cs.CV（2024-03-15）

📊 共 44 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) (19 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (13) 支柱二：RL算法与架构 (RL & Architecture) (8 🔗4) 支柱八：物理动画 (Physics-based Animation) (3 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (19 篇)

#题目一句话要点标签🔗⭐
1 GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time 提出GGRt以解决实时3D高斯点云合成中的相机姿态依赖问题 3D gaussian splatting 3DGS gaussian splatting
2 GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting 提出GS-Pose框架以解决6D物体姿态估计问题 3D gaussian splatting gaussian splatting splatting ✅
3 GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting 提出GeoGS3D以解决单视图3D重建问题 3D reconstruction gaussian splatting splatting
4 Texture-GS: Disentangling the Geometry and Texture for 3D Gaussian Splatting Editing 提出Texture-GS以解决3D高斯点云编辑中的几何与纹理耦合问题 3D gaussian splatting gaussian splatting splatting
5 Thermal-NeRF: Neural Radiance Fields from an Infrared Camera 提出Thermal-NeRF以解决低光照条件下的3D重建问题 NeRF neural radiance field scene reconstruction
6 Enhancing Human-Centered Dynamic Scene Understanding via Multiple LLMs Collaborated Reasoning 提出V-HOI MLCR框架以提升动态场景中的人机交互理解能力 scene understanding human-object interaction HOI
7 URS-NeRF: Unordered Rolling Shutter Bundle Adjustment for Neural Radiance Fields 提出URS-NeRF以解决无序滚动快门图像的3D重建问题 NeRF neural radiance field
8 SWAG: Splatting in the Wild images with Appearance-conditioned Gaussians 提出SWAG以解决野外图像中3D高斯渲染问题 3D gaussian splatting gaussian splatting splatting
9 Leveraging Neural Radiance Field in Descriptor Synthesis for Keypoints Scene Coordinate Regression 提出基于神经辐射场的特征描述子合成以解决数据稀缺问题 NeRF neural radiance field ✅
10 DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video 提出DyBluRF以解决动态场景中的运动模糊问题 NeRF neural radiance field
11 Den-SOFT: Dense Space-Oriented Light Field DataseT for 6-DOF Immersive Experience 提出Den-SOFT以解决大空间稠密光场数据集缺乏问题 3DGS 3D reconstruction NeRF
12 NeuFlow: Real-time, High-accuracy Optical Flow Estimation on Robots Using Edge Devices 提出NeuFlow以解决机器人实时光流估计的高效性问题 optical flow ✅
13 SwinMTL: A Shared Architecture for Simultaneous Depth Estimation and Semantic Segmentation from Monocular Camera Images 提出SwinMTL框架以同时解决深度估计和语义分割问题 depth estimation ✅
14 Exploring Optical Flow Inclusion into nnU-Net Framework for Surgical Instrument Segmentation 将光流信息引入nnU-Net框架以提升外科器械分割精度 optical flow
15 Motion-Boundary-Driven Unsupervised Surgical Instrument Segmentation in Low-Quality Optical Flow 提出基于运动边界的无监督外科器械分割方法以解决低质量光流问题 optical flow
16 Generative Region-Language Pretraining for Open-Ended Object Detection 提出GenerateU以解决开放式物体检测问题 open-vocabulary open vocabulary
17 Robust Shape Fitting for 3D Scene Abstraction 提出一种鲁棒的形状拟合方法以解决复杂场景抽象问题 depth estimation
18 ViiNeuS: Volumetric Initialization for Implicit Neural Surface reconstruction of urban scenes with limited image overlap 提出ViiNeuS以解决城市场景重建中的视觉重叠不足问题 3D reconstruction
19 Region-aware Distribution Contrast: A Novel Approach to Multi-Task Partially Supervised Learning 提出区域感知分布对比以解决多任务部分监督学习问题 depth estimation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
20 VideoAgent: Long-form Video Understanding with Large Language Model as Agent 提出VideoAgent以解决长视频理解问题 large language model foundation model
21 TransLandSeg: A Transfer Learning Approach for Landslide Semantic Segmentation Based on Vision Foundation Model 提出TransLandSeg以解决滑坡语义分割问题 foundation model
22 Visual Foundation Models Boost Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation 提出VFMSeg以提升3D语义分割的跨模态无监督领域适应能力 foundation model
23 Knowledge Condensation and Reasoning for Knowledge-based VQA 提出知识凝聚与推理模型以解决知识基础视觉问答问题 large language model multimodal
24 Spotter+GPT: Turning Sign Spottings into Sentences with LLMs 提出Spotter+GPT框架以解决手语翻译问题 large language model
25 HawkEye: Training Video-Text LLMs for Grounding Text in Videos 提出HawkEye以解决长视频文本定位问题 large language model
26 Animate Your Motion: Turning Still Images into Dynamic Videos 提出SMCD模型以解决视频生成中的多模态融合问题 multimodal
27 CSDNet: Detect Salient Object in Depth-Thermal via A Lightweight Cross Shallow and Deep Perception Network 提出CSDNet以解决深度热成像中的显著目标检测问题 multimodal
28 CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner 提出CrossGLG以解决一-shot骨架动作识别中的信息损失问题 large language model
29 TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model 提出TextBlockV2以解决场景文本检测与识别的精确性问题 large language model
30 Temporal-spatial Adaptation of Promptable SAM Enhance Accuracy and Generalizability of cine CMR Segmentation 提出cineCMR-SAM以解决cine CMR分割的泛化性问题 foundation model
31 ST-LDM: A Universal Framework for Text-Grounded Object Generation in Real Images 提出ST-LDM框架以解决文本引导的物体生成问题 multimodal
32 ViTCN: Vision Transformer Contrastive Network For Reasoning 提出ViTCN以解决抽象推理问题 large language model

