📚 文献库
Literature Library

Read It Back: Pretrained MLLMs Are Zero-Shot Reward 模型 (Model)s for Text-to-Image Generation

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

作者
Authors: Runhui Huang | Qihui Zhang | Zhe Liu | Yu Gao | Ji... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 187 📚 26

PanoWorld: Real-World Panoramic Generation

作者
Authors: Haoyuan Li | Dizhe Zhang | Yuemei Zhou | Xiangkai ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 196 📚 7

LongE2V: Long-Horizon Event-based Video Reconstruction, 预测 (Prediction), and Frame Interpolation wit...

LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Vid...

作者
Authors: Cheng-De Fan | Chun-Wei Tuan Mu | Chen-Wei Chang |... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 55 📚 23

ZipDepth: Bringing Lightweight Zero-Shot Monocular Depth Anywhere, on Any Device

作者
Authors: Fabio Tosi | Luca Bartolomei | Matteo Poggi | Stef... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 64 📚 13

Wat3R: Underwater 3D Geometry 学习 (Learning) without Annotations

Wat3R: Underwater 3D Geometry Learning without Annotations

作者
Authors: Jiangwei Ren | Xingyu Jiang | Zijie Song | Wei Xu ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 130 📚 21

Selective Timestep Weighting and Advantage-Based Replay for Sample-Efficient Diffusion RLHF

作者
Authors: Eric Zhu | Abhinav Shrivastava | Soumik Mukhopadhy... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 38 📚 19

Lift3D-VLA: Lifting VLA 模型 (Model)s to 3D Geometry and Dynamics-Aware Manipulation

Lift3D-VLA: Lifting VLA Models to 3D Geometry and Dynamics-Aware Manipulation

作者
Authors: Jiaming Liu | Qingpo Wuwu | Nuowei Han | Hao Chen ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 86 📚 11

SynCity 3000: Bootstrapping Scene-Scale 3D Diffusion

作者
Authors: Paul Engstler | Iro Laina | Christian Rupprecht | ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 59 📚 26

PointDiT: Pixel-Space Diffusion for Monocular Geometry 估计 (Estimation)

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

作者
Authors: Haofei Xu | Rundi Wu | Philipp Henzler | Nikolai K... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 66 📚 16

Alignment Is All You Need For X-to-4D Generation

作者
Authors: Qiaowei Miao | Kehan Li | Yawei Luo | Yi Yang 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 163 📚 4

WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory

作者
Authors: Hanlin Wang | Hao Ouyang | Qiuyu Wang | Wen Wang |... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 83 📚 15

Lyophilized platelet-rich fibrin (PRF) promotes craniofacial bone regeneration through Runx2.

作者
Authors: Qi Li, David A Reed, Liu Min, Gokul Gopinathan, St... 期刊
Journal: International Journal of Molecular Sciences 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 16 📚 0

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative 模型 (Model)s

Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models

作者
Authors: Yue Han | Chong Li | Zhening Liu | Cong Huang | Fa... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 87 📚 19

FaceMoE: Mixture of Experts for Low-Resolution Face Recognition

作者
Authors: Kartik Narayan | Vishal M. Patel 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 83 📚 18

Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors

作者
Authors: Jameel Hassan | Yasiru Ranasinghe | Vishal Patel 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 77 📚 17

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

作者
Authors: Yana Wei | Hongbo Peng | Yanlin Lai | Liang Zhao |... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 206 📚 19

World Action 模型 (Model)s Enable Continual Imitation 学习 (Learning) with Recurrent Generative Replays

World Action Models Enable Continual Imitation Learning with Recurrent Generative Replays

作者
Authors: Manish Kumar Govind | Dominick Reilly | Smit Patel... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 161 📚 12

Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consist...

作者
Authors: Ritesh Thawkar | Shravan Venkatraman | Omkar Thawa... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 144 📚 11

学习 (Learning) Action Priors for Cross-embodiment Robot Manipulation

Learning Action Priors for Cross-embodiment Robot Manipulation

作者
Authors: Dong Jing | Tianqi Zhang | Jiaqi Liu | Jinman Zhao... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 186 📚 20

DiffusionBench: On Holistic Evaluation of Diffusion Transformers

作者
Authors: Xingjian Leng | Jaskirat Singh | Zhanhao Liang | E... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 166 📚 11