作者：Ziqi Huang Tianxing Wu Yuming Jiang Kelvin C. K. Chan Ziwei Liu 扩散模型因其生成能力而越来越受欢迎。最近，通过…
Read MoreMAE预训练对十亿规模预训练的有效性 The effectiveness of MAE pre-pretraining for billion-scale pretraining
作者：Mannat Singh Quentin Duval Kalyan Vasudev Alwala Haoqi Fan Vaibhav Aggarwal Aaron Adcoc…
Read MoreTriPlaneNet:一种用于EG3D反演的编码器 TriPlaneNet: An Encoder for EG3D Inversion
作者：Ananta R. Bhattarai Matthias Nießner Artem Sevastopolsky 基于NeRF的GANs的最新进展已经引入了许多用于人头的高分…
Read More旗流形上的弦平均及其应用 Chordal Averaging on Flag Manifolds and Its Applications
作者：Nathan Mankovich Tolga Birdal 本文提出了一种新的、可证明收敛的算法，用于在弦度量下计算标志流形上一组点的滞后均值和标志中值。标志流形是一个由标志…
Read More基于动作识别新基准的时空表征学习的大规模研究 A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition
作者：Andong Deng Taojiannan Yang Chen Chen 建立基准（数据集套件）的目标是为公平评估提供统一的协议，从而促进特定领域的发展。尽管如此，我们指出…
Read MoreReBotNet：快速实时视频增强 ReBotNet: Fast Real-time Video Enhancement
作者：Jeya Maria Jose Valanarasu Rahul Garg Andeep Toor Xin Tong Weijuan Xi Andreas Lugmayr V…
Read MoreDreamBooth3D：主题驱动的文本到3D生成 DreamBooth3D: Subject-Driven Text-to-3D Generation
作者：Amit Raj Srinivas Kaza Ben Poole Michael Niemeyer Nataniel Ruiz Ben Mildenhall Shiran Z…
Read MoreMV-JAR:用于基于激光雷达的自监督预训练的掩模体素拼图和重建 MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-Based Self-Supervised Pre-Training
作者：Runsen Xu Tai Wang Wenwei Zhang Runjian Chen Jinkun Cao Jiangmiao Pang Dahua Lin 本文介绍了用…
Read More位置引导点云泛光分割转换器 Position-Guided Point Cloud Panoptic Segmentation Transformer
作者：Zeqi Xiao Wenwei Zhang Tai Wang Chen Change Loy Dahua Lin Jiangmiao Pang DEtection-TRan…
Read More颜色风格转换的神经预设 Neural Preset for Color Style Transfer
作者：Zhanghan Ke Yuhao Liu Lei Zhu Nanxuan Zhao Rynson W. H. Lau 在本文中，我们提出了一种神经预设技术来解决现有颜色风格…
Read More