We propose a fully automated system that simultaneously estimates the camera intrinsics, the ground plane, and physical distances between people from a single RGB image or video captured by a camera viewing a 3-D scene from a fixed vantage point. To automate camera calibration and distance estimation, we leverage priors about human pose and develop a novel direct formulation for pose-based auto-calibration and distance estimation, which shows state-of-the-art performance on publicly available datasets. The proposed approach enables existing camera systems to measure physical distances without needing a dedicated calibration process or range sensors, and is applicable to a broad range of use cases such as social distancing and workplace safety. Furthermore, to enable evaluation and drive research in this area, we contribute to the publicly available MEVA dataset with additional distance annotations, resulting in "MEVADA" -- an evaluation benchmark for the pose-based auto-calibration and distance estimation problem.
论文检索
输入标题、作者或关键词，从 4,294 篇学术成果中精准定位
Gradient-based algorithms are crucial to modern computer-vision and graphics applications, enabling learning-based optimization and inverse problems. For example, photorealistic differentiable rendering pipelines for color images have been proven highly valuable to applications aiming to map 2D and 3D domains. However, to the best of our knowledge, no effort has been made so far towards extending these gradient-based methods to the generation of depth (2.5D) images, as simulating structured-light depth sensors implies solving complex light transport and stereo-matching problems. In this paper, we introduce a novel end-to-end differentiable simulation pipeline for the generation of realistic 2.5D scans, built on physics-based 3D rendering and custom block-matching algorithms. Each module can be differentiated w.r.t sensor and scene parameters; e.g., to automatically tune the simulation for new devices over some provided scans or to leverage the pipeline as a 3D-to-2.5D transformer within larger computer-vision applications. Applied to the training of deep-learning methods for various depth-based recognition tasks (classification, pose estimation, semantic segmentation), our simulation greatly improves the performance of the resulting models on real scans, thereby demonstrating the fidelity and value of its synthetic depth data compared to previous static simulations and learning-based domain adaptation schemes.
We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances in neural implicit representation and uses continuous and differentiable functions for modeling the time-varying structure and the appearance of the scene. We jointly train a time-invariant static NeRF and a time-varying dynamic NeRF, and learn how to blend the results in an unsupervised manner. However, learning this implicit function from a single video is highly ill-posed (with infinitely many solutions that match the input video). To resolve the ambiguity, we introduce regularization losses to encourage a more physically plausible solution. We show extensive quantitative and qualitative results of dynamic view synthesis from casually captured videos.
Human motion synthesis is an important problem for applications in graphics and gaming, and even in simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we propose a framework for training generative models of physically plausible human motion directly from monocular RGB videos, which are much more widely available. At the core of our method is a novel optimization formulation that aims to correct imperfect image-based pose estimations by enforcing physics constraints and reasons about contacts in a differentiable way. This optimization yields corrected 3D poses and motions, as well as their corresponding contact forces. Results show that our physically-correct motions significantly outperform prior work on pose estimation. We then train a generative model to synthesize both future motion and contact forces. We demonstrate both qualitatively and quantitatively significantly improved motion synthesis quality and physical plausibility achieved by our method on the large scale Human3.6m dataset as compared to prior learning-based kinematic and physics-based methods. By learning directly from video, our method paves the way for large-scale, realistic and diverse motion synthesis not previously possible.
We present 3DeepCT, a deep neural network for computed tomography, which performs 3D reconstruction of scattering volumes from multi-view images. The architecture is dictated by the stationary nature of atmospheric cloud fields. The task of volumetric scattering tomography aims at recovering a volume from its 2D projections. This problem has been approached by diverse inverse methods based on signal processing and physics models. However, such techniques are typically iterative, exhibiting a high computational load and a long convergence time. We show that 3DeepCT outperforms physics-based inverse scattering methods, in accuracy, as well as offering orders of magnitude improvement in computational run-time. We further introduce a hybrid model that combines 3DeepCT and physics-based analysis. The resultant hybrid technique enjoys fast inference time and improved recovery performance.
