cs.CV（2026-09-17）

📊 共 36 篇论文 | 🔗 9 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (12 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗2) 支柱六：视频提取与匹配 (Video Extraction) (4 🔗3) 支柱一：机器人控制 (Robot Control) (3 🔗1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (12 篇)

#题目一句话要点标签🔗⭐
1 VGGT-GS SLAM: Uncalibrated Monocular Gaussian Splatting SLAM with Feed-Forward Priors 提出VGGT-GS SLAM以解决未标定视频的三维重建问题 3D gaussian splatting gaussian splatting splatting
2 EliGSiR: Continual RGB-D Mapping with Gaussian Splatting under Bounded Compute 提出EliGSiR以解决持续RGB-D映射中的优化预算问题 3D gaussian splatting gaussian splatting splatting
3 PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping 提出PerSeM以解决无人机长时间开放词汇映射中的语义不一致问题 semantic mapping semantic map open-vocabulary
4 CitySTAR: Structured and Topology-Aware Reasoning for Open-Vocabulary Urban 3D Grounding 提出CitySTAR以解决开放词汇城市3D定位问题 open-vocabulary open vocabulary multimodal
5 BinoGen: Scaling egocentric binocular data for embodied visual perception and learning 提出BinoGen以解决大规模自我中心双目数据收集难题 depth estimation semantic map optical flow
6 PhGS: Post-Hoc Pruning and Refinement of Single-View Feed-Forward 3D Gaussian Reconstructions 提出后处理修剪与精炼方法以优化单视图3D高斯重建 3D gaussian splatting 3DGS gaussian splatting
7 RawSLAM: Online HDR Gaussian SLAM from Linear Radiance 提出RawSLAM以解决极端光照下的SLAM问题 visual SLAM gaussian splatting splatting
8 Earth Surface Immune System for Rapid Monitoring of Unknown Anomalies 提出地球表面免疫系统以快速监测未知异常问题 open-vocabulary open vocabulary foundation model
9 GAPrompt++: Multi-Granular Geometry-Aware Point Cloud Prompt for 3D Vision Model 提出GAPrompt++以解决点云适应性不足问题 3D gaussian splatting gaussian splatting splatting
10 GRF-Recon: Global Ray-Field Optimization for Long-Sequence Feed-forward Reconstruction 提出GRF-Recon以解决长序列单目重建中的全局一致性问题 3D reconstruction
11 SnapPhysics: A Physics-Aware Scene Graph from a Single View for Interactive Mixed Reality Scenes 提出SnapPhysics以解决单视图物理属性估计问题 3D reconstruction ✅
12 PerSeM: Persistent Semantic Memory for Long-Horizon Open-Vocabulary UAV Mapping 提出PerSeM以解决无人机长时间开放词汇映射中的语义不一致问题 semantic mapping semantic map open-vocabulary

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
13 AgriScope: Pixel-Grounded Multimodal Understanding for Agricultural Images 提出AgriScope以解决农业图像理解中的多模态问题 large language model multimodal instruction following ✅
14 Beyond Patch Removal: Persistent Adversarial Effects in Vision-Language-Action Policies 提出状态恢复协议以解决视觉-语言-动作策略中的对抗性影响问题 vision-language-action VLA OpenVLA
15 Can 4D Foundation Models Remember? 提出PersistBench以解决4D模型记忆能力不足问题 foundation model
16 FreqDINO++: A Frequency-Guided Multi-Task Routing Vision Foundation Model for Universal Ultrasound Analysis 提出FreqDINO++以解决超声图像分析中的多任务挑战 foundation model ✅
17 QCPruner: Query-Conditioned Population Coverage for Visual Token Pruning 提出QCPruner以解决多模态大语言模型中的视觉令牌修剪问题 large language model multimodal
18 Scientific Image Quality Assessment via Multi-modal Retrieval-Augmented Generation 提出多模态检索增强生成框架以解决科学图像质量评估问题 large language model multimodal
19 Grounded Product Understanding in Livestream Videos 提出GPUB基准以解决电商直播中的产品理解问题 multimodal
20 Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding 提出安全认知场景否定理解框架以解决多模态大语言模型的偏差问题 large language model
21 MemeTAG: Keyword-Driven Meme Classification through Tag Embedding Reconstruction 提出MemeTAG以解决有害网络表情包自动分类问题 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
22 Cross-Architecture Foundation-Model Distillation for Edge Flood Segmentation 提出跨架构基础模型蒸馏以解决边缘洪水分割问题 distillation foundation model
23 Astronex-World 1.0: Real-Time Interactive World Model Foundation 提出Astronex-World 1.0以实现实时交互式世界模型生成 world model world models
24 GS-PI: An Optimization-Decoupled Appearance Decomposition Approach for Generating PBR Gaussian Assets 提出GS-PI以解决PBR资产生成中的光照与几何耦合问题 distillation gaussian splatting splatting
25 FlowSGS: Improving Flow Matching Priors for Inverse Imaging with Stochastic Interpolants 提出FlowSGS以解决流匹配先验在逆成像中的不足问题 flow matching
26 Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement 提出教师预测精炼蒸馏以提升检测变换器的性能 distillation ✅
27 Instance Segmentation and Fine-grained Classification for Urban Buildings with Adaptive Region Dividing and Spatially-Supervised Contrastive Learning 提出自适应区域划分与空间监督对比学习以解决城市建筑实例分割与细粒度分类问题 contrastive learning
28 Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint 提出负向字幕框架以解决安全认知约束下的视觉场景理解问题 representation learning scene understanding
29 MarsFM: Shading-Regularized Flow Matching for Martian Relief Estimation 提出MarsFM以解决火星地形估计问题 flow matching ✅

🔬 支柱六：视频提取与匹配 (Video Extraction) (4 篇)

#题目一句话要点标签🔗⭐
30 AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization 提出AI智能眼镜平台以解决个性化辅助问题 egocentric foundation model multimodal
31 DirtyMoCap: Robust Motion Capture from Unconstrained Markers 提出DirtyMoCap以解决无约束标记的运动捕捉问题 SMPL human motion ✅
32 PROVIA: Procedure State Tracking for Online Mistake Detection in Egocentric Videos 提出PROVIA以解决自我中心视频中的错误检测问题 egocentric ✅
33 SlugTrails: An Egocentric Benchmark for Floor Plan Localization in Large Buildings 提出SlugTrails基准以解决大型建筑室内定位问题 egocentric ✅

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
34 SenseFuse: Label-Free Fusion of Image and Shape Encoders for Open-Vocabulary 3D Instance Segmentation 提出SenseFuse以解决开放词汇3D实例分割问题 manipulation scene understanding open-vocabulary ✅
35 TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation 提出TouchSight以解决无侵入式触觉信号预测问题 manipulation HOI egocentric
36 AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention 提出AnyviewMeter以解决机器人奖励模型视角适应问题 manipulation

⬅️ 返回 cs.CV 首页 · 🏠 返回主页