Changfeng Ma

Yifen Ke, Changfeng Ma, Zhigang Jia et al.

To address the non-negativity dropout problem of quaternion models, a novel quasi non-negative quaternion matrix factorization (QNQMF) model is presented for color image processing. To implement QNQMF, the quaternion projected gradient algorithm and the quaternion alternating direction method of multipliers are proposed via formulating QNQMF as the non-convex constraint quaternion optimization problems. Some properties of the proposed algorithms are studied. The numerical experiments on the color image reconstruction show that these algorithms encoded on the quaternion perform better than these algorithms encoded on the red, green and blue channels. Furthermore, we apply the proposed algorithms to the color face recognition. Numerical results indicate that the accuracy rate of face recognition on the quaternion model is better than on the red, green and blue channels of color image as well as single channel of gray level images for the same data, when large facial expressions and shooting angle variations are presented.

Xiaoyu Zhan, Wenxuan Huang, Hao Sun et al.

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved 2D visual understanding, prompting interest in their application to complex 3D reasoning tasks. However, it remains unclear whether these models can effectively capture the detailed spatial information required for robust real-world performance, especially cross-view consistency, a key requirement for accurate 3D reasoning. Considering this issue, we introduce Viewpoint Learning, a task designed to evaluate and improve the spatial reasoning capabilities of MLLMs. We present the Viewpoint-100K dataset, consisting of 100K object-centric image pairs with diverse viewpoints and corresponding question-answer pairs. Our approach employs a two-stage fine-tuning strategy: first, foundational knowledge is injected to the baseline MLLM via Supervised Fine-Tuning (SFT) on Viewpoint-100K, resulting in significant improvements across multiple tasks; second, generalization is enhanced through Reinforcement Learning using the Group Relative Policy Optimization (GRPO) algorithm on a broader set of questions. Additionally, we introduce a hybrid cold-start initialization method designed to simultaneously learn viewpoint representations and maintain coherent reasoning thinking. Experimental results show that our approach significantly activates the spatial reasoning ability of MLLM, improving performance on both in-domain and out-of-domain reasoning tasks. Our findings highlight the value of developing foundational spatial skills in MLLMs, supporting future progress in robotics, autonomous systems, and 3D scene understanding.

Changfeng Ma, Pengxiao Guo, Shuangyu Yang et al.

Structural representation is crucial for reconstructing and generating editable 3D shapes with part semantics. Recent 3D shape generation works employ complicated networks and structure definitions relying on hierarchical annotations and pay less attention to the details inside parts. In this paper, we propose the method that parameterizes the shared structure in the same category using a differentiable template and corresponding fixed-length parameters. Specific parameters are fed into the template to calculate cuboids that indicate a concrete shape. We utilize the boundaries of three-view drawings of each cuboid to further describe the inside details. Shapes are represented with the parameters and three-view details inside cuboids, from which the SDF can be calculated to recover the object. Benefiting from our fixed-length parameters and three-view details, our networks for reconstruction and generation are simple and effective to learn the latent space. Our method can reconstruct or generate diverse shapes with complicated details, and interpolate them smoothly. Extensive evaluations demonstrate the superiority of our method on reconstruction from point cloud, generation, and interpolation.