The fluctuation of the water surface causes refractive distortions that severely downgrade the image of an underwater scene. Here, we present the distortion-guided network (DG-Net) for restoring distortion-free underwater images. The key idea is to use a distortion map to guide network training. The distortion map models the pixel displacement caused by water refraction. We first use a physically constrained convolutional network to estimate the distortion map from the refracted image. We then use a generative adversarial network guided by the distortion map to restore the sharp distortion-free image. Since the distortion map indicates correspondences between the distorted image and the distortion-free one, it guides the network to make better predictions. We evaluate our network on several real and synthetic underwater image datasets and show that it out-performs the state-of-the-art algorithms, especially in presence of large distortions. We also show results of complex scenarios, including outdoor swimming pool images captured by the drone and indoor aquarium images taken by cellphone camera.
Dark environment becomes a challenge for computer vision algorithms owing to insufficient photons and undesirable noises. Most of the existing studies tackle this by either targeting human vision for better visual perception or improving the machine vision for specific high-level tasks. In addition, these methods rely on data argumentation and directly train their models based on real-world or over-simplified synthetic datasets without exploring the intrinsic pattern behind illumination translation. Here, we propose a novel multitask auto encoding transformation (MAET) model that combines human vision and machine vision tasks to enhance object detection in a dark environment. With a self-supervision learning, the MAET learns an intrinsic visual structure by encoding and decoding the realistic illumination-degrading transformation considering the physical noise model and image signal processing (ISP). Based on this representation, we achieve object detection task by decoding the bounding box coordinates and classes. To avoid the over-entanglement of two tasks, our MAET disentangles the object and degrading features by imposing an orthogonal tangent regularity. This forms a parametric manifold along which multitask predictions can be geometrically formulated by maximizing the orthogonality between the tangents along the outputs of respective tasks. Our framework can be implemented based on the mainstream object detection architecture and directly trained end-to-end using the normal target detection datasets, such as COCO and VOC. We have achieved the state-of-the-art performance using synthetic and real-world datasets.
The lack of large-scale real raw image denoising dataset gives the rise to challenges on synthesizing realistic raw image noise for training denoising models. However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors. Existing methods are unable to model all noise sources accurately, and building a noise model for each sensor is also laborious. In this paper, we introduce a new perspective to synthesize noise by directly sampling from the sensor's real noise. It inherently generates accurate raw image noise for different camera sensors. Two efficient and generic techniques: pattern-aligned patch sampling and high-bit reconstruction help accurate synthesis of spatial-correlated noise and high-bit noise respectively. We conduct systematic experiments on SIDD and ELD datasets. The results show that (1) our method outperforms existing methods and demonstrates wide generalization on different sensors and lighting conditions. (2) Recent conclusions derived from DNN-based noise modeling methods are actually based on inaccurate noise parameters. The DNN-based methods still cannot outperform physics-based statistical methods.
This paper proposes GraviCap, i.e., a new approach for joint markerless 3D human motion capture and object trajectory estimation from monocular RGB videos. We focus on scenes with objects partially observed during a free flight. In contrast to existing monocular methods, we can recover scale, object trajectories as well as human bone lengths in meters and the ground plane's orientation, thanks to the awareness of the gravity constraining object motions. Our objective function is parametrised by the object's initial velocity and position, gravity direction and focal length, and jointly optimised for one or several free flight episodes. The proposed human-object interaction constraints ensure geometric consistency of the 3D reconstructions and improved physical plausibility of human poses compared to the unconstrained case. We evaluate GraviCap on a new dataset with ground-truth annotations for persons and different objects undergoing free flights. In the experiments, our approach achieves state-of-the-art accuracy in 3D human motion capture on various metrics. We urge the reader to watch our supplementary video. Both the source code and the dataset are released; see http://4dqv.mpi-inf.mpg.de/GraviCap/.
TravelNet: Self-Supervised Physically Plausible Hand Motion Learning From Monocular Color Images
PDF ↗This paper aims to reconstruct physically plausible hand motion from monocular color images. Existing frame-by-frame estimating approaches can not guarantee the physical plausibility (e.g. penetration, jittering) directly. In this paper, we embed physical constraints on the per-frame estimated motions in both spatial and temporal space. Our key idea is to adopt a self-supervised learning strategy to train a novel encoder-decoder, named TravelNet, whose training motion data is prepared by the physics engine using discrete pose states. TravelNet captures key pose states from hand motion sequences as compact motion descriptors, inspired by the concept of keyframes in animation. Finally, it manages to extract those key states out of perturbations without manual annotations, and reconstruct the motions preserving details and physical plausibility. In the experiments, we show that the outputs of the TravelNet contain both finger synergism and time consistency. Through the proposed framework, hand motions can be accurately reconstructed and flexibly re-edited, which is superior to the state-of-the-art methods.
