We introduce a new system for Multi-Session SLAM, which tracks camera motion across multiple disjoint videos under a single global reference. Our approach couples the prediction of optical flow with solver layers to estimate camera pose. The backbone is trained end-to-end using a novel differentiable solver for wide-baseline two-view pose. The full system can connect disjoint sequences, perform visual odometry, and global optimization. Compared to existing approaches, our design is accurate and robust to catastrophic failures. Code is available at github.com/princeton-vl/MultiSlam_DiffPose
This paper introduces FlowMap, an end-to-end differentiable method that solves for precise camera poses, camera intrinsics, and per-frame dense depth of a video sequence. Our method performs per-video gradient-descent minimization of a simple least-squares objective that compares the optical flow induced by depth, intrinsics, and poses against correspondences obtained via off-the-shelf optical flow and point tracking. Alongside the use of point tracks to encourage long-term geometric consistency, we introduce differentiable re-parameterizations of depth, intrinsics, and pose that are amenable to first-order optimization. We empirically show that camera parameters and dense depth recovered by our method enable photo-realistic novel view synthesis on 360-degree trajectories using Gaussian Splatting. Our method not only far outperforms prior gradient-descent based bundle adjustment methods, but surprisingly performs on par with COLMAP, the state-of-the-art SfM method, on the downstream task of 360-degree novel view synthesis (even though our method is purely gradient-descent based, fully differentiable, and presents a complete departure from conventional SfM).
Given a source portrait, the automatic human body reshaping task aims at editing it to an aesthetic body shape. As the technology has been widely used in media, several methods have been proposed mainly focusing on generating optical flow to warp the body shape. However, those previous works only consider the local transformation of different body parts (arms, torso, and legs), ignoring the global affinity, and limiting the capacity to ensure consistency and quality across the entire body. In this paper, we propose a novel Adaptive Affinity-Graph Network (AAGN), which extracts the global affinity between different body parts to enhance the quality of the generated optical flow. Specifically, our AAGN primarily introduces the following designs: (1) we propose an Adaptive Affinity-Graph (AAG) Block that leverages the characteristic of a fully connected graph. AAG represents different body parts as nodes in an adaptive fully connected graph and captures all the affinities between nodes to obtain a global affinity map. The design could better improve the consistency between body parts. (2) Besides, for high-frequency details are crucial for photo aesthetics, a Body Shape Discriminator (BSD) is designed to extract information from both high-frequency and spatial domain. Particularly, an SRM filter is utilized to extract high-frequency details, which are combined with spatial features as input to the BSD. With this design, BSD guides the Flow Generator (FG) to pay attention to various fine details rather than rigid pixel-level fitting. Extensive experiments conducted on the BR-5K dataset demonstrate that our framework significantly enhances the aesthetic appeal of reshaped photos, surpassing all previous work to achieve state-of-the-art in all evaluation metrics.
Deep neural networks have made significant advancements in accurately estimating scene flow using point clouds, which is vital for many applications like video analysis, action recognition, and navigation. The robustness of these techniques, however, remains a concern, particularly in the face of adversarial attacks that have been proven to deceive state-of-the-art deep neural networks in many domains. Surprisingly, the robustness of scene flow networks against such attacks has not been thoroughly investigated. To address this problem, the proposed approach aims to bridge this gap by introducing adversarial white-box attacks specifically tailored for scene flow networks. Experimental results show that the generated adversarial examples obtain up to 33.7 relative degradation in average end-point error on the KITTI and FlyingThings3D datasets. The study also reveals the significant impact that attacks targeting point clouds in only one dimension or color channel have on average end-point error. Analyzing the success and failure of these attacks on the scene flow networks and their 2D optical flow network variants shows a higher vulnerability for the optical flow networks. Code is available at https://github.com/aheldis/Attack-on-Scene-Flow-using-Point-Clouds.git.
