Stereo videos for the dynamic scenes often show unpleasant blurred effects due to the camera motion and the multiple moving objects with large depth variations. Given consecutive blurred stereo video frames, we aim to recover the latent clean images, estimate the 3D scene flow and segment the multiple moving objects. These three tasks have been previously addressed separately, which fail to exploit the internal connections among these tasks and cannot achieve optimality. In this paper, we propose to jointly solve these three tasks in a unified framework by exploiting their intrinsic connections. To this end, we represent the dynamic scenes with the piece-wise planar model, which exploits the local structure of the scene and expresses various dynamic scenes. Under our model, these three tasks are naturally connected and expressed as the parameter estimation of 3D scene structure and camera motion (structure and motion for the dynamic scenes). By exploiting the blur model constraint, the moving objects and the 3D scene structure, we reach an energy minimization formulation for joint deblurring, scene flow and segmentation. We evaluate our approach extensively on both synthetic datasets and publicly available real datasets with fast-moving objects, camera motion, uncontrolled lighting conditions and shadows. Experimental results demonstrate that our method can achieve significant improvement in stereo video deblurring, scene flow estimation and moving object segmentation, over state-of-the-art methods.

Deep neural networks have achieved significant success in image dehazing. However, existing backbones face an irreconcilable trade-off between the global receptive field and computational efficiency, hindering further applications. State space models, such as Mamba, offer a potential solution to this conflict by modeling long-range dependencies with linear complexity. Although Mamba is well-suited for sequential tasks (e.g., natural language processing), it still encounters challenges when applied to low-level vision tasks. In this work, we propose a large multi-modal model (LMM) guided, Mamba-based image dehazing method (DehazeMamba). It enhances the standard Mamba architecture by incorporating image quality priors provided by the LMM and a channel attention mechanism. Additionally, we present a challenging image dehazing dataset and conduct new benchmark studies based on the LMM, evaluating hazy images and dehazing results by simulating human perception. Our experimental results demonstrate that our dataset exhibits superior haze quality, and our method outperforms current state-of-the-art (SOTA) dehazing methods by achieving a performance improvement of more than 5% on both the O-Haze and Dense-Haze datasets.

The artificial neuron (N-N) model-based networks have accomplished extraordinary success for various vision tasks. However, as a simplification of the mammal neuron model, their structure is locked during training, resulting in overfitting and over-parameters. The astrocyte, newly explored by biologists, can adaptively modulate neuronal communication by inserting itself between neurons. The communication, between the astrocyte and neuron, is bidirectionally and shows the potential to alleviate issues raised by unidirectional communication in the N-N model. In this paper, we first elaborate on the artificial Multi-Astrocyte-Neuron (MA-N) model, which enriches the functionality of the artificial neuron model. Our MA-N model is formulated at both astrocyte- and neuron-level that mimics the bidirectional communication with temporal and joint mechanisms. Then, we construct the MA-Net network with the MA-N model, whose neural connections can be continuously and adaptively modulated during training. Experiments show that our MA-Net advances new state-of-the-art on multiple tasks while significantly reducing its parameters by connection optimization.