Self-supervised multi-frame methods have currently achieved promising results in depth estimation. However, these methods often suffer from mismatch problems due to the moving objects, which break the static assumption. Additionally, unfairness can occur when calculating photometric errors in high-freq or low-texture regions of the images. To address these issues, existing approaches use additional semantic priori black-box networks to separate moving objects and improve the model only at the loss level. Therefore, we propose FlowDepth, where a Dynamic Motion Flow Module (DMFM) decouples the optical flow by a mechanism-based approach and warps the dynamic regions thus solving the mismatch problem. For the unfairness of photometric errors caused by high-freq and low-texture regions, we use Depth-Cue-Aware Blur (DCABlur) and Cost-Volume sparsity loss respectively at the input and the loss level to solve the problem. Experimental results on the KITTI and Cityscapes datasets show that our method outperforms the state-of-the-art methods.
The scarcity of ground-truth labels poses one major challenge in developing optical flow estimation models that are both generalizable and robust. While current methods rely on data augmentation, they have yet to fully exploit the rich information available in labeled video sequences. We propose OCAI, a method that supports robust frame interpolation by generating intermediate video frames alongside optical flows in between. Utilizing a forward warping approach, OCAI employs occlusion awareness to resolve ambiguities in pixel values and fills in missing values by leveraging the forward-backward consistency of optical flows. Additionally, we introduce a teacher-student style semi-supervised learning method on top of the interpolated frames. Using a pair of unlabeled frames and the teacher model's predicted optical flow, we generate interpolated frames and flows to train a student model. The teacher's weights are maintained using Exponential Moving Averaging of the student. Our evaluations demonstrate perceptually superior interpolation quality and enhanced optical flow accuracy on established benchmarks such as Sintel and KITTI.
Self-supervised monocular depth estimation methods have been increasingly given much attention due to the benefit of not requiring large, labelled datasets. Such self-supervised methods require high-quality salient features and consequently suffer from severe performance drop for indoor scenes, where low-textured regions dominant in the scenes are almost indiscriminative. To address the issue, we propose a self-supervised indoor monocular depth estimation framework called $\mathrm{F^2Depth}$. A self-supervised optical flow estimation network is introduced to supervise depth learning. To improve optical flow estimation performance in low-textured areas, only some patches of points with more discriminative features are adopted for finetuning based on our well-designed patch-based photometric loss. The finetuned optical flow estimation network generates high-accuracy optical flow as a supervisory signal for depth estimation. Correspondingly, an optical flow consistency loss is designed. Multi-scale feature maps produced by finetuned optical flow estimation network perform warping to compute feature map synthesis loss as another supervisory signal for depth learning. Experimental results on the NYU Depth V2 dataset demonstrate the effectiveness of the framework and our proposed losses. To evaluate the generalization ability of our $\mathrm{F^2Depth}$, we collect a Campus Indoor depth dataset composed of approximately 1500 points selected from 99 images in 18 scenes. Zero-shot generalization experiments on 7-Scenes dataset and Campus Indoor achieve $\delta_1$ accuracy of 75.8% and 76.0% respectively. The accuracy results show that our model can generalize well to monocular images captured in unknown indoor scenes.
Implicit neural representations for video (NeRV) have recently become a novel way for high-quality video representation. However, existing works employ a single network to represent the entire video, which implicitly confuse static and dynamic information. This leads to an inability to effectively compress the redundant static information and lack the explicitly modeling of global temporal-coherent dynamic details. To solve above problems, we propose DS-NeRV, which decomposes videos into sparse learnable static codes and dynamic codes without the need for explicit optical flow or residual supervision. By setting different sampling rates for two codes and applying weighted sum and interpolation sampling methods, DS-NeRV efficiently utilizes redundant static information while maintaining high-frequency details. Additionally, we design a cross-channel attention-based (CCA) fusion module to efficiently fuse these two codes for frame decoding. Our approach achieves a high quality reconstruction of 31.2 PSNR with only 0.35M parameters thanks to separate static and dynamic codes representation and outperforms existing NeRV methods in many downstream tasks. Our project website is at https://haoyan14.github.io/DS-NeRV.