Tackling image degradation due to atmospheric turbulence, particularly in dynamic environment, remains a challenge for long-range imaging systems. Existing techniques have been primarily designed for static scenes or scenes with small motion. This paper presents the first segment-then-restore pipeline for restoring the videos of dynamic scenes in turbulent environment. We leverage mean optical flow with an unsupervised motion segmentation method to separate dynamic and static scene components prior to restoration. After camera shake compensation and segmentation, we introduce foreground/background enhancement leveraging the statistics of turbulence strength and a transformer model trained on a novel noise-based procedural turbulence generator for fast dataset augmentation. Benchmarked against existing restoration methods, our approach restores most of the geometric distortion and enhances sharpness for videos. We make our code, simulator, and data publicly available to advance the field of video restoration from turbulence: riponcs.github.io/TurbSegRes
In this paper, we present RStab, a novel framework for video stabilization that integrates 3D multi-frame fusion through volume rendering. Departing from conventional methods, we introduce a 3D multi-frame perspective to generate stabilized images, addressing the challenge of full-frame generation while preserving structure. The core of our approach lies in Stabilized Rendering (SR), a volume rendering module, which extends beyond the image fusion by incorporating feature fusion. The core of our RStab framework lies in Stabilized Rendering (SR), a volume rendering module, fusing multi-frame information in 3D space. Specifically, SR involves warping features and colors from multiple frames by projection, fusing them into descriptors to render the stabilized image. However, the precision of warped information depends on the projection accuracy, a factor significantly influenced by dynamic regions. In response, we introduce the Adaptive Ray Range (ARR) module to integrate depth priors, adaptively defining the sampling range for the projection process. Additionally, we propose Color Correction (CC) assisting geometric constraints with optical flow for accurate color aggregation. Thanks to the three modules, our RStab demonstrates superior performance compared with previous stabilizers in the field of view (FOV), image quality, and video stability across various datasets.
Weakly supervised LiDAR semantic segmentation has made significant strides with limited labeled data. However, most existing methods focus on the network training under weak supervision, while efficient annotation strategies remain largely unexplored. To tackle this gap, we implement LiDAR semantic segmentation using scatter image annotation, effectively integrating an efficient annotation strategy with network training. Specifically, we propose employing scatter images to annotate LiDAR point clouds, combining a pre-trained optical flow estimation network with a foundation image segmentation model to rapidly propagate manual annotations into dense labels for both images and point clouds. Moreover, we propose ScatterNet, a network that includes three pivotal strategies to reduce the performance gap caused by such annotations. Firstly, it utilizes dense semantic labels as supervision for the image branch, alleviating the modality imbalance between point clouds and images. Secondly, an intermediate fusion branch is proposed to obtain multimodal texture and structural features. Lastly, a perception consistency loss is introduced to determine which information needs to be fused and which needs to be discarded during the fusion process. Extensive experiments on the nuScenes and SemanticKITTI datasets have demonstrated that our method requires less than 0.02% of the labeled points to achieve over 95% of the performance of fully-supervised methods. Notably, our labeled points are only 5% of those used in the most advanced weakly supervised methods.
The objective of this paper is motion segmentation -- discovering and segmenting the moving objects in a video. This is a much studied area with numerous careful, and sometimes complex, approaches and training schemes including: self-supervised learning, learning from synthetic datasets, object-centric representations, amodal representations, and many more. Our interest in this paper is to determine if the Segment Anything model (SAM) can contribute to this task. We investigate two models for combining SAM with optical flow that harness the segmentation power of SAM with the ability of flow to discover and group moving objects. In the first model, we adapt SAM to take optical flow, rather than RGB, as an input. In the second, SAM takes RGB as an input, and flow is used as a segmentation prompt. These surprisingly simple methods, without any further modifications, outperform all previous approaches by a considerable margin in both single and multi-object benchmarks. We also extend these frame-level segmentations to sequence-level segmentations that maintain object identity. Again, this simple model achieves outstanding performance across multiple moving object segmentation benchmarks.
