits the high-resolution input images. To tackle these problems, we propose a simple yet effective 3D human digitization method called 2K2K, which constructs a large-scale 2K human dataset and infers 3D human models from 2K resolution images. The proposed method separately recovers the global shape of a human and its details. The low-resolution depth network predicts the global structure from a low-resolution image, and the part-wise image-to-normal network predicts the details of the 3D human body structure. The high-resolution depth network merges the global 3D shape and the detailed structures to infer the high-resolution front and back side depth maps. Finally, an off-the-shelf mesh generator reconstructs the full 3D human model, which are available at https://github.com/SangHunHan92/2K2K. In addition, we also provide 2,050 3D human models, including texture maps, 3D joints, and SMPL parameters for research purposes. In experiments, we demonstrate competitive performance over the recent works on various datasets.

Capturing high-dimensional social interactions and feasible futures is essential for predicting trajectories. To address this complex nature, several attempts have been devoted to reducing the dimensionality of the output variables via parametric curve fitting such as the Bézier curve and B-spline function. However, these functions, which originate in computer graphics fields, are not suitable to account for socially acceptable human dynamics. In this paper, we present EigenTrajectory ($\mathbb{E}\mathbb{T}$), a trajectory prediction approach that uses a novel trajectory descriptor to form a compact space, known here as $\mathbb{E}\mathbb{T}$ space, in place of Euclidean space, for representing pedestrian movements. We first reduce the complexity of the trajectory descriptor via a low-rank approximation. We transform the pedestrians' history paths into our $\mathbb{E}\mathbb{T}$ space represented by spatio-temporal principle components, and feed them into off-the-shelf trajectory forecasting models. The inputs and outputs of the models as well as social interactions are all gathered and aggregated in the corresponding $\mathbb{E}\mathbb{T}$ space. Lastly, we propose a trajectory anchor-based refinement method to cover all possible futures in the proposed $\mathbb{E}\mathbb{T}$ space. Extensive experiments demonstrate that our EigenTrajectory predictor can significantly improve both the prediction accuracy and reliability of existing trajectory forecasting models on public benchmarks, indicating that the proposed descriptor is suited to represent pedestrian behaviors. Code is publicly available at https://github.com/inhwanbae/EigenTrajectory.

Recent approaches to representation learning have successfully demonstrated the benefits in hyperbolic space, driven by an excellent ability to make hierarchical relationships. In this work, we demonstrate that the properties of hyperbolic geometry serve as a valuable alternative to learning hierarchical affinity for spatial propagation tasks. We propose a Hyperbolic Affinity learning Module (HAM) to learn spatial affinity by considering geodesic distance on the hyperbolic space. By simply incorporating our HAM into conventional spatial propagation tasks, we validate its effectiveness, capturing the pixel hierarchy of affinity maps in hyperbolic space. The proposed methodology can lead to performance improvements in explicit propagation processes such as depth completion and semantic segmentation.

With the increasing social demands of disaster response, methods of visual observation for rescue and safety have become increasingly important. However, because of the shortage of datasets for disaster scenarios, there has been little progress in computer vision and robotics in this field. With this in mind, we present the first large-scale synthetic dataset of egocentric viewpoints for disaster scenarios. We simulate pre- and post-disaster cases with drastic changes in appearance, such as buildings on fire and earthquakes. The dataset consists of more than 300K high-resolution stereo image pairs, all annotated with ground-truth data for the semantic label, depth in metric scale, optical flow with sub-pixel precision, and surface normal as well as their corresponding camera poses. To create realistic disaster scenes, we manually augment the effects with 3D models using physically-based graphics tools. We train various state-of-the-art methods to perform computer vision tasks using our dataset, evaluate how well these methods recognize the disaster situations, and produce reliable results of virtual scenes as well as real-world images. We also present a convolutional neural network-based egocentric localization method that is robust to drastic appearance changes, such as the texture changes in a fire, and layout changes from a collapse. To address these key challenges, we propose a new model that learns a shape-based representation by training on stylized images, and incorporate the dominant planes of query images as approximate scene coordinates. We evaluate the proposed method using various scenes including a simulated disaster dataset to demonstrate the effectiveness of our method when confronted with significant changes in scene layout. Experimental results show that our method provides reliable camera pose predictions despite vastly changed conditions.