The advancement of generation models has led to the emergence of highly realistic artificial intelligence (AI)-generated videos. Malicious users can easily create non-existent videos to spread false information. This letter proposes an effective AI-generated video detection (AIGVDet) scheme by capturing the forensic traces with a two-branch spatio-temporal convolutional neural network (CNN). Specifically, two ResNet sub-detectors are learned separately for identifying the anomalies in spatical and optical flow domains, respectively. Results of such sub-detectors are fused to further enhance the discrimination ability. A large-scale generated video dataset (GVD) is constructed as a benchmark for model training and evaluation. Extensive experimental results verify the high generalization and robustness of our AIGVDet scheme. Code and dataset will be available at https://github.com/multimediaFor/AIGVDet.
Applications of an efficient emotion recognition system can be found in several domains such as medicine, driver fatigue surveillance, social robotics, and human-computer interaction. Appraising human emotional states, behaviors, and reactions displayed in real-world settings can be accomplished using latent continuous dimensions. Continuous dimensional models of human affect, such as those based on valence and arousal are more accurate in describing a broad range of spontaneous everyday emotions than more traditional models of discrete stereotypical emotion categories (e.g. happiness, surprise). Most of the prior work on estimating valence and arousal considers laboratory settings and acted data. But, for emotion recognition systems to be deployed and integrated into real-world mobile and computing devices, we need to consider data collected in the world. Action recognition is a domain of Computer Vision that involves capturing complementary information on appearance from still frames and motion between frames. In this paper, we treat emotion recognition from the perspective of action recognition by exploring the application of deep learning architectures specifically designed for action recognition, for continuous affect recognition. We propose a novel three-stream end-to-end deep learning regression pipeline with an attention mechanism, which is an ensemble design based on sub-modules of multiple state-of-the-art action recognition systems. The pipeline constitutes a novel data pre-processing approach with a spatial self-attention mechanism to extract keyframes. The optical flow of high-attention regions of the face is extracted to capture temporal context. AFEW-VA in-the-wild dataset has been used to conduct comparative experiments. Quantitative analysis shows that the proposed model outperforms multiple standard baselines of both emotion recognition and action recognition models.
In minimally invasive endovascular procedures, contrast-enhanced angiography remains the most robust imaging technique. However, it is at the expense of the patient and clinician's health due to prolonged radiation exposure. As an alternative, interventional ultrasound has notable benefits such as being radiation-free, fast to deploy, and having a small footprint in the operating room. Yet, ultrasound is hard to interpret, and highly prone to artifacts and noise. Additionally, interventional radiologists must undergo extensive training before they become qualified to diagnose and treat patients effectively, leading to a shortage of staff, and a lack of open-source datasets. In this work, we seek to address both problems by introducing a self-supervised deep learning architecture to segment catheters in longitudinal ultrasound images, without demanding any labeled data. The network architecture builds upon AiAReSeg, a segmentation transformer built with the Attention in Attention mechanism, and is capable of learning feature changes across time and space. To facilitate training, we used synthetic ultrasound data based on physics-driven catheter insertion simulations, and translated the data into a unique CT-Ultrasound common domain, CACTUSS, to improve the segmentation performance. We generated ground truth segmentation masks by computing the optical flow between adjacent frames using FlowNet2, and performed thresholding to obtain a binary map estimate. Finally, we validated our model on a test dataset, consisting of unseen synthetic data and images collected from silicon aorta phantoms, thus demonstrating its potential for applications to clinical data in the future.
In this paper, we propose a simple and strong framework for Tracking Any Point with TRansformers (TAPTR). Based on the observation that point tracking bears a great resemblance to object detection and tracking, we borrow designs from DETR-like algorithms to address the task of TAP. In the proposed framework, in each video frame, each tracking point is represented as a point query, which consists of a positional part and a content part. As in DETR, each query (its position and content feature) is naturally updated layer by layer. Its visibility is predicted by its updated content feature. Queries belonging to the same tracking point can exchange information through self-attention along the temporal dimension. As all such operations are well-designed in DETR-like algorithms, the model is conceptually very simple. We also adopt some useful designs such as cost volume from optical flow models and develop simple designs to provide long temporal information while mitigating the feature drifting issue. Our framework demonstrates strong performance with state-of-the-art performance on various TAP datasets with faster inference speed.