In this work, we address the problem of jointly estimating albedo, normals, depth and 3D spatially-varying lighting from a single image. Most existing methods formulate the task as image-to-image translation, ignoring the 3D properties of the scene. However, indoor scenes contain complex 3D light transport where a 2D representation is insufficient. In this paper, we propose a unified, learning-based inverse rendering framework that formulates 3D spatially-varying lighting. Inspired by classic volume rendering techniques, we propose a novel Volumetric Spherical Gaussian representation for lighting, which parameterizes the exitant radiance of the 3D scene surfaces on a voxel grid. We design a physicsbased differentiable renderer that utilizes our 3D lighting representation, and formulates the energy-conserving image formation process that enables joint training of all intrinsic properties with the re-rendering constraint. Our model ensures physically correct predictions and avoids the need for ground-truth HDR lighting which is not easily accessible. Experiments show that our method outperforms prior works both quantitatively and qualitatively, and is capable of producing photorealistic results for AR applications such as virtual object insertion even for highly specular objects.
People often use physical intuition when manipulating articulated objects, irrespective of object semantics. Motivated by this observation, we identify an important embodied task where an agent must play with objects to recover their parts. To this end, we introduce Act the Part (AtP) to learn how to interact with articulated objects to discover and segment their pieces. By coupling action selection and motion segmentation, AtP is able to isolate structures to make perceptual part recovery possible without semantic labels. Our experiments show AtP learns efficient strategies for part discovery, can generalize to unseen categories, and is capable of conditional reasoning for the task. Although trained in simulation, we show convincing transfer to real world data with no fine-tuning. A summery video, interactive demo, and code will be available at atp.cs.columbia.edu.
Goal-conditioned approaches recently have been found very useful to human trajectory prediction, when adequate goal estimates are provided. Yet, goal inference is difficult in itself and often incurs extra learning efforts. We propose to predict pedestrian trajectories via the guidance of goal expertise, which can be obtained with modest expense through a novel goal-search mechanism on already seen training examples. There are three key contributions in our study. First, we devise a framework that exploits the nearest examples for high-quality goal position inquiry. This approach naturally considers multi-modality, physical constraints, compatibility with existing methods and is model-free; it therefore does not require additional learning efforts typical in goal inference. Second, we present an end-to-end trajectory predictor that can efficiently associate goal retrievals to past motion information and dynamically infer possible future trajectories. Third, with these two novel techniques in hand, we conduct a series of experiments on two broadly explored datasets (SDD and ETH/UCY) and show that our approach surpasses previous state-of-the-art performance by notable margins and reduces the need for additional parameters.
We derive computed tomography (CT) of a time-varying volumetric scattering object, using a small number of moving cameras. We focus on passive tomography of dynamic clouds, as clouds have a major effect on the Earth's climate. State of the art scattering CT assumes a static object. Existing 4D CT methods rely on a linear image formation model and often on significant priors. In this paper, the angular and temporal sampling rates needed for a proper recovery are discussed. Spatiotemporal CT is achieved using gradient-based optimization, which accounts for the correlation time of the dynamic object content. We demonstrate this in physics-based simulations and on experimental real-world data.
Document unwarping attempts to undo the physical deformation of the paper and recover a 'flatbed' scanned document-image for downstream tasks such as OCR. Current state-of-the-art relies on global unwarping of the document which is not robust to local deformation changes. Moreover, a global unwarping often produces spurious warping artifacts in less warped regions to compensate for severe warps present in other parts of the document. In this paper, we propose the first end-to-end trainable piece-wise unwarping method that predicts local deformation fields and stitches them together with global information to obtain an improved unwarping. The proposed piece-wise formulation results in 4% improvement in terms of multi-scale structural similarity (MS-SSIM) and shows better performance in terms of OCR metrics, character error rate (CER) and word error rate (WER) compared to the state-of-the-art.