Understanding how a city’s physical appearance and environmental surroundings impact society traits, such as safety, is an essential issue in social artificial intelligence. To demonstrate the relationship, most existing studies utilize subjective human perceptual attributes, categorization only for a few violent crimes, and images taken from still shot images. These lead to difficulty in identifying location-specific characteristics for urban safety. In this work, to address this problem, we propose a large-scale dataset and a novel method by adopting a concept of “Deviance" which explains behaviors violating social norms, both formally (e.g. crime) and informally (e.g. civil complaints). We first collect a geo-tagged dataset consisting of incident report data for seven metropolitan cities, with corresponding sequential images around incident sites obtained from Google street view. We also design a convolutional neural network that learns spatio-temporal visual attributes of deviant streets. Experimental results show that our framework can reliably recognize real-world deviance in various cities. Furthermore, we analyze which visual attribute is important for deviance identification and severity estimation. We have released our dataset and source codes at our project page: https://deviance-project.github.io/DevianceNet/

Capturing multimodal natures is essential for stochastic pedestrian trajectory prediction, to infer a finite set of future trajectories. The inferred trajectories are based on observation paths and the latent vectors of potential decisions of pedestrians in the inference step. However, stochastic approaches provide varying results for the same data and parameter settings, due to the random sampling of the latent vector. In this paper, we analyze the problem by reconstructing and comparing probabilistic distributions from prediction samples and socially-acceptable paths, respectively. Through this analysis, we observe that the inferences of all stochastic models are biased toward the random sampling, and fail to generate a set of realistic paths from finite samples. The problem cannot be resolved unless an infinite number of samples is available, which is infeasible in practice. We introduce that the Quasi-Monte Carlo (QMC) method, ensuring uniform coverage on the sampling space, as an alternative to the conventional random sampling. With the same finite number of samples, the QMC improves all the multimodal prediction results. We take an additional step ahead by incorporating a learnable sampling network into the existing networks for trajectory prediction. For this purpose, we propose the Non-Probability Sampling Network (NPSN), a very small network (~5K parameters) that generates purposive sample sequences using the past paths of pedestrians and their social interactions. Extensive experiments confirm that NPSN can significantly improve both the prediction accuracy (up to 60%) and reliability of the public pedestrian trajectory prediction benchmark. Code is publicly available at https://github.com/inhwanbae/NPSN.

Pedestrian trajectory prediction is one of the important tasks required for autonomous navigation and social robots in human environments. Previous studies focused on estimating social forces among individual pedestrians. However, they did not consider the social forces of groups on pedestrians, which results in over-collision avoidance problems. To address this problem, we present a Disentangled Multi-Relational Graph Convolutional Network (DMRGCN) for socially entangled pedestrian trajectory prediction. We first introduce a novel disentangled multi-scale aggregation to better represent social interactions, among pedestrians on a weighted graph. For the aggregation, we construct the multi-relational weighted graphs based on distances and relative displacements among pedestrians. In the prediction step, we propose a global temporal aggregation to alleviate accumulated errors for pedestrians changing their directions. Finally, we apply DropEdge into our DMRGCN to avoid the over-fitting issue on relatively small pedestrian trajectory datasets. Through the effective incorporation of the three parts within an end-to-end framework, DMRGCN achieves state-of-the-art performances on a variety of challenging trajectory prediction benchmarks.

We propose a novel approach to infer a high-quality depth map from a set of images with small viewpoint variations. In general, techniques for depth estimation from small motion consist of camera pose estimation and dense reconstruction. In contrast to prior approaches that recover scene geometry and camera motions using pre-calibrated cameras, we introduce in this paper a self-calibrating bundle adjustment method tailored for small motion which enables computation of camera poses without the need for camera calibration. For dense depth reconstruction, we present a convolutional neural network called DPSNet (Deep Plane Sweep Network) whose design is inspired by best practices of traditional geometry-based approaches. Rather than directly estimating depth or optical flow correspondence from image pairs as done in many previous deep learning methods, DPSNet takes a plane sweep approach that involves building a cost volume from deep features using the plane sweep algorithm, regularizing the cost volume, and regressing the depth map from the cost volume. The cost volume is constructed using a differentiable warping process that allows for end-to-end training of the network. Through the effective incorporation of conventional multiview stereo concepts within a deep learning framework, the proposed method achieves state-of-the-art results on a variety of challenging datasets.