Visual simultaneous localization and mapping (VSLAM) has broad applications, with state-of-the-art methods leveraging deep neural networks for better robustness and applicability. However, there is a lack of research in fusing these learning-based methods with multi-sensor information, which could be indispensable to push related applications to large-scale and complex scenarios. In this paper, we tightly integrate the trainable deep dense bundle adjustment (DBA) with multi-sensor information through a factor graph. In the framework, recurrent optical flow and DBA are performed among sequential images. The Hessian information derived from DBA is fed into a generic factor graph for multi-sensor fusion, which employs a sliding window and supports probabilistic marginalization. A pipeline for visual-inertial integration is firstly developed, which provides the minimum ability of metric-scale localization and mapping. Furthermore, other sensors (e.g., global navigation satellite system) are integrated for driftless and geo-referencing functionality. Extensive tests are conducted on both public datasets and self-collected datasets. The results validate the superior localization performance of our approach, which enables real-time dense mapping in large-scale environments. The code has been made open-source (https://github.com/GREAT-WHU/DBA-Fusion).
Diffusion models have achieved great success in image generation. However, when leveraging this idea for video generation, we face significant challenges in maintaining the consistency and continuity across video frames. This is mainly caused by the lack of an effective framework to align frames of videos with desired temporal features while preserving consistent semantic and stochastic features. In this work, we propose a novel Sector-Shaped Diffusion Model (S2DM) whose sector-shaped diffusion region is formed by a set of ray-shaped reverse diffusion processes starting at the same noise point. S2DM can generate a group of intrinsically related data sharing the same semantic and stochastic features while varying on temporal features with appropriate guided conditions. We apply S2DM to video generation tasks, and explore the use of optical flow as temporal conditions. Our experimental results show that S2DM outperforms many existing methods in the task of video generation without any temporal-feature modelling modules. For text-to-video generation tasks where temporal conditions are not explicitly given, we propose a two-stage generation strategy which can decouple the generation of temporal features from semantic-content features. We show that, without additional training, our model integrated with another temporal conditions generative model can still achieve comparable performance with existing works. Our results can be viewd at https://s2dm.github.io/S2DM/.
Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models, directly supervising Gaussian motions remains underexplored. In this paper, we introduce a novel concept, Gaussian flow, which connects the dynamics of 3D Gaussians and pixel velocities between consecutive frames. The Gaussian flow can be efficiently obtained by splatting Gaussian dynamics into the image space. This differentiable process enables direct dynamic supervision from optical flow. Our method significantly benefits 4D dynamic content generation and 4D novel view synthesis with Gaussian Splatting, especially for contents with rich motions that are hard to be handled by existing methods. The common color drifting issue that happens in 4D generation is also resolved with improved Guassian dynamics. Superior visual quality on extensive experiments demonstrates our method's effectiveness. Quantitative and qualitative evaluations show that our method achieves state-of-the-art results on both tasks of 4D generation and 4D novel view synthesis. Project page: https://zerg-overmind.github.io/GaussianFlow.github.io/
Despite the progress of learning-based methods for 6D object pose estimation, the trade-off between accuracy and scalability for novel objects still exists. Specifically, previous methods for novel objects do not make good use of the target object's 3D shape information since they focus on generalization by processing the shape indirectly, making them less effective. We present GenFlow, an approach that enables both accuracy and generalization to novel objects with the guidance of the target object's shape. Our method predicts optical flow between the rendered image and the observed image and refines the 6D pose iteratively. It boosts the performance by a constraint of the 3D shape and the generalizable geometric knowledge learned from an end-to-end differentiable system. We further improve our model by designing a cascade network architecture to exploit the multi-scale correlations and coarse-to-fine refinement. GenFlow ranked first on the unseen object pose estimation benchmarks in both the RGB and RGB-D cases. It also achieves performance competitive with existing state-of-the-art methods for the seen object pose estimation without any fine-tuning.
