Training native 3D texture generative models remains a fundamental yet challenging problem, largely due to the limited availability of large-scale, high-quality 3D texture datasets. This scarcity hinders generalization to real-world scenarios. To address this, most existing methods finetune foundation image generative models to exploit their learned visual priors. However, these approaches typically generate only multi-view images and rely on post-processing to produce UV texture maps—an essential representation in modern graphics pipelines. Such two-stage pipelines often suffer from error accumulation and spatial inconsistencies across the 3D surface. In this paper, we introduce SeqTex, a novel end-to-end framework that leverages the visual knowledge encoded in pretrained video foundation models to directly generate complete UV texture maps. Unlike previous methods that model the distribution of UV textures in isolation, SeqTex reformulates the task as a sequence generation problem, enabling the model to learn the joint distribution of multi-view renderings and UV textures. This design effectively transfers the consistent image-space priors from video foundation models into the UV domain. To further enhance performance, we propose several architectural innovations: a decoupled multi-view and UV branch design, geometry-informed attention to guide cross-domain feature alignment, and adaptive token resolution to preserve fine texture details while maintaining computational efficiency. Together, these components allow SeqTex to fully utilize pretrained video priors and synthesize high-fidelity UV texture maps without the need for post-processing. Extensive experiments show that SeqTex achieves state-of-the-art performance on both image-conditioned and text-conditioned 3D texture generation tasks, with superior 3D consistency, texture-geometry alignment, and real-world generalization. Our project page is https://yuanze1024.github.io/SeqTex/.

Recently, indoor 3D object detection has shown impressive progress. However, these improvements have come at the cost of increased memory consumption and longer inference times, making it difficult to apply these methods in practical scenarios. To address this issue, knowledge distillation has emerged as a promising technique for model acceleration. In this paper, we propose the VRDistill framework, the first knowledge distillation framework designed for efficient indoor 3D object detection. Our VRDistill framework includes a refinement module and a soft foreground mask operation to enhance the quality of the distillation. The refinement module utilizes trainable layers to improve the quality of the teacher's votes, while the soft foreground mask operation focuses on foreground votes, further enhancing the distillation performance. Comprehensive experiments on the ScanNet and SUN-RGBD datasets demonstrate the effectiveness and generalization ability of our VRDistill framework.

He Zhu, Junran Wu, Ruomei Liu, Yue Hou, Ze Yuan, Shangzhe Li, Yicheng Pan, Ke Xu. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

While high-quality texture maps are essential for realistic 3D asset rendering, few studies have explored learning directly in the texture space, especially on large-scale datasets. In this work, we depart from the conventional approach of relying on pre-trained 2D diffusion models for testtime optimization of 3D textures. Instead, we focus on the fundamental problem of learning in the UV texture space itself. For the first time, we train a large diffusion model capable of directly generating high-resolution texture maps in a feed-forward manner. To facilitate efficient learning in high-resolution UV spaces, we propose a scalable network architecture that interleaves convolutions on UV maps with attention layers on point clouds. Leveraging this architectural design, we train a 700 million parameter diffusion model that can generate UV texture maps guided by text prompts and single-view images. Once trained, our model naturally supports various extended applications, including text-guided texture inpainting, sparse-view texture completion, and text-driven texture synthesis. The code is available at https://github.com/CVMI-Lab/TEXGen.

Industrial Internet of Things (IIoT) is one of the most important application scenarios of the fifth generation mobile communication. In IIoT applications, the propagation channel differs significantly from the propagation environment of the typical cell communication system. In this paper, two special propagation cases are considered. The sensors/actuators (together with the RF transceiver) sometimes are equipped on the swinging mechanical robot arms (MRAs) and on moving automated guided vehicles (AGVs), which have never been thoroughly investigated, and hence the wireless channel between the sensor/actuator and control center becomes time-varying when the MRA is working and vehicles are moving. A two-dimensional geometrical model for the MRA and a mathematical model of random Doppler offset for AGVs are provided to depict these Doppler frequency trajectories in the industrial propagation environment. By using the realistic measurement data, these Doppler frequency trajectories are verified and the simulated results show good agreements. The established models are informative to design wireless networks for industrial scenarios.

This paper presents a fast charging system for smart devices. A novel scheme of dynamically adjusted charging current based on voltage-current dual-loop control is employed to fully utilize the power of the adaptor and maximize the charging speed. Simulation and experiment show that at least 12% more battery can be charged by the proposed method within 5 minutes of fast charging, compared to the conventional fast charging scheme.

Viewpoint Space Partition based on Aspect Graph is one of the core techniques of 3D object recognition. Projection images obtained from critical viewpoint following this approach can efficiently provide topological information of an object. Computational complexity has been a huge challenge for obtaining the representation viewpoints used in 3D recognition. In this paper, we discuss inefficiency of calculation due to redundant nonexistent visual events; propose a systematic criterion for edge selection involved in EEE events. Pruning algorithm based on concave-convex property is demonstrated. We further introduce intersect relation into our pruning algorithm. These two methods not only enable the calculation of EEE events, but also can be implemented before viewpoint calculation, hence realizes view-independent pruning algorithm. Finally, analysis on simple representative models supports the effectiveness of our methods. Further investigations on Princeton Models, including airplane, automobile, etc, show a two orders of magnitude reduction in the number of EEE events on average.