Scene reconstruction in the presence of high-speed motion and low illumination is important in many applications such as augmented and virtual reality, drone navigation, and autonomous robotics. Traditional motion estimation techniques fail in such conditions, suffering from too much blur in the presence of high-speed motion and strong noise in low-light conditions. Single-photon cameras have recently emerged as a promising technology capable of capturing hundreds of thousands of photon frames per second thanks to their high speed and extreme sensitivity. Unfortunately, traditional computer vision techniques are not well suited for dealing with the binary-valued photon data captured by these cameras because these are corrupted by extreme Poisson noise. Here we present a method capable of estimating extreme scene motion under challenging conditions, such as low light or high dynamic range, from a sequence of high-speed image frames such as those captured by a single-photon camera. Our method relies on iteratively improving a motion estimate by grouping and aggregating frames after-the-fact, in a stratified manner. We demonstrate the creation of high-quality panoramas under fast motion and extremely low light, and super-resolution results using a custom single-photon camera prototype. For code and supplemental material see our $\href{https://wisionlab.com/project/panoramas-from-photons/}{\text{project webpage}}$.
New 3+1D high-resolution radar sensors are gaining importance for 3D object detection in the automotive domain due to their relative affordability and improved detection compared to classic low-resolution radar sensors. One limitation of high-resolution radar sensors, compared to lidar sensors, is the sparsity of the generated point cloud. This sparsity could be partially overcome by accumulating radar point clouds of subsequent time steps. This contribution analyzes limitations of accumulating radar point clouds on the View-of-Delft dataset. By employing different ego-motion estimation approaches, the dataset's inherent constraints, and possible solutions are analyzed. Additionally, a learning-based instance motion estimation approach is deployed to investigate the influence of dynamic motion on the accumulated point cloud for object detection. Experiments document an improved object detection performance by applying an ego-motion estimation and dynamic motion correction approach.
Estimating the shape and motion state of the myocardium is essential in diagnosing cardiovascular diseases.However, cine magnetic resonance (CMR) imaging is dominated by 2D slices, whose large slice spacing challenges inter-slice shape reconstruction and motion acquisition.To address this problem, we propose a 4D reconstruction method that decouples motion and shape, which can predict the inter-/intra- shape and motion estimation from a given sparse point cloud sequence obtained from limited slices. Our framework comprises a neural motion model and an end-diastolic (ED) shape model. The implicit ED shape model can learn a continuous boundary and encourage the motion model to predict without the supervision of ground truth deformation, and the motion model enables canonical input of the shape model by deforming any point from any phase to the ED phase. Additionally, the constructed ED-space enables pre-training of the shape model, thereby guiding the motion model and addressing the issue of data scarcity. We propose the first 4D myocardial dataset as we know and verify our method on the proposed, public, and cross-modal datasets, showing superior reconstruction performance and enabling various clinical applications.
Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous driving and robotics. Compared to the complex, multi-modal systems deployed today, multi-camera systems provide a simpler, low-cost alternative. However, camera-based 3D reconstruction of complex dynamic scenes has proven extremely difficult, as existing solutions often produce incomplete or incoherent results. We propose R3D3, a multi-camera system for dense 3D reconstruction and ego-motion estimation. Our approach iterates between geometric estimation that exploits spatial-temporal information from multiple cameras, and monocular depth refinement. We integrate multi-camera feature correlation and dense bundle adjustment operators that yield robust geometric depth and pose estimates. To improve reconstruction where geometric depth is unreliable, e.g. for moving objects or low-textured regions, we introduce learnable scene priors via a depth refinement network. We show that this design enables a dense, consistent 3D reconstruction of challenging, dynamic outdoor environments. Consequently, we achieve state-of-the-art dense depth prediction on the DDAD and NuScenes benchmarks.