Autonomous driving requires an accurate representation of the environment. A strategy toward high accuracy is to fuse data from several sensors. Learned Bird's-Eye View (BEV) encoders can achieve this by mapping data from individual sensors into one joint latent space. For cost-efficient camera-only systems, this provides an effective mechanism to fuse data from multiple cameras with different views. Accuracy can further be improved by aggregating sensor information over time. This is especially important in monocular camera systems to account for the lack of explicit depth and velocity measurements. Thereby, the effectiveness of developed BEV encoders crucially depends on the operators used to aggregate temporal information and on the used latent representation spaces. We analyze BEV encoders proposed in the literature and compare their effectiveness, quantifying the effects of aggregation operators and latent representations. While most existing approaches aggregate temporal information either in image or in BEV latent space, our analyses and performance comparisons suggest that these latent representations exhibit complementary strengths. Therefore, we develop a novel temporal BEV encoder, TempBEV, which integrates aggregated temporal information from both latent spaces. We consider subsequent image frames as stereo through time and leverage methods from optical flow estimation for temporal stereo encoding. Empirical evaluation on the NuScenes dataset shows a significant improvement by TempBEV over the baseline for 3D object detection and BEV segmentation. The ablation uncovers a strong synergy of joint temporal aggregation in the image and BEV latent space. These results indicate the overall effectiveness of our approach and make a strong case for aggregating temporal information in both image and BEV latent spaces.
This work addresses the landing problem of an aerial vehicle, exemplified by a simple quadrotor, on a moving platform using image-based visual servo control. First, the mathematical model of the quadrotor aircraft is introduced, followed by the design of the inner-loop control. At the second stage, the image features on the textured target plane are exploited to derive a vision-based control law. The image of the spherical centroid of a set of landmarks present in the landing target is used as a position measurement, whereas the translational optical flow is used as velocity measurement. The kinematics of the vision-based system is expressed in terms of the observable features, and the proposed control law guarantees convergence without estimating the unknown distance between the vision system and the target, which is also guaranteed to remain strictly positive, avoiding undesired collisions. The performance of the proposed control law is evaluated in MATLAB and 3-D simulation software Gazebo. Simulation results for a quadrotor UAV are provided for different velocity profiles of the moving target, showcasing the robustness of the proposed controller.
In this paper, we address the Bracket Image Restoration and Enhancement (BracketIRE) task using a novel framework, which requires restoring a high-quality high dynamic range (HDR) image from a sequence of noisy, blurred, and low dynamic range (LDR) multi-exposure RAW inputs. To overcome this challenge, we present the IREANet, which improves the multiple exposure alignment and aggregation with a Flow-guide Feature Alignment Module (FFAM) and an Enhanced Feature Aggregation Module (EFAM). Specifically, the proposed FFAM incorporates the inter-frame optical flow as guidance to facilitate the deformable alignment and spatial attention modules for better feature alignment. The EFAM further employs the proposed Enhanced Residual Block (ERB) as a foundational component, wherein a unidirectional recurrent network aggregates the aligned temporal features to better reconstruct the results. To improve model generalization and performance, we additionally employ the Bayer preserving augmentation (BayerAug) strategy to augment the multi-exposure RAW inputs. Our experimental evaluations demonstrate that the proposed IREANet shows state-of-the-art performance compared with previous methods.
Spin plays a pivotal role in ball-based sports. Estimating spin becomes a key skill due to its impact on the ball's trajectory and bouncing behavior. Spin cannot be observed directly, making it inherently challenging to estimate. In table tennis, the combination of high velocity and spin renders traditional low frame rate cameras inadequate for quickly and accurately observing the ball's logo to estimate the spin due to the motion blur. Event cameras do not suffer as much from motion blur, thanks to their high temporal resolution. Moreover, the sparse nature of the event stream solves communication bandwidth limitations many frame cameras face. To the best of our knowledge, we present the first method for table tennis spin estimation using an event camera. We use ordinal time surfaces to track the ball and then isolate the events generated by the logo on the ball. Optical flow is then estimated from the extracted events to infer the ball's spin. We achieved a spin magnitude mean error of $10.7 \pm 17.3$ rps and a spin axis mean error of $32.9 \pm 38.2\deg$ in real time for a flying ball.
