Recently, Gaussian Splatting (GS) has shown great potential for urban scene reconstruction in the field of autonomous driving. However, current urban scene reconstruction methods often depend on multimodal sensors as inputs, $\textit{i.e.}$ LiDAR and images. Though the geometry prior provided by LiDAR point clouds can largely mitigate ill-posedness in reconstruction, acquiring such accurate LiDAR data is still challenging in practice: i) precise spatiotemporal calibration between LiDAR and other sensors is required, as they may not capture data simultaneously; ii) reprojection errors arise from spatial misalignment when LiDAR and cameras are mounted at different locations. To avoid the difficulty of acquiring accurate LiDAR depth, we propose ${D}^2GS$, a LiDAR-free urban scene reconstruction framework. In this work, we obtain geometry priors that are as effective as LiDAR while being denser and more accurate. $\textbf{First}$, we initialize a dense point cloud by back-projecting multi-view metric depth predictions. This point cloud is then optimized by a Progressive Pruning strategy to improve the global consistency. $\textbf{Second}$, we jointly refine Gaussian geometry and predicted dense metric depth via a Depth Enhancer. Specifically, we leverage diffusion priors from a depth foundation model to enhance the depth maps rendered by Gaussians. In turn, the enhanced depths provide stronger geometric constraints during Gaussian training. $\textbf{Finally}$, we improve the accuracy of ground geometry by constraining the shape and normal attributes of Gaussians within road regions. Extensive experiments on the Waymo dataset demonstrate that our method consistently outperforms state-of-the-art methods, producing more accurate geometry even when compared with those using ground-truth LiDAR data.

Computed Tomography (CT) is an advanced imaging technology. To obtain high-resolution (HR) CT images from low-resolution (LR) sinograms, we present a deep-learning (DL) based CT super-resolution (SR) method.The proposed method combines a SR model in the sinogram domain and the iterative framework into a CT SR algorithm. We unrolled the proposed method into a DL network (SRECT-Net) for adaptive estimation of inherent blurring effects causing by the insufficient sampling of LR X-Ray detector. For CT systems, if the scanning protocol is fixed, the system blur effect will remain relatively stable. Inspired by this fact, the proposed methods can be pre-trained with amounts of simulated datasets, effectively fine-tuned with just a single sample, and then obtain a machine-specific SR model. The proposed SRECT was evaluated via SR CT imaging of a Catphan700phantom and a ham, whose performance was compared to the other DL-based CT SR methods. The results show that the proposed SRECT can provide a CT SR reconstruction performance superior to the other state-of-the-art CT SR methods, demonstrating the potential use in improving CT resolution beyond its hardware limit, lowering the requirement of CT hardware, or reducing X-Ray dose during CT imaging.

This paper presents Uncertainty-aware Contrastive Learning (UCoL): a fully unsupervised framework for discriminative facial representation learning. Our UCoL is built upon a momentum contrastive network, referred to as Dual-path Momentum Network. Specifically, two flows of pairwise contrastive training are conducted simultaneously: one is formed with intra-instance self augmentation, and the other is to identify positive pairs collected by online pairwise prediction. We introduce a novel uncertainty-aware consistency K-nearest neighbors algorithm to generate predicted positive pairs, which enables efficient discriminative learning from large-scale open-world unlabeled data. Experiments show that UCoL significantly improves the baselines of unsupervised models and performs on par with the semi-supervised and supervised face representation learning methods.

Real-world dynamic scene deblurring has long been a challenging task since paired blurry-sharp training data is unavailable. Conventional Maximum A Posteriori estimation and deep learning-based deblurring methods are restricted by handcrafted priors and synthetic blurry-sharp training pairs respectively, thereby failing to generalize to real dynamic blurriness. To this end, we propose a Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data. The proposed NeruMAP consists of a motion estimation network and a deblurring network which are trained jointly to model the (re)blurring process (i.e. likelihood function). Meanwhile, the motion estimation network is trained to explore the motion information in images by applying implicit dynamic motion prior, and in return enforces the deblurring network training (i.e. providing sharp image prior). The proposed NeurMAP is an orthogonal approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets. Experiments demonstrate our superiority on both quantitative metrics and visual quality over State-of-the-art methods.

The training of deep learning-based image deblurring models heavily relies on the paired sharp/blurry image dataset. Although many works verified that synthesized blurry-sharp pairs contribute to improving the deblurring performance, it is still an open problem about how to synthesize realistic and diverse dynamic blurry images. Instead of directly synthesizing blurry images, in this paper, we propose a novel method to generate semantic-aware dense dynamic motion, and employ the generated motion to synthesize blurry images. Specifically, for each sharp image, both the global motion (camera shake) and local motion (object moving) are considered given the depth information as the condition. Then, a blur creation module takes the spatial-variant motion information and the sharp image as input to synthesize a motion-blurred image. A relativistic GAN loss is employed to assure the synthesized blurry image is as realistic as possible. Experiments show that our method can generate diverse dynamic motion and visually realistic blurry images. Also, the generated image pairs can further improve the quantitative performance and generalization ability of the existing deblurring method on several test sets.

Motion blur in dynamic scenes is an important yet challenging research topic. Recently, deep learning methods have achieved impressive performance for dynamic scene deblurring. However, the motion information contained in a blurry image has yet to be fully explored and accurately formulated because: (i) the ground truth of dynamic motion is difficult to obtain; (ii) the temporal ordering is destroyed during the exposure; and (iii) the motion estimation from a blurry image is highly ill-posed. By revisiting the principle of camera exposure, motion blur can be described by the relative motions of sharp content with respect to each exposed position. In this paper, we define exposure trajectories, which represent the motion information contained in a blurry image and explain the causes of motion blur. A novel motion offset estimation framework is proposed to model pixel-wise displacements of the latent sharp image at multiple timepoints. Under mild constraints, our method can recover dense, (non-)linear exposure trajectories, which significantly reduce temporal disorder and ill-posed problems. Finally, experiments demonstrate that the recovered exposure trajectories not only capture accurate and interpretable motion information from a blurry image, but also benefit motion-aware image deblurring and warping-based video extraction tasks. Codes are available on https://github.com/yjzhang96/Motion-ETR.

Video frame interpolation, which aims to synthesize non-exist intermediate frames in a video sequence, is an important research topic in computer vision. Existing video frame interpolation methods have achieved remarkable results under specific assumptions, such as instant or known exposure time. However, in complicated real-world situations, the temporal priors of videos, i.e. frames per second (FPS) and frame exposure time, may vary from different camera sensors. When test videos are taken under different exposure settings from training ones, the interpolated frames will suffer significant misalignment problems. In this work, we solve the video frame interpolation problem in a general situation, where input frames can be acquired under uncertain exposure (and interval) time. Unlike previous methods that can only be applied to a specific temporal prior, we derive a general curvilinear motion trajectory formula from four consecutive sharp frames or two consecutive blurry frames without temporal priors. Moreover, utilizing constraints within adjacent motion trajectories, we devise a novel optical flow refinement strategy for better interpolation results. Finally, experiments demonstrate that one well-trained model is enough for synthesizing high-quality slow-motion videos under complicated real-world situations. Codes are available on https://github.com/yjzhang96/UTI-VFI.