The rapid tracer kinetics of rubidium-82 ($^{82}$Rb) and high variation of cross-frame distribution in dynamic cardiac positron emission tomography (PET) raise significant challenges for inter-frame motion correction, particularly for the early frames where conventional intensity-based image registration techniques are not applicable. Alternatively, a promising approach utilizes generative methods to handle the tracer distribution changes to assist existing registration methods. To improve frame-wise registration and parametric quantification, we propose a Temporally and Anatomically Informed Generative Adversarial Network (TAI-GAN) to transform the early frames into the late reference frame using an all-to-one mapping. Specifically, a feature-wise linear modulation layer encodes channel-wise parameters generated from temporal tracer kinetics information, and rough cardiac segmentations with local shifts serve as the anatomical information. We validated our proposed method on a clinical $^{82}$Rb PET dataset and found that our TAI-GAN can produce converted early frames with high image quality, comparable to the real reference frames. After TAI-GAN conversion, motion estimation accuracy and clinical myocardial blood flow (MBF) quantification were improved compared to using the original frames. Our code is published at https://github.com/gxq1998/TAI-GAN.
Depth estimation in surgical video plays a crucial role in many image-guided surgery procedures. However, it is difficult and time consuming to create depth map ground truth datasets in surgical videos due in part to inconsistent brightness and noise in the surgical scene. Therefore, building an accurate and robust self-supervised depth and camera ego-motion estimation system is gaining more attention from the computer vision community. Although several self-supervision methods alleviate the need for ground truth depth maps and poses, they still need known camera intrinsic parameters, which are often missing or not recorded. Moreover, the camera intrinsic prediction methods in existing works depend heavily on the quality of datasets. In this work, we aimed to build a self-supervised depth and ego-motion estimation system which can predict not only accurate depth maps and camera pose, but also camera intrinsic parameters. We proposed a cost-volume-based supervision manner to give the system auxiliary supervision for camera parameters prediction. The experimental results showed that the proposed method improved the accuracy of estimated camera parameters, ego-motion, and depth estimation.
We study the problem of synthesizing a long-term dynamic video from only a single image. This is challenging since it requires consistent visual content movements given large camera motions. Existing methods either hallucinate inconsistent perpetual views or struggle with long camera trajectories. To address these issues, it is essential to estimate the underlying 4D (including 3D geometry and scene motion) and fill in the occluded regions. To this end, we present Make-It-4D, a novel method that can generate a consistent long-term dynamic video from a single image. On the one hand, we utilize layered depth images (LDIs) to represent a scene, and they are then unprojected to form a feature point cloud. To animate the visual content, the feature point cloud is displaced based on the scene flow derived from motion estimation and the corresponding camera pose. Such 4D representation enables our method to maintain the global consistency of the generated dynamic video. On the other hand, we fill in the occluded regions by using a pretrained diffusion model to inpaint and outpaint the input image. This enables our method to work under large camera motions. Benefiting from our design, our method can be training-free which saves a significant amount of training time. Experimental results demonstrate the effectiveness of our approach, which showcases compelling rendering results.
The aim of audio-visual segmentation (AVS) is to precisely differentiate audible objects within videos down to the pixel level. Traditional approaches often tackle this challenge by combining information from various modalities, where the contribution of each modality is implicitly or explicitly modeled. Nevertheless, the interconnections between different modalities tend to be overlooked in audio-visual modeling. In this paper, inspired by the human ability to mentally simulate the sound of an object and its visual appearance, we introduce a bidirectional generation framework. This framework establishes robust correlations between an object's visual characteristics and its associated sound, thereby enhancing the performance of AVS. To achieve this, we employ a visual-to-audio projection component that reconstructs audio features from object segmentation masks and minimizes reconstruction errors. Moreover, recognizing that many sounds are linked to object movements, we introduce an implicit volumetric motion estimation module to handle temporal dynamics that may be challenging to capture using conventional optical flow methods. To showcase the effectiveness of our approach, we conduct comprehensive experiments and analyses on the widely recognized AVSBench benchmark. As a result, we establish a new state-of-the-art performance level in the AVS benchmark, particularly excelling in the challenging MS3 subset which involves segmenting multiple sound sources. To facilitate reproducibility, we plan to release both the source code and the pre-trained model.