The task of face reenactment is to transfer the head motion and facial expressions from a driving video to the appearance of a source image, which may be of a different person (cross-reenactment). Most existing methods are CNN-based and estimate optical flow from the source image to the current driving frame, which is then inpainted and refined to produce the output animation. We propose a transformer-based encoder for computing a set-latent representation of the source image(s). We then predict the output color of a query pixel using a transformer-based decoder, which is conditioned with keypoints and a facial expression vector extracted from the driving frame. Latent representations of the source person are learned in a self-supervised manner that factorize their appearance, head pose, and facial expressions. Thus, they are perfectly suited for cross-reenactment. In contrast to most related work, our method naturally extends to multiple source images and can thus adapt to person-specific facial dynamics. We also propose data augmentation and regularization schemes that are necessary to prevent overfitting and support generalizability of the learned representations. We evaluated our approach in a randomized user study. The results indicate superior performance compared to the state-of-the-art in terms of motion transfer quality and temporal consistency.
Optical flow estimation is crucial to a variety of vision tasks. Despite substantial recent advancements, achieving real-time on-device optical flow estimation remains a complex challenge. First, an optical flow model must be sufficiently lightweight to meet computation and memory constraints to ensure real-time performance on devices. Second, the necessity for real-time on-device operation imposes constraints that weaken the model's capacity to adequately handle ambiguities in flow estimation, thereby intensifying the difficulty of preserving flow accuracy. This paper introduces two synergistic techniques, Self-Cleaning Iteration (SCI) and Regression Focal Loss (RFL), designed to enhance the capabilities of optical flow models, with a focus on addressing optical flow regression ambiguities. These techniques prove particularly effective in mitigating error propagation, a prevalent issue in optical flow models that employ iterative refinement. Notably, these techniques add negligible to zero overhead in model parameters and inference latency, thereby preserving real-time on-device efficiency. The effectiveness of our proposed SCI and RFL techniques, collectively referred to as SciFlow for brevity, is demonstrated across two distinct lightweight optical flow model architectures in our experiments. Remarkably, SciFlow enables substantial reduction in error metrics (EPE and Fl-all) over the baseline models by up to 6.3% and 10.5% for in-domain scenarios and by up to 6.2% and 13.5% for cross-domain scenarios on the Sintel and KITTI 2015 datasets, respectively.
Heart rate is an important physiological indicator of human health status. Existing remote heart rate measurement methods typically involve facial detection followed by signal extraction from the region of interest (ROI). These SOTA methods have three serious problems: (a) inaccuracies even failures in detection caused by environmental influences or subject movement; (b) failures for special patients such as infants and burn victims; (c) privacy leakage issues resulting from collecting face video. To address these issues, we regard the remote heart rate measurement as the process of analyzing the spatiotemporal characteristics of the optical flow signal in the video. We apply chaos theory to computer vision tasks for the first time, thus designing a brain-inspired framework. Firstly, using an artificial primary visual cortex model to extract the skin in the videos, and then calculate heart rate by time-frequency analysis on all pixels. Our method achieves Robust Skin Tracking for Heart Rate measurement, called HR-RST. The experimental results show that HR-RST overcomes the difficulty of environmental influences and effectively tracks the subject movement. Moreover, the method could extend to other body parts. Consequently, the method can be applied to special patients and effectively protect individual privacy, offering an innovative solution.
Optical flow is a classical task that is important to the vision community. Classical optical flow estimation uses two frames as input, whilst some recent methods consider multiple frames to explicitly model long-range information. The former ones limit their ability to fully leverage temporal coherence along the video sequence; and the latter ones incur heavy computational overhead, typically not possible for real-time flow estimation. Some multi-frame-based approaches even necessitate unseen future frames for current estimation, compromising real-time applicability in safety-critical scenarios. To this end, we present MemFlow, a real-time method for optical flow estimation and prediction with memory. Our method enables memory read-out and update modules for aggregating historical motion information in real-time. Furthermore, we integrate resolution-adaptive re-scaling to accommodate diverse video resolutions. Besides, our approach seamlessly extends to the future prediction of optical flow based on past observations. Leveraging effective historical motion aggregation, our method outperforms VideoFlow with fewer parameters and faster inference speed on Sintel and KITTI-15 datasets in terms of generalization performance. At the time of submission, MemFlow also leads in performance on the 1080p Spring dataset. Codes and models will be available at: https://dqiaole.github.io/MemFlow/.