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

#题目一句话要点标签🔗⭐
33 Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting 提出MVControl以解决可控文本到3D生成问题 distillation gaussian splatting splatting ✅
34 Improving Medical Multi-modal Contrastive Learning with Expert Annotations 提出eCLIP以解决医学多模态对比学习中的数据稀缺问题 contrastive learning large language model
35 T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory 提出T4P方法以解决轨迹预测中的测试时学习问题 representation learning masked autoencoder MAE ✅
36 EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba 提出EfficientVMamba以解决轻量级视觉模型的效率与准确性问题 Mamba SSM state space model ✅
37 CoReEcho: Continuous Representation Learning for 2D+time Echocardiography Analysis 提出CoReEcho以解决心脏超声图像分析中的表示学习问题 representation learning MAE ✅
38 Histo-Genomic Knowledge Distillation For Cancer Prognosis From Histopathology Whole Slide Images 提出G-HANet以解决癌症预后中的单模态图像信息不足问题 teacher-student distillation
39 On the low-shot transferability of [V]-Mamba 探讨[V]-Mamba在低样本迁移学习中的表现 Mamba
40 PAME: Self-Supervised Masked Autoencoder for No-Reference Point Cloud Quality Assessment 提出自监督掩码自编码器PAME以解决无参考点云质量评估问题 masked autoencoder

🔬 支柱八：物理动画 (Physics-based Animation) (3 篇)

#题目一句话要点标签🔗⭐
41 Joint Multimodal Transformer for Emotion Recognition in the Wild 提出联合多模态变换器以解决情感识别问题 spatiotemporal multimodal
42 Learning Spatiotemporal Inconsistency via Thumbnail Layout for Face Deepfake Detection 提出Thumbnail Layout以解决深伪视频检测中的时空不一致性问题 spatiotemporal ✅
43 Autoregressive Queries for Adaptive Tracking with Spatio-TemporalTransformers 提出AQATrack以解决视觉跟踪中的时空信息聚合问题 spatiotemporal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
44 ANIM: Accurate Neural Implicit Model for Human Reconstruction from a single RGB-D image 提出ANIM以解决单视角RGB-D图像的人体重建问题 spatial relationship

⬅️ 返回 cs.CV 首页 · 🏠 返回主页