We address the task of simultaneous part-level reconstruction and motion parameter estimation for articulated objects. Given two sets of multi-view images of an object in two static articulation states, we decouple the movable part from the static part and reconstruct shape and appearance while predicting the motion parameters. To tackle this problem, we present PARIS: a self-supervised, end-to-end architecture that learns part-level implicit shape and appearance models and optimizes motion parameters jointly without any 3D supervision, motion, or semantic annotation. Our experiments show that our method generalizes better across object categories, and outperforms baselines and prior work that are given 3D point clouds as input. Our approach improves reconstruction relative to state-of-the-art baselines with a Chamfer-L1 distance reduction of 3.94 (45.2%) for objects and 26.79 (84.5%) for parts, and achieves 5% error rate for motion estimation across 10 object categories. Video summary at: https://youtu.be/tDSrROPCgUc
The proliferation of technologies, such as extended reality (XR), has increased the demand for high-quality three-dimensional (3D) graphical representations. Industrial 3D applications encompass computer-aided design (CAD), finite element analysis (FEA), scanning, and robotics. However, current methods employed for industrial 3D representations suffer from high implementation costs and reliance on manual human input for accurate 3D modeling. To address these challenges, neural radiance fields (NeRFs) have emerged as a promising approach for learning 3D scene representations based on provided training 2D images. Despite a growing interest in NeRFs, their potential applications in various industrial subdomains are still unexplored. In this paper, we deliver a comprehensive examination of NeRF industrial applications while also providing direction for future research endeavors. We also present a series of proof-of-concept experiments that demonstrate the potential of NeRFs in the industrial domain. These experiments include NeRF-based video compression techniques and using NeRFs for 3D motion estimation in the context of collision avoidance. In the video compression experiment, our results show compression savings up to 48\% and 74\% for resolutions of 1920x1080 and 300x168, respectively. The motion estimation experiment used a 3D animation of a robotic arm to train Dynamic-NeRF (D-NeRF) and achieved an average peak signal-to-noise ratio (PSNR) of disparity map with the value of 23 dB and an structural similarity index measure (SSIM) 0.97.
Tagged magnetic resonance imaging (tMRI) has been employed for decades to measure the motion of tissue undergoing deformation. However, registration-based motion estimation from tMRI is difficult due to the periodic patterns in these images, particularly when the motion is large. With a larger motion the registration approach gets trapped in a local optima, leading to motion estimation errors. We introduce a novel "momenta, shooting, and correction" framework for Lagrangian motion estimation in the presence of repetitive patterns and large motion. This framework, grounded in Lie algebra and Lie group principles, accumulates momenta in the tangent vector space and employs exponential mapping in the diffeomorphic space for rapid approximation towards true optima, circumventing local optima. A subsequent correction step ensures convergence to true optima. The results on a 2D synthetic dataset and a real 3D tMRI dataset demonstrate our method's efficiency in estimating accurate, dense, and diffeomorphic 2D/3D motion fields amidst large motion and repetitive patterns.
Optical Flow Estimation aims to find the 2D dense motion field between two frames. Due to the limitation of model structures and training datasets, existing methods often rely too much on local clues and ignore the integrity of objects, resulting in fragmented motion estimation. Through theoretical analysis, we find the pre-trained large vision models are helpful in optical flow estimation, and we notice that the recently famous Segment Anything Model (SAM) demonstrates a strong ability to segment complete objects, which is suitable for solving the fragmentation problem. We thus propose a solution to embed the frozen SAM image encoder into FlowFormer to enhance object perception. To address the challenge of in-depth utilizing SAM in non-segmentation tasks like optical flow estimation, we propose an Optical Flow Task-Specific Adaption scheme, including a Context Fusion Module to fuse the SAM encoder with the optical flow context encoder, and a Context Adaption Module to adapt the SAM features for optical flow task with Learned Task-Specific Embedding. Our proposed SAMFlow model reaches 0.86/2.10 clean/final EPE and 3.55/12.32 EPE/F1-all on Sintel and KITTI-15 training set, surpassing Flowformer by 8.5%/9.9% and 13.2%/16.3%. Furthermore, our model achieves state-of-the-art performance on the Sintel and KITTI-15 benchmarks, ranking #1 among all two-frame methods on Sintel clean pass.