Visual localization is an important task for applications such as navigation and augmented reality, but is a challenging problem when there are changes in scene appearances through day, seasons, or environments. In this paper, we present a convolutional neural network (CNN)-based approach for visual localization across normal to drastic appearance variations such as pre- and post-disaster cases. Our approach aims to address two key challenges: (1) to reduce the biases based on scene textures as in traditional CNNs, our model learns a shape-based representation by training on stylized images; (2) to make the model robust against layout changes, our approach uses the estimated dominant planes of query images as approximate scene coordinates. Our method is evaluated on various scenes including a simulated disaster dataset to demonstrate the effectiveness of our method in significant changes of scene layout. Experimental results show that our method provides reliable camera pose predictions in various changing conditions.

Depth from focus (DfF) is a method of estimating the depth of a scene by using information acquired through changes in the focus of a camera. Within the DfF framework of, the focus measure (FM) forms the foundation which determines the accuracy of the output. With the results from the FM, the role of a DfF pipeline is to determine and recalculate unreliable measurements while enhancing those that are reliable. In this paper, we propose a new FM, which we call the "ring difference filter" (RDF), that can more accurately and robustly measure focus. FMs can usually be categorized as confident local methods or noise robust non-local methods. The RDF's unique ring-and-disk structure allows it to have the advantages of both local and non-local FMs. We then describe an efficient pipeline that utilizes the RDF's properties. Part of this pipeline is our proposed RDF-based cost aggregation method, which is able to robustly refine the initial results in the presence of image noise. Our method is able to reproduce results that are on par with or even better than those of state-of-the-art methods, while spending less time in computation.

In this paper, we present an end-to-end convolutional neural network (CNN) for depth completion. Our network consists of a geometry network and a context network. The geometry network, a single encoder-decoder network, learns to optimize a multi-task loss to generate an initial propagated depth map and a surface normal. The complementary outputs allow it to correctly propagate initial sparse depth points in slanted surfaces. The context network extracts a local and a global feature of an image to compute a bilateral weight, which enables it to preserve edges and fine details in the depth maps. At the end, a final output is produced by multiplying the initially propagated depth map with the bilateral weight. In order to validate the effectiveness and the robustness of our network, we performed extensive ablation studies and compared the results against state-of-the-art CNN-based depth completions, where we showed promising results on various scenes.

In this paper, we present the first large-scale synthetic dataset for visual perception in disaster scenarios, and analyze state-of-the-art methods for multiple computer vision tasks with reference baselines. We simulated before and after disaster scenarios such as fire and building collapse for fifteen different locations in realistic virtual worlds. The dataset consists of more than 300K high-resolution stereo image pairs, all annotated with ground-truth data for semantic segmentation, depth, optical flow, surface normal estimation and camera pose estimation. To create realistic disaster scenes, we manually augmented the effects with 3D models using physical-based graphics tools. We use our dataset to train state-of-the-art methods and evaluate how well these methods can recognize the disaster situations and produce reliable results on virtual scenes as well as real-world images. The results obtained from each task are then used as inputs to the proposed visual odometry network for generating 3D maps of buildings on fire. Finally, we discuss challenges for future research.

