📚 文献库
Literature Library

Exploring Easy Boosts for Lidar Semantic Scene Completion

作者
Authors: Tetiana Martyniuk | Jonathan Seele | Alexandre Bou... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 89 📚 3

Representation Forcing for Bottleneck-Free Unified Multimodal 模型 (Model)s

Representation Forcing for Bottleneck-Free Unified Multimodal Models

作者
Authors: Yuqing Wang | Zhijie Lin | Ceyuan Yang | Yang Zhao... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 207 📚 5

AdaState: Self-Evolving Anchors for Streaming Video Generation

作者
Authors: Yusuf Dalva | Pinar Yanardag 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 188 📚 3

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion

作者
Authors: Hidir Yesiltepe | Jiazhen Hu | Tuna Han Salih Mera... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 85 📚 22

GMOS: Grounding Moving Object Segmentation in 3D Space and Time

作者
Authors: Junyu Xie | Tengda Han | Weidi Xie | Andrew Zisser... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 181 📚 16

From Pixels to Words -- Towards Native One-Vision 模型 (Model)s at Scale

From Pixels to Words -- Towards Native One-Vision Models at Scale

作者
Authors: Haiwen Diao | Jiahao Wang | Penghao Wu | Yuhao Don... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 187 📚 4

G3T Up! Gravity Aligned Coordinate Frames Simplify Pointmap Processing

作者
Authors: Bharath Raj Nagoor Kani | Noah Snavely 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 121 📚 11

TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction

作者
Authors: Weijie Wang | Zimu Li | Jinchuan Shi | Zeyu Zhang ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 168 📚 17

Geo-Align: Video Generation Alignment via Metric Geometry Reward

作者
Authors: Zizun Li | Haoyu Guo | Runzhe Teng | Chunhua Shen ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 59 📚 10

MotiMotion: Motion-Controlled Video Generation with Visual Reasoning

作者
Authors: Lee Hsin-Ying | Hanwen Jiang | Yiqun Mei | Jing Sh... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 158 📚 17

Cambrian-P: Pose-Grounded Video Understanding

作者
Authors: Jihan Yang | Zifan Zhao | Xichen Pan | Shusheng Ya... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 157 📚 16

Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs

作者
Authors: Jongseo Lee | Hyuntak Lee | Sunghun Kim | Sooa Kim... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 64 📚 3

Uni-Edit: Intelligent Editing Is A General Task For Unified 模型 (Model) Tuning

Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning

作者
Authors: Dian Zheng | Manyuan Zhang | Hongyu Li | Hongbo Li... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 68 📚 2

PiG-Avatar: Hierarchical Neural-Field-Guided Gaussian Avatars

作者
Authors: Julian Kaltheuner | Jan Spindler | Sina Kitz | Pat... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 186 📚 17

Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation 模型 (Model)s Hal...

Can These Views Be One Scene? Evaluating Multiview 3D Consistency when 3D Foundation Models Hallucin...

作者
Authors: Soumava Paul | Prakhar Kaushik | Alan Yuille 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 200 📚 12

IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation

作者
Authors: Yuqi Wu | Tianyu Hu | Wenzhao Zheng | Yuanhui Huan... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 195 📚 3

EntityBench: Towards Entity-Consistent Long-Range Multi-Shot Video Generation

作者
Authors: Ruozhen He | Meng Wei | Ziyan Yang | Vicente Ordon... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 95 📚 12

R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow

作者
Authors: Zijie Wu | Lixin Xu | Puhua Jiang | Sicong Liu | C... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 186 📚 27

Covering Human Action Space for Computer Use: 数据 (Data) Synthesis and Benchmark

Covering Human Action Space for Computer Use: Data Synthesis and Benchmark

作者
Authors: Miaosen Zhang | Xiaohan Zhao | Zhihong Tan | Zhou ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 60 📚 6

Power Reinforcement Post-Training of Text-to-Image 模型 (Model)s with Super-Linear Advantage Shaping

Power Reinforcement Post-Training of Text-to-Image Models with Super-Linear Advantage Shaping

作者
Authors: Haoyuan Sun | Jing Wang | Yuxin Song | Yu Lu | Bo ... 期刊
Journal: arXiv 年份
Year: 2026 分类
Category: 计算机视觉
Computer Vision

👁 211 📚 0