Deep learning technologies have dramatically reshaped the field of medical image registration over the past decade. The initial developments, such as regression-based and U-Net-based networks, established the foundation for deep learning in image registration. Subsequent progress has been made in various aspects of deep learning-based registration, including similarity measures, deformation regularizations, network architectures, and uncertainty estimation. These advancements have not only enriched the field of image registration but have also facilitated its application in a wide range of tasks, including atlas construction, multi-atlas segmentation, motion estimation, and 2D-3D registration. In this paper, we present a comprehensive overview of the most recent advancements in deep learning-based image registration. We begin with a concise introduction to the core concepts of deep learning-based image registration. Then, we delve into innovative network architectures, loss functions specific to registration, and methods for estimating registration uncertainty. Additionally, this paper explores appropriate evaluation metrics for assessing the performance of deep learning models in registration tasks. Finally, we highlight the practical applications of these novel techniques in medical imaging and discuss the future prospects of deep learning-based image registration.
Self-supervised monocular depth estimation (SS-MDE) has the potential to scale to vast quantities of data. Unfortunately, existing approaches limit themselves to the automotive domain, resulting in models incapable of generalizing to complex environments such as natural or indoor settings. To address this, we propose a large-scale SlowTV dataset curated from YouTube, containing an order of magnitude more data than existing automotive datasets. SlowTV contains 1.7M images from a rich diversity of environments, such as worldwide seasonal hiking, scenic driving and scuba diving. Using this dataset, we train an SS-MDE model that provides zero-shot generalization to a large collection of indoor/outdoor datasets. The resulting model outperforms all existing SSL approaches and closes the gap on supervised SoTA, despite using a more efficient architecture. We additionally introduce a collection of best-practices to further maximize performance and zero-shot generalization. This includes 1) aspect ratio augmentation, 2) camera intrinsic estimation, 3) support frame randomization and 4) flexible motion estimation. Code is available at https://github.com/jspenmar/slowtv_monodepth.
LiDAR is crucial for robust 3D scene perception in autonomous driving. LiDAR perception has the largest body of literature after camera perception. However, multi-task learning across tasks like detection, segmentation, and motion estimation using LiDAR remains relatively unexplored, especially on automotive-grade embedded platforms. We present a real-time multi-task convolutional neural network for LiDAR-based object detection, semantics, and motion segmentation. The unified architecture comprises a shared encoder and task-specific decoders, enabling joint representation learning. We propose a novel Semantic Weighting and Guidance (SWAG) module to transfer semantic features for improved object detection selectively. Our heterogeneous training scheme combines diverse datasets and exploits complementary cues between tasks. The work provides the first embedded implementation unifying these key perception tasks from LiDAR point clouds achieving 3ms latency on the embedded NVIDIA Xavier platform. We achieve state-of-the-art results for two tasks, semantic and motion segmentation, and close to state-of-the-art performance for 3D object detection. By maximizing hardware efficiency and leveraging multi-task synergies, our method delivers an accurate and efficient solution tailored for real-world automated driving deployment. Qualitative results can be seen at https://youtu.be/H-hWRzv2lIY.
Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion information is represented as optical flows in most of the existing deep video compression networks. Indeed, these networks often adopt pre-trained optical flow estimation networks for motion estimation. The optical flows, however, may be less suitable for video compression due to the following two factors. First, the optical flow estimation networks were trained to perform inter-frame prediction as accurately as possible, but the optical flows themselves may cost too many bits to encode. Second, the optical flow estimation networks were trained on synthetic data, and may not generalize well enough to real-world videos. We address the twofold limitations by enhancing the optical flows in two stages: offline and online. In the offline stage, we fine-tune a trained optical flow estimation network with the motion information provided by a traditional (non-deep) video compression scheme, e.g. H.266/VVC, as we believe the motion information of H.266/VVC achieves a better rate-distortion trade-off. In the online stage, we further optimize the latent features of the optical flows with a gradient descent-based algorithm for the video to be compressed, so as to enhance the adaptivity of the optical flows. We conduct experiments on a state-of-the-art deep video compression scheme, DCVC. Experimental results demonstrate that the proposed offline and online enhancement together achieves on average 12.8% bitrate saving on the tested videos, without increasing the model or computational complexity of the decoder side.
