Stereo video synthesis from monocular input is challenging in spatial computing and virtual reality due to the lack of high-quality stereo video pairs for training and the difficulty of maintaining spatio-temporal consistency between frames. Existing methods primarily address these issues by directly applying novel view synthesis (NVS) techniques to video, while facing limitations such as the inability to effectively represent dynamic scenes and the requirement for extensive training data. In this paper, we introduce a novel self-supervised stereo video synthesis paradigm via a video diffusion model, termed SpatialDreamer, which meets the challenges head-on. Firstly, to address the stereo video data insufficiency, we propose a Depth based Video Generation module DVG, which employs a forward-backward rendering mechanism to generate paired videos with geometric and temporal priors. Leveraging data generated by DVG, we propose RefinerNet along with a self-supervised synthetic framework designed to facilitate efficient and dedicated training. More importantly, we devise a consistency control module, which consists of a metric of stereo deviation strength and a Temporal Interaction Learning module TIL for geometric and temporal consistency ensurance respectively. We evaluated the proposed method against various benchmark methods, with the results showcasing its superior performance. Our project website is at: https://spatialdreamer.github.io.

A domain adaptation scenario called few-shot hypothesis adaptation (FHA) only permits access to the well-trained source model and few labeled target data. Previous works may be misled by the discriminative yet undesirable domain-specific information since they learn the spurious correlation between inputs and predictions. In this work, our goal is to achieve the robust adaptation from the causality perspective. Specifically, we abstract FHA into a Structural Causal Model (SCM) and notice that the domain-specific variables are confounders, which lead to the spurious correlation. To eliminate the negative effects, we propose a novel Causal Interventional Few-shot hypothesis Adaption (CIFA) that consists of sampling, mixing and classification modules to perform backdoor adjustment. We also calculate the optimal solution for better convergence. Experiments on the benchmarks demonstrate the effectiveness of our algorithm.

Although convolutional neural network based stereo matching architectures have made impressive achievements, there are still some limitations: 1) Convolutional Feature (CF) tends to capture appearance information, which is inadequate for accurate matching. 2) Due to the static filters, current convolution based disparity refinement modules often produce over-smooth results. In this paper, we present two schemes to address these issues, where some traditional wisdoms are integrated. Firstly, we introduce a pairwise feature for deep stereo matching networks, named LSP (Local Similarity Pattern). Through explicitly revealing the neighbor relationships, LSP contains rich structural information, which can be leveraged to aid CF for more discriminative feature description. Secondly, we design a dynamic self-reassembling refinement strategy and apply it to the cost distribution and the disparity map respectively. The former could be equipped with the unimodal distribution constraint to alleviate the over-smoothing problem, and the latter is more practical. The effectiveness of the proposed methods is demonstrated via incorporating them into two well-known basic architectures, GwcNet and GANet-deep. Experimental results on the SceneFlow and KITTI benchmarks show that our modules significantly improve the performance of the model. Code is available at https://github.com/SpadeLiu/Lac-GwcNet.