Visual Odometry (VO) is vital for the navigation of autonomous systems, providing accurate position and orientation estimates at reasonable costs. While traditional VO methods excel in some conditions, they struggle with challenges like variable lighting and motion blur. Deep learning-based VO, though more adaptable, can face generalization problems in new environments. Addressing these drawbacks, this paper presents a novel hybrid visual odometry (VO) framework that leverages pose-only supervision, offering a balanced solution between robustness and the need for extensive labeling. We propose two cost-effective and innovative designs: a self-supervised homographic pre-training for enhancing optical flow learning from pose-only labels and a random patch-based salient point detection strategy for more accurate optical flow patch extraction. These designs eliminate the need for dense optical flow labels for training and significantly improve the generalization capability of the system in diverse and challenging environments. Our pose-only supervised method achieves competitive performance on standard datasets and greater robustness and generalization ability in extreme and unseen scenarios, even compared to dense optical flow-supervised state-of-the-art methods.
Satellite image sequence prediction is a crucial and challenging task. Previous studies leverage optical flow methods or existing deep learning methods on spatial–temporal sequence models for the task. However, they suffer from either oversimplified model assumptions or blurry predictions and sequential error accumulation issue, for a long-term forecast requirement. In this article, we propose a novel multiscale time conditional generative adversarial network (MSTCGAN). To address the sequential error accumulation issue, MSTCGAN adopts a parallel prediction framework to produce the future image sequences by a one-hot time condition input. In addition, a powerful multiscale generator is designed with the multihead axial attention, which helps to carefully preserve the fine-grained details for appearance consistency. Moreover, we develop a temporal discriminator to address the blurry issue and maintain the motion consistency in prediction. Extensive experiments have been conducted on the FengYun-4A satellite dataset, and the results demonstrate the effectiveness and superiority of the proposed method over state-of-the-art approaches.
Pixel-wise regression tasks (e.g., monocular depth estimation (MDE) and optical flow estimation (OFE)) have been widely involved in our daily life in applications like autonomous driving, augmented reality and video composition. Although certain applications are security-critical or bear societal significance, the adversarial robustness of such models are not sufficiently studied, especially in the black-box scenario. In this work, we introduce the first unified black-box adversarial patch attack framework against pixel-wise regression tasks, aiming to identify the vulnerabilities of these models under query-based black-box attacks. We propose a novel square-based adversarial patch optimization framework and employ probabilistic square sampling and score-based gradient estimation techniques to generate the patch effectively and efficiently, overcoming the scalability problem of previous black-box patch attacks. Our attack prototype, named BadPart, is evaluated on both MDE and OFE tasks, utilizing a total of 7 models. BadPart surpasses 3 baseline methods in terms of both attack performance and efficiency. We also apply BadPart on the Google online service for portrait depth estimation, causing 43.5% relative distance error with 50K queries. State-of-the-art (SOTA) countermeasures cannot defend our attack effectively.
Temporal Action Localization (TAL) involves localizing and classifying action snippets in an untrimmed video. The emergence of large video foundation models has led RGB-only video backbones to outperform previous methods needing both RGB and optical flow modalities. Leveraging these large models is often limited to training only the TAL head due to the prohibitively large GPU memory required to adapt the video backbone for TAL. To overcome this limitation, we introduce LoSA, the first memory-and-parameter-efficient backbone adapter designed specifically for TAL to handle untrimmed videos. LoSA specializes for TAL by introducing Long-Short-range Adapters that adapt the intermediate layers of the video backbone over different temporal ranges. These adapters run parallel to the video backbone to significantly reduce memory footprint. LoSA also includes Long-Short-range Gated Fusion that strategically combines the output of these adapters from the video backbone layers to enhance the video features provided to the TAL head. Experiments show that LoSA significantly outperforms all existing methods on standard TAL benchmarks, THUMOS-14 and ActivityNet-v1.3, by scaling end-to-end backbone adaptation to billion-parameter-plus models like VideoMAEv2~(ViT-g) and leveraging them beyond head-only transfer learning.