Event cameras respond to changes in log-brightness at the millisecond level, making them ideal for optical flow estimation. However, existing datasets from event cameras provide only low frame rate ground truth for optical flow, limiting the research potential of event-driven optical flow. To address this challenge, we introduce a low-latency event representation, Unified Voxel Grid, and propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision. Furthermore, we propose the Rectified Flow Warp Loss (RFWL) for the unsupervised assessment of intermediate optical flow. A comprehensive variety of experiments on MVSEC, DESC, and our EVA-FlowSet demonstrates that EVA-Flow achieves competitive performance, super-low-latency (5ms), time-dense motion estimation (200Hz), and strong generalization. Our code will be available at https://github.com/Yaozhuwa/EVA-Flow.
Anti-collision assistance, integral to the current drive towards increased vehicular autonomy, relies heavily on precise detection and localization of moving targets in the vehicle's vicinity. A crucial step towards achieving this is the removal of static objects from the scene, thereby enhancing the detection and localization of dynamic targets - a pivotal aspect in augmenting overall system performance. In this paper, we propose a static background removal algorithm tailored for automotive scenarios, designed for common frequency-modulated continuous wave (FMCW) radars. This algorithm effectively eliminates reflections corresponding to static backgrounds from radar images through a two-step process: 4-dimensional (4D) radar imaging and filtering in the azimuth-elevation-Doppler domain. Our proposed approach is underpinned by a model customized for FMCW radar signals, incorporating a time-division multiplexing-based multiple-input multiple-output scheme on the non-uniform radar array. Furthermore, our filtering process requires knowledge of the 3-dimensional (3D) radar ego-motion velocity, typically obtained from an external sensor. To address scenarios where such sensors are unavailable, we introduce a self-contained 3D ego-motion estimation approach. Finally, we evaluate the performance of our algorithm using both simulated and real-world data, analyzing its sensitivity and time complexity in comparison to established baselines.
This paper explores the application of event-based cameras in the domains of image segmentation and motion estimation. These cameras offer a groundbreaking technology by capturing visual information as a continuous stream of asynchronous events, departing from the conventional frame-based image acquisition. We introduce a Generalized Nash Equilibrium based framework that leverages the temporal and spatial information derived from the event stream to carry out segmentation and velocity estimation. To establish the theoretical foundations, we derive an existence criteria and propose a multi-level optimization method for calculating equilibrium. The efficacy of this approach is shown through a series of experiments.
High-quality ultrafast ultrasound imaging is based on coherent compounding from multiple transmissions of plane waves (PW) or diverging waves (DW). However, compounding results in reduced frame rate, as well as destructive interferences from high-velocity tissue motion if motion compensation (MoCo) is not considered. While many studies have recently shown the interest of deep learning for the reconstruction of high-quality static images from PW or DW, its ability to achieve such performance while maintaining the capability of tracking cardiac motion has yet to be assessed. In this paper, we addressed such issue by deploying a complex-weighted convolutional neural network (CNN) for image reconstruction and a state-of-the-art speckle tracking method. The evaluation of this approach was first performed by designing an adapted simulation framework, which provides specific reference data, i.e. high quality, motion artifact-free cardiac images. The obtained results showed that, while using only three DWs as input, the CNN-based approach yielded an image quality and a motion accuracy equivalent to those obtained by compounding 31 DWs free of motion artifacts. The performance was then further evaluated on non-simulated, experimental in vitro data, using a spinning disk phantom. This experiment demonstrated that our approach yielded high-quality image reconstruction and motion estimation, under a large range of velocities and outperforms a state-of-the-art MoCo-based approach at high velocities. Our method was finally assessed on in vivo datasets and showed consistent improvement in image quality and motion estimation compared to standard compounding. This demonstrates the feasibility and effectiveness of deep learning reconstruction for ultrafast speckle-tracking echocardiography.