English
Related papers

Related papers: VersaQ-3D: A Reconfigurable Accelerator Enabling F…

200 papers

Recently, linear complexity sequence modeling networks have achieved modeling capabilities similar to Vision Transformers on a variety of computer vision tasks, while using fewer FLOPs and less memory. However, their advantage in terms of…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Bencheng Liao , Xinggang Wang , Lianghui Zhu , Qian Zhang , Chang Huang

While high fidelity and efficiency are central to the creation of digital head avatars, recent methods relying on 2D or 3D generative models often experience limitations such as shape distortion, expression inaccuracy, and identity…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Xiaochen Zhao , Jingxiang Sun , Lizhen Wang , Jinli Suo , Yebin Liu

Recent advancements in implicit neural representations have contributed to high-fidelity surface reconstruction and photorealistic novel view synthesis. However, the computational complexity inherent in these methodologies presents a…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Yiying Yang , Wen Liu , Fukun Yin , Xin Chen , Gang Yu , Jiayuan Fan , Tao Chen

This work explores a simple yet powerful lightweight adapter design for feed-forward 3D Gaussian Splatting (3DGS). Existing methods typically apply complex, architecture-specific designs on top of the generic pipeline of image feature…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mingwei Xing , Xinliang Wang , Yifeng Shi

Transformer uses GPU as the initial design platform, but GPU can only perform limited hardware customization. Although FPGA has strong customization ability, the design solution space is huge and the design difficulty is high. Versal ACAP…

Hardware Architecture · Computer Science 2024-09-17 Wenbo Zhang , Yiqi Liu , Zhenshan Bao

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has motivated extending these models to understand 3D scenes, aiming for human-like visual-spatial intelligence. Nevertheless, achieving deep spatial…

3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subsequent operations like offset learning, attention weighting, and cross-camera aggregation…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Xun Chen , Tianchen Deng , Rui Wang , Fangjinhua Wang , Junyi Ma , Hongming Shen , Hesheng Wang , Danwei Wang

Limited-angle computed tomography (LACT) offers the advantages of reduced radiation dose and shortened scanning time. Traditional reconstruction algorithms exhibit various inherent limitations in LACT. Currently, most deep learning-based…

Image and Video Processing · Electrical Eng. & Systems 2026-02-03 Yiyang Wen , Liu Shi , Zekun Zhou , WenZhe Shan , Qiegen Liu

Dense visual odometry (VO), which provides pose estimation and dense 3D reconstruction, serves as the cornerstone for applications ranging from robotics to augmented reality. Recently, feed-forward models have demonstrated remarkable…

Robotics · Computer Science 2026-04-03 Junxiang Pan , Lipu Zhou , Baojie Chen

Deploying large-scale transformer models on edge devices presents significant challenges due to strict constraints on memory, compute, and latency. In this work, we propose a lightweight yet effective multi-stage optimization pipeline…

Machine Learning · Computer Science 2025-12-24 Shoaib Mohammad , Guanqun Song , Ting Zhu

Video stabilization is pivotal for video processing, as it removes unwanted shakiness while preserving the original user motion intent. Existing approaches, depending on the domain they operate, suffer from several issues (e.g. geometric…

Graphics · Computer Science 2025-07-21 Zinuo You , Stamatios Georgoulis , Anpei Chen , Siyu Tang , Dengxin Dai

3D Gaussian splatting (3DGS) has demonstrated impressive performance in synthesizing high-fidelity novel views. Nonetheless, its effectiveness critically depends on the quality of the initialized point cloud. Specifically, achieving uniform…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Yikang Zhang , Rui Fan

Recently, 3D Gaussian Splatting has emerged as a prominent research direction owing to its ultrarapid training speed and high-fidelity rendering capabilities. However, the unstructured and irregular nature of Gaussian point clouds poses…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Xiao Ren , Yu Liu , Ning An , Jian Cheng , Xin Qiao , He Kong

3D reconstruction and novel view synthesis are critical for validating autonomous driving systems and training advanced perception models. Recent self-supervised methods have gained significant attention due to their cost-effectiveness and…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Xiao Tang , Guirong Zhuo , Cong Wang , Boyuan Zheng , Minqing Huang , Lianqing Zheng , Long Chen , Shouyi Lu

Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions…

Graphics · Computer Science 2025-07-11 Wei Yao , Shuzhao Xie , Letian Li , Weixiang Zhang , Zhixin Lai , Shiqi Dai , Ke Zhang , Zhi Wang

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

Hardware Architecture · Computer Science 2026-04-29 Mingbo Hao , Changwei Yan , Haoyu Cui , Zhihao Yan , Yizhi Ding , Zhangrui Qian , Weiwei Shan

We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture. Existing methods for generalizable 3D reconstruction either do not scale to…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Christopher Wewer , Kevin Raj , Eddy Ilg , Bernt Schiele , Jan Eric Lenssen

Large reasoning models (LRMs) reach competition-level math and coding accuracy via long autoregressive decoding, making per-token decoding cost a primary deployment concern. Weight quantization is the standard tool for acceleration, but…

Machine Learning · Computer Science 2026-05-12 Euntae Choi , Sumin Song , Sungjoo Yoo

Recent feed-forward reconstruction models like VGGT and $\pi^3$ achieve impressive reconstruction quality but cannot process streaming videos due to quadratic memory complexity, limiting their practical deployment. While existing streaming…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Tianye Ding , Yiming Xie , Yiqing Liang , Moitreya Chatterjee , Pedro Miraldo , Huaizu Jiang

Feed-forward 3D reconstruction models are efficient but rigid: once trained, they perform inference in a zero-shot manner and cannot adapt to the test scene. As a result, visually plausible reconstructions often contain errors, particularly…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Yuhang Dai , Xingyi Yang