3D Gaussian Splatting (3DGS) has become an emerging tool for dynamic scene reconstruction. However, existing methods focus mainly on extending static 3DGS into a time-variant representation, while overlooking the rich motion information carried by 2D observations, thus suffering from performance degradation and model redundancy. To address the above problem, we propose a novel motion-aware enhancement framework for dynamic scene reconstruction, which mines useful motion cues from optical flow to improve different paradigms of dynamic 3DGS. Specifically, we first establish a correspondence between 3D Gaussian movements and pixel-level flow. Then a novel flow augmentation method is introduced with additional insights into uncertainty and loss collaboration. Moreover, for the prevalent deformation-based paradigm that presents a harder optimization problem, a transient-aware deformation auxiliary module is proposed. We conduct extensive experiments on both multi-view and monocular scenes to verify the merits of our work. Compared with the baselines, our method shows significant superiority in both rendering quality and efficiency.
We propose a deep learning based novel prediction framework for enhanced bandwidth reduction in motion transfer enabled video applications such as video conferencing, virtual reality gaming and privacy preservation for patient health monitoring. To model complex motion, we use the First Order Motion Model (FOMM) that represents dynamic objects using learned keypoints along with their local affine transformations. Keypoints are extracted by a self-supervised keypoint detector and organized in a time series corresponding to the video frames. Prediction of keypoints, to enable transmission using lower frames per second on the source device, is performed using a Variational Recurrent Neural Network (VRNN). The predicted keypoints are then synthesized to video frames using an optical flow estimator and a generator network. This efficacy of leveraging keypoint based representations in conjunction with VRNN based prediction for both video animation and reconstruction is demonstrated on three diverse datasets. For real-time applications, our results show the effectiveness of our proposed architecture by enabling up to 2x additional bandwidth reduction over existing keypoint based video motion transfer frameworks without significantly compromising video quality.
Real-time high-accuracy optical flow estimation is a crucial component in various applications, including localization and mapping in robotics, object tracking, and activity recognition in computer vision. While recent learning-based optical flow methods have achieved high accuracy, they often come with heavy computation costs. In this paper, we propose a highly efficient optical flow architecture, called NeuFlow, that addresses both high accuracy and computational cost concerns. The architecture follows a global-to-local scheme. Given the features of the input images extracted at different spatial resolutions, global matching is employed to estimate an initial optical flow on the 1/16 resolution, capturing large displacement, which is then refined on the 1/8 resolution with lightweight CNN layers for better accuracy. We evaluate our approach on Jetson Orin Nano and RTX 2080 to demonstrate efficiency improvements across different computing platforms. We achieve a notable 10x-80x speedup compared to several state-of-the-art methods, while maintaining comparable accuracy. Our approach achieves around 30 FPS on edge computing platforms, which represents a significant breakthrough in deploying complex computer vision tasks such as SLAM on small robots like drones. The full training and evaluation code is available at https://github.com/neufieldrobotics/NeuFlow.
Surgical instrument segmentation in laparoscopy is essential for computer-assisted surgical systems. Despite the Deep Learning progress in recent years, the dynamic setting of laparoscopic surgery still presents challenges for precise segmentation. The nnU-Net framework excelled in semantic segmentation analyzing single frames without temporal information. The framework's ease of use, including its ability to be automatically configured, and its low expertise requirements, have made it a popular base framework for comparisons. Optical flow (OF) is a tool commonly used in video tasks to estimate motion and represent it in a single frame, containing temporal information. This work seeks to employ OF maps as an additional input to the nnU-Net architecture to improve its performance in the surgical instrument segmentation task, taking advantage of the fact that instruments are the main moving objects in the surgical field. With this new input, the temporal component would be indirectly added without modifying the architecture. Using CholecSeg8k dataset, three different representations of movement were estimated and used as new inputs, comparing them with a baseline model. Results showed that the use of OF maps improves the detection of classes with high movement, even when these are scarce in the dataset. To further improve performance, future work may focus on implementing other OF-preserving augmentations.