Structure from small motion has become an important topic in 3D computer vision as a method for estimating depth, since capturing the input is so user-friendly. However, major limitations exist with respect to the form of depth uncertainty, due to the narrow baseline and the rolling shutter effect. In this paper, we present a dense 3D reconstruction method from small motion clips using commercial hand-held cameras, which typically cause the undesired rolling shutter artifact. To address these problems, we introduce a novel small motion bundle adjustment that effectively compensates for the rolling shutter effect. Moreover, we propose a pipeline for a fine-scale dense 3D reconstruction that models the rolling shutter effect by utilizing both sparse 3D points and the camera trajectory from narrow-baseline images. In this reconstruction, the sparse 3D points are propagated to obtain an initial depth hypothesis using a geometry guidance term. Then, the depth information on each pixel is obtained by sweeping the plane around each depth search space near the hypothesis. The proposed framework shows accurate dense reconstruction results suitable for various sought-after applications. Both qualitative and quantitative evaluations show that our method consistently generates better depth maps compared to state-of-the-art methods.

One of the core applications of light field imaging is depth estimation. To acquire a depth map, existing approaches apply a single photo-consistency measure to an entire light field. However, this is not an optimal choice because of the non-uniform light field degradations produced by limitations in the hardware design. In this paper, we introduce a pipeline that automatically determines the best configuration for photo-consistency measure, which leads to the most reliable depth label from the light field. We analyzed the practical factors affecting degradation in lenslet light field cameras, and designed a learning based framework that can retrieve the best cost measure and optimal depth label. To enhance the reliability of our method, we augmented an existing light field benchmark to simulate realistic source dependent noise, aberrations, and vignetting artifacts. The augmented dataset was used for the training and validation of the proposed approach. Our method was competitive with several state-of-the-art methods for the benchmark and real-world light field datasets.

As the computing power of hand-held devices grows, there has been increasing interest in the capture of depth information, to enable a variety of photographic applications. However, under low-light conditions, most devices still suffer from low imaging quality and inaccurate depth acquisition. To address the problem, we present a robust depth estimation method from a short burst shot with varied intensity (i.e., Auto-exposure bracketing) and/or strong noise (i.e., High ISO). Our key idea synergistically combines deep convolutional neural networks with geometric understanding of the scene. We introduce a geometric transformation between optical flow and depth tailored for burst images, enabling our learning-based multi-view stereo matching to be performed effectively. We then describe our depth estimation pipeline that incorporates this geometric transformation into our residual-flow network. It allows our framework to produce an accurate depth map even with a bracketed image sequence. We demonstrate that our method outperforms state-of-the-art methods for various datasets captured by a smartphone and a DSLR camera. Moreover, we show that the estimated depth is applicable for image quality enhancement and photographic editing.

As demand for advanced photographic applications on hand-held devices grows, these electronics require the capture of high quality depth. However, under low-light conditions, most devices still suffer from low imaging quality and inaccurate depth acquisition. To address the problem, we present a robust depth estimation method from a short burst shot with varied intensity (i.e., Auto Bracketing) or strong noise (i.e., High ISO). We introduce a geometric transformation between flow and depth tailored for burst images, enabling our learning-based multi-view stereo matching to be performed effectively. We then describe our depth estimation pipeline that incorporates the geometric transformation into our residual-flow network. It allows our framework to produce an accurate depth map even with a bracketed image sequence. We demonstrate that our method outperforms state-of-the-art methods for various datasets captured by a smartphone and a DSLR camera. Moreover, we show that the estimated depth is applicable for image quality enhancement and photographic editing.

Light field cameras capture both the spatial and the angular properties of light rays in space. Due to its property, one can compute the depth from light fields in uncontrolled lighting environments, which is a big advantage over active sensing devices. Depth computed from light fields can be used for many applications including 3D modelling and refocusing. However, light field images from hand-held cameras have very narrow baselines with noise, making the depth estimation difficult. Many approaches have been proposed to overcome these limitations for the light field depth estimation, but there is a clear trade-off between the accuracy and the speed in these methods. In this paper, we introduce a fast and accurate light field depth estimation method based on a fully-convolutional neural network. Our network is designed by considering the light field geometry and we also overcome the lack of training data by proposing light field specific data augmentation methods. We achieved the top rank in the HCI 4D Light Field Benchmark on most metrics, and we also demonstrate the effectiveness of the proposed method on real-world light-field images.