Light field images contain both angular and spatial information of captured light rays. The rich information of light fields enables straightforward disparity recovery capability but demands high computational cost as well. In this paper, we design a lightweight disparity estimation model with physical-based multi-disparity-scale cost volume aggregation for fast disparity estimation. By introducing a sub-network of edge guidance, we significantly improve the recovery of geometric details near edges and improve the overall performance. We test the proposed model extensively on both synthetic and real-captured datasets, which provide both densely and sparsely sampled light fields. Finally, we significantly reduce computation cost and GPU memory consumption, while achieving comparable performance with state-of-the-art disparity estimation methods for light fields. Our source code is available at https://github.com/zcong17huang/FastLFnet.
Self-Supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond
PDF ↗To learn distinguishable patterns, most of recent works in vehicle re-identification (ReID) struggled to redevelop official benchmarks to provide various supervisions, which requires prohibitive human labors. In this paper, we seek to achieve the similar goal but do not involve more human efforts. To this end, we introduce a novel framework, which successfully encodes both geometric local features and global representations to distinguish vehicle instances, optimized only by the supervision from official ID labels. Specifically, given our insight that objects in ReID share similar geometric characteristics, we propose to borrow self-supervised representation learning to facilitate geometric features discovery. To condense these features, we introduce an interpretable attention module, with the core of local maxima aggregation instead of fully automatic learning, whose mechanism is completely understandable and whose response map is physically reasonable. To the best of our knowledge, we are the first that perform self-supervised learning to discover geometric features. We conduct comprehensive experiments on three most popular datasets for vehicle ReID, i.e., VeRi-776, CityFlow-ReID, and VehicleID. We report our state-of-the-art (SOTA) performances and promising visualization results. We also show the excellent scalability of our approach on other ReID related tasks, i.e., person ReID and multi-target multi-camera (MTMC) vehicle tracking.
Many computer vision problems face difficulties when imaging through turbulent refractive media (e.g., air and water) due to the refraction and scattering of light. These effects cause geometric distortion that requires either handcrafted physical priors or supervised learning methods to remove. In this paper, we present a novel unsupervised network to recover the latent distortion-free image. The key idea is to model non-rigid distortions as deformable grids. Our network consists of a grid deformer that estimates the distortion field and an image generator that outputs the distortion-free image. By leveraging the positional encoding operator, we can simplify the network structure while maintaining fine spatial details in the recovered images. Our method doesn't need to be trained on labeled data and has good transferability across various turbulent image datasets with different types of distortions. Extensive experiments on both simulated and real-captured turbulent images demonstrate that our method can remove both air and water distortions without much customization.
We present a novel approach for extracting human pose features from human action videos. The goal is to let the pose features capture only the poses of the action while being invariant to other factors, including video backgrounds, the video subject's anthropometric characteristics and viewpoints. Such human pose features facilitate the comparison of pose similarity and can be used for down-stream tasks, such as human action video alignment and pose retrieval. The key to our approach is to first normalize the poses in the video frames by retargeting the poses onto a pre-defined 3D skeleton to not only disentangle subject physical features, such as bone lengths and ratios, but also to unify global orientations of the poses. Then the normalized poses are mapped to a pose embedding space of high-level features, learned via unsupervised metric learning. We evaluate the effectiveness of our normalized features both qualitatively by visualizations, and quantitatively by a video alignment task on the Human3.6M dataset and an action recognition task on the Penn Action dataset.
Vulnerability of 3D point cloud (PC) classifiers has become a grave concern due to the popularity of 3D sensors in safety-critical applications. Existing adversarial attacks against 3D PC classifiers are all test-time evasion (TTE) attacks that aim to induce test-time misclassifications using knowledge of the classifier. But since the victim classifier is usually not accessible to the attacker, the threat is largely diminished in practice, as PC TTEs typically have poor transferability. Here, we propose the first backdoor attack (BA) against PC classifiers. Originally proposed for images, BAs poison the victim classifier's training set so that the classifier learns to decide to the attacker's target class whenever the attacker's backdoor pattern is present in a given input sample. Significantly, BAs do not require knowledge of the victim classifier. Different from image BAs, we propose to insert a cluster of points into a PC as a robust backdoor pattern customized for 3D PCs. Such clusters are also consistent with a physical attack (i.e., with a captured object in a scene). We optimize the cluster's location using an independently trained surrogate classifier and choose the cluster's local geometry to evade possible PC preprocessing and PC anomaly detectors (ADs). Experimentally, our BA achieves a uniformly high success rate (>=87%) and shows evasiveness against state-of-the-art PC ADs. Code is available at https://github.com/zhenxianglance/PCBA.