Unsupervised video-based surgical instrument segmentation has the potential to accelerate the adoption of robot-assisted procedures by reducing the reliance on manual annotations. However, the generally low quality of optical flow in endoscopic footage poses a great challenge for unsupervised methods that rely heavily on motion cues. To overcome this limitation, we propose a novel approach that pinpoints motion boundaries, regions with abrupt flow changes, while selectively discarding frames with globally low-quality flow and adapting to varying motion patterns. Experiments on the EndoVis2017 VOS and EndoVis2017 Challenge datasets show that our method achieves mean Intersection-over-Union (mIoU) scores of 0.75 and 0.72, respectively, effectively alleviating the constraints imposed by suboptimal optical flow. This enables a more scalable and robust surgical instrument segmentation solution in clinical settings. The code will be publicly released.
Ego-to-exo video generation refers to generating the corresponding exocentric video according to the egocentric video, providing valuable applications in AR/VR and embodied AI. Benefiting from advancements in diffusion model techniques, notable progress has been achieved in video generation. However, existing methods build upon the spatiotemporal consistency assumptions between adjacent frames, which cannot be satisfied in the ego-to-exo scenarios due to drastic changes in views. To this end, this paper proposes an Intention-Driven Ego-to-exo video generation framework (IDE) that leverages action intention consisting of human movement and action description as view-independent representation to guide video generation, preserving the consistency of content and motion. Specifically, the egocentric head trajectory is first estimated through multi-view stereo matching. Then, cross-view feature perception module is introduced to establish correspondences between exo- and ego- views, guiding the trajectory transformation module to infer human full-body movement from the head trajectory. Meanwhile, we present an action description unit that maps the action semantics into the feature space consistent with the exocentric image. Finally, the inferred human movement and high-level action descriptions jointly guide the generation of exocentric motion and interaction content (i.e., corresponding optical flow and occlusion maps) in the backward process of the diffusion model, ultimately warping them into the corresponding exocentric video. We conduct extensive experiments on the relevant dataset with diverse exo-ego video pairs, and our IDE outperforms state-of-the-art models in both subjective and objective assessments, demonstrating its efficacy in ego-to-exo video generation.
As the use of neuromorphic, event-based vision sensors expands, the need for compression of their output streams has increased. While their operational principle ensures event streams are spatially sparse, the high temporal resolution of the sensors can result in high data rates from the sensor depending on scene dynamics. For systems operating in communication-bandwidth-constrained and power-constrained environments, it is essential to compress these streams before transmitting them to a remote receiver. Therefore, we introduce a flow-based method for the real-time asynchronous compression of event streams as they are generated. This method leverages real-time optical flow estimates to predict future events without needing to transmit them, therefore, drastically reducing the amount of data transmitted. The flow-based compression introduced is evaluated using a variety of methods including spatiotemporal distance between event streams. The introduced method itself is shown to achieve an average compression ratio of 2.81 on a variety of event-camera datasets with the evaluation configuration used. That compression is achieved with a median temporal error of 0.48 ms and an average spatiotemporal event-stream distance of 3.07. When combined with LZMA compression for non-real-time applications, our method can achieve state-of-the-art average compression ratios ranging from 10.45 to 17.24. Additionally, we demonstrate that the proposed prediction algorithm is capable of performing real-time, low-latency event prediction.
3D object detection is one of the most important components in any Self-Driving stack, but current state-of-the-art (SOTA) lidar object detectors require costly & slow manual annotation of 3D bounding boxes to perform well. Recently, several methods emerged to generate pseudo ground truth without human supervision, however, all of these methods have various drawbacks: Some methods require sensor rigs with full camera coverage and accurate calibration, partly supplemented by an auxiliary optical flow engine. Others require expensive high-precision localization to find objects that disappeared over multiple drives. We introduce a novel self-supervised method to train SOTA lidar object detection networks which works on unlabeled sequences of lidar point clouds only, which we call trajectory-regularized self-training. It utilizes a SOTA self-supervised lidar scene flow network under the hood to generate, track, and iteratively refine pseudo ground truth. We demonstrate the effectiveness of our approach for multiple SOTA object detection networks across multiple real-world datasets. Code will be released.