Depth from focus (DfF) is a method of estimating depth of a scene by using the information acquired through the change of the focus of a camera. Within the framework of DfF, the focus measure (FM) forms the foundation on which the accuracy of the output is determined. With the result from the FM, the role of a DfF pipeline is to determine and recalculate unreliable measurements while enhancing those that are reliable. In this paper, we propose a new FM that more accurately and robustly measures focus, which we call the ring difference filter (RDF). FMs can usually be categorized as confident local methods or noise robust non-local methods. RDFs unique ring-and-disk structure allows it to have the advantageous sides of both local and non-local FMs. We then describe an efficient pipeline that utilizes the properties that the RDF brings. Our method is able to reproduce results that are on par with or even better than those of the state-of-the-art, while spending less time in computation.

We present a novel method for the geometric calibration of micro-lens-based light field cameras. Accurate geometric calibration is the basis of various applications. Instead of using sub-aperture images, we directly utilize raw images for calibration. We select appropriate regions in raw images and extract line features from micro-lens images in those regions. For the entire process, we formulate a new projection model of a micro-lens-based light field camera, which contains a smaller number of parameters than previous models. The model is transformed into a linear form using line features. We compute the initial solution of both the intrinsic and the extrinsic parameters by a linear computation and refine them via non-linear optimization. Experimental results demonstrate the accuracy of the correspondences between rays and pixels in raw images, as estimated by the proposed method.

In this letter, we present an accurate Depth from Small Motion approach, which reconstructs three-dimensional (3-D) depth from image sequences with extremely narrow baselines. We start with estimating sparse 3-D points and camera poses via the structure from motion method. For dense depth reconstruction, we propose a novel depth propagation using a geometric guidance term that considers not only the geometric constraint from the surface normal, but also color consistency. In addition, we propose an accurate surface normal estimation method with a multiple range search so that the normal vector can guide the direction of the depth propagation precisely. The major benefit of our depth propagation method is that it obtains detailed structures of a scene without fronto-parallel bias. We validate our method using various indoor and outdoor datasets, and both qualitative and quantitative experimental results show that our new algorithm consistently generates better 3-D depth information than the results of existing state-of-the-art methods.

Commercial light field cameras provide spatial and angular information, but their limited resolution becomes an important problem in practical use. In this letter, we present a novel method for light field image super-resolution (SR) to simultaneously up-sample both the spatial and angular resolutions of a light field image via a deep convolutional neural network. We first augment the spatial resolution of each subaperture image by a spatial SR network, then novel views between super-resolved subaperture images are generated by three different angular SR networks according to the novel view locations. We improve both the efficiency of training and the quality of angular SR results by using weight sharing. In addition, we provide a new light field image dataset for training and validating the network. We train our whole network end-to-end, and show state-of-the-art performances on quantitative and qualitative evaluations.

We present a novel coded exposure video technique for multi-image motion deblurring. The key idea of this paper is to capture video frames with a set of complementary fluttering patterns, which enables us to preserve all spectrum bands of a latent image and recover a sharp latent image. To achieve this, we introduce an algorithm for generating a complementary set of binary sequences based on the modern communication theory and implement the coded exposure video system with an off-the-shelf machine vision camera. To demonstrate the effectiveness of our method, we provide in-depth analyses of the theoretical bounds and the spectral gains of our method and other state-of-the-art computational imaging approaches. We further show deblurring results on various challenging examples with quantitative and qualitative comparisons to other computational image capturing methods used for image deblurring, and show how our method can be applied for protecting privacy in videos.

We propose a novel approach that generates a highquality depth map from a set of images captured with a small viewpoint variation, namely small motion clip. As opposed to prior methods that recover scene geometry and camera motions using pre-calibrated cameras, we introduce a self-calibrating bundle adjustment tailored for small motion. This allows our dense stereo algorithm to produce a high-quality depth map for the user without the need for camera calibration. In the dense matching, the distributions of intensity profiles are analyzed to leverage the benefit of having negligible intensity changes within the scene due to the minuscule variation in viewpoint. The depth maps obtained by the proposed framework show accurate and extremely fine structures that are unmatched by previous literature under the same small motion configuration.

Consumer devices with stereo cameras have become popular because of their low-cost depth sensing capability. However, those systems usually suffer from low imaging quality and inaccurate depth acquisition under low-light conditions. To address the problem, we present a new stereo matching method with a color and monochrome camera pair. We focus on the fundamental trade-off that monochrome cameras have much better light-efficiency than color-filtered cameras. Our key ideas involve compensating for the radiometric difference between two cross-spectral images and taking full advantage of complementary data. Consequently, our method produces both an accurate depth map and high-quality images, which are applicable for various depth-aware image processing. Our method is evaluated using various datasets and the performance of our depth estimation consistently outperforms state-of-the-art methods.

This paper introduces an algorithm that accurately estimates depth maps using a lenslet light field camera. The proposed algorithm estimates the multi-view stereo correspondences with sub-pixel accuracy using the cost volume. The foundation for constructing accurate costs is threefold. First, the sub-aperture images are displaced using the phase shift theorem. Second, the gradient costs are adaptively aggregated using the angular coordinates of the light field. Third, the feature correspondences between the sub-aperture images are used as additional constraints. With the cost volume, the multi-label optimization propagates and corrects the depth map in the weak texture regions. Finally, the local depth map is iteratively refined through fitting the local quadratic function to estimate a non-discrete depth map. Because micro-lens images contain unexpected distortions, a method is also proposed that corrects this error. The effectiveness of the proposed algorithm is demonstrated through challenging real world examples and including comparisons with the performance of advanced depth estimation algorithms.

We present a practical 3D reconstruction method to obtain a high-quality dense depth map from narrow-baseline image sequences captured by commercial digital cameras, such as DSLRs or mobile phones. Depth estimation from small motion has gained interest as a means of various photographic editing, but important limitations present themselves in the form of depth uncertainty due to a narrow baseline and rolling shutter. To address these problems, we introduce a novel 3D reconstruction method from narrow-baseline image sequences that effectively handles the effects of a rolling shutter that occur from most of commercial digital cameras. Additionally, we present a depth propagation method to fill in the holes associated with the unknown pixels based on our novel geometric guidance model. Both qualitative and quantitative experimental results show that our new algorithm consistently generates better 3D depth maps than those by the state-of-the-art method.

In this paper, we present a novel multi-image motion deblurring method utilizing the coded exposure technique. The key idea of our work is to capture video frames with a set of complementary fluttering patterns to preserve spatial frequency details. We introduce an algorithm for generating a complementary set of binary sequences based on the modern communication theory and implement the coded exposure video system with an off-the-shelf machine vision camera. The effectiveness of our method is demonstrated on various challenging examples with quantitative and qualitative comparisons to other computational image capturing methods used for image deblurring.

We present a method to reconstruct dense 3D points from small camera motion. We begin with estimating sparse 3D points and camera poses by Structure from Motion (SfM) method with homography decomposition. Although the estimated points are optimized via bundle adjustment and gives reliable accuracy, the reconstructed points are sparse because it heavily depends on the extracted features of a scene. To handle this, we propose a depth propagation method using both a color prior from the images and a geometry prior from the initial points. The major benefit of our method is that we can easily handle the regions with similar colors but different depths by using the surface normal estimated from the initial points. We design our depth propagation framework into the cost minimization process. The cost function is linearly designed, which makes our optimization tractable. We demonstrate the effectiveness of our approach by comparing with a conventional method using various real-world examples.

Finding a good binary sequence is critical in determining the performance of the coded exposure imaging, but previous methods mostly rely on a random search for finding the binary codes, which could easily fail to find good long sequences due to the exponentially growing search space. In this paper, we present a new computationally efficient algorithm for generating the binary sequence, which is especially well suited for longer sequences. We show that the concept of the low autocorrelation binary sequence that has been well exploited in the information theory community can be applied for generating the fluttering patterns of the shutter, propose a new measure of a good binary sequence, and present a new algorithm by modifying the Legendre sequence for the coded exposure imaging. Experiments using both synthetic and real data show that our new algorithm consistently generates better binary sequences for the coded exposure problem, yielding better deblurring and resolution enhancement results compared to the previous methods for generating the binary codes.