cs.CV（2024-03-18）

📊 共 52 篇论文 | 🔗 10 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (25 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (9 🔗2) 支柱七：动作重定向 (Motion Retargeting) (3 🔗1) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (25 篇)

#题目一句话要点标签🔗⭐
1 3DGS-Calib: 3D Gaussian Splatting for Multimodal SpatioTemporal Calibration 提出3DGS-Calib以解决多模态时空标定问题 3D gaussian splatting 3DGS gaussian splatting
2 Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction 提出运动感知3D高斯点云以解决动态场景重建问题 3D gaussian splatting 3DGS gaussian splatting
3 OpenOcc: Open Vocabulary 3D Scene Reconstruction via Occupancy Representation 提出OpenOcc以解决开放词汇3D场景重建问题 3D reconstruction neural radiance field scene reconstruction
4 NEDS-SLAM: A Neural Explicit Dense Semantic SLAM Framework using 3D Gaussian Splatting 提出NEDS-SLAM以解决实时3D语义映射与跟踪问题 3D gaussian splatting gaussian splatting splatting
5 BAD-Gaussians: Bundle Adjusted Deblur Gaussian Splatting 提出BAD-Gaussians以解决运动模糊图像重建问题 3D gaussian splatting gaussian splatting splatting ✅
6 ThermoNeRF: Joint RGB and Thermal Novel View Synthesis for Building Facades using Multimodal Neural Radiance Fields 提出ThermoNeRF以解决建筑外立面RGB与热图像合成问题 NeRF neural radiance field scene reconstruction
7 GaussNav: Gaussian Splatting for Visual Navigation 提出GaussNav以解决实例图像目标导航问题 3D gaussian splatting 3DGS gaussian splatting ✅
8 BAGS: Building Animatable Gaussian Splatting from a Monocular Video with Diffusion Priors 提出基于扩散先验的单目视频动画高斯点云重建方法 3D gaussian splatting 3D reconstruction gaussian splatting
9 SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications 提出SSAP以全面干扰单目深度估计问题 depth estimation monocular depth
10 RoGUENeRF: A Robust Geometry-Consistent Universal Enhancer for NeRF 提出RoGUENeRF以解决NeRF重建高频细节不足问题 NeRF scene reconstruction geometric consistency
11 UV Gaussians: Joint Learning of Mesh Deformation and Gaussian Textures for Human Avatar Modeling 提出UV Gaussians以解决人类头像建模中的模糊纹理问题 NeRF human motion ✅
12 R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding 提出R3DS数据集以提升全景场景理解能力 scene understanding
13 GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors 提出GNeRP以解决反射物体的3D重建问题 3D reconstruction NeRF neural radiance field
14 DVN-SLAM: Dynamic Visual Neural SLAM Based on Local-Global Encoding 提出DVN-SLAM以解决动态场景下SLAM的局限性 visual SLAM NeRF implicit representation
15 Just Add $100 More: Augmenting NeRF-based Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem 提出PGT-Aug以解决LiDAR点云类不平衡问题 NeRF
16 Agent3D-Zero: An Agent for Zero-shot 3D Understanding 提出Agent3D-Zero以解决零-shot 3D理解问题 scene understanding large language model
17 Hierarchical Spatial Proximity Reasoning for Vision-and-Language Navigation 提出层次空间邻近推理方法以解决视觉与语言导航中的决策不准确问题 scene understanding VLN ✅
18 Exploring Multi-modal Neural Scene Representations With Applications on Thermal Imaging 提出多模态神经场景表示以解决热成像合成问题 NeRF neural radiance field ✅
19 Aerial Lifting: Neural Urban Semantic and Building Instance Lifting from Aerial Imagery 提出神经辐射场方法以解决城市航拍图像的语义与实例分割问题 NeRF neural radiance field
20 The POLAR Traverse Dataset: A Dataset of Stereo Camera Images Simulating Traverses across Lunar Polar Terrain under Extreme Lighting Conditions 提出POLAR Traverse数据集以模拟月球极地环境下的立体视觉问题 visual odometry
21 Zero-Shot Image Feature Consensus with Deep Functional Maps 提出深功能映射以提升图像特征一致性问题 affordance
22 LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation 提出LN3Diff++以解决统一3D扩散生成问题 3D reconstruction
23 SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion 提出SV3D以解决单图像生成多视图视频的问题 3D reconstruction
24 Exploring 3D-aware Latent Spaces for Efficiently Learning Numerous Scenes 提出3D感知潜在空间以高效学习大量场景 NeRF
25 GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objects 提出GenFlow以解决新物体6D姿态估计的准确性与可扩展性问题 optical flow

🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)

#题目一句话要点标签🔗⭐
26 Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning 提出Fed3DGS以解决大规模3D重建的可扩展性问题 distillation 3D gaussian splatting 3DGS
27 Reinforcement Learning with Generalizable Gaussian Splatting 提出通用高斯点云表示框架以提升强化学习性能 reinforcement learning 3D gaussian splatting 3DGS
28 MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control 提出MineDreamer以解决指令理解与执行问题 dreamer generalist agent large language model
29 TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models 提出TTT-KD以解决3D语义分割中的数据分布适应问题 distillation foundation model
30 VmambaIR: Visual State Space Model for Image Restoration 提出VmambaIR以解决图像恢复中的长距离依赖问题 Mamba SSM state space model
31 HVDistill: Transferring Knowledge from Images to Point Clouds via Unsupervised Hybrid-View Distillation 提出HVDistill以解决点云特征学习中的知识转移问题 representation learning distillation
32 Boosting Continuous Emotion Recognition with Self-Pretraining using Masked Autoencoders, Temporal Convolutional Networks, and Transformers 提出自我预训练方法以提升连续情感识别性能 masked autoencoder MAE
33 DreamMotion: Space-Time Self-Similar Score Distillation for Zero-Shot Video Editing 提出DreamMotion以解决零-shot视频编辑中的运动一致性问题 distillation
34 Relational Representation Learning Network for Cross-Spectral Image Patch Matching 提出关系表示学习网络以解决跨光谱图像块匹配问题 representation learning ✅
35 Better (pseudo-)labels for semi-supervised instance segmentation 提出双重策略以改善半监督实例分割中的标签质量 teacher-student distillation

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

#题目一句话要点标签🔗⭐
36 VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding 提出VideoAgent以解决长视频理解问题 large language model foundation model multimodal
37 Federated Modality-specific Encoders and Multimodal Anchors for Personalized Brain Tumor Segmentation 提出FedMEMA框架以解决多模态医学图像分割中的异质性问题 multimodal
38 Arc2Face: A Foundation Model for ID-Consistent Human Faces 提出Arc2Face以解决人脸生成中的身份一致性问题 foundation model
39 Diffusion-Based Environment-Aware Trajectory Prediction 提出基于扩散模型的环境感知轨迹预测方法 multimodal
40 Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment 提出主观对齐的数据集和指标以解决文本到视频质量评估问题 large language model ✅
41 SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules 提出SuperLoRA以实现多层注意力模块的高效统一适应 large language model
42 Modality-Agnostic fMRI Decoding of Vision and Language 提出模态无关的fMRI解码方法以解决视觉与语言的交互问题 multimodal
43 Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs 提出Meta-Prompting以自动化零-shot视觉识别 large language model
44 LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images 提出LLaVA-UHD以解决多模态模型在高分辨率图像处理中的不足 multimodal ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (3 篇)

#题目一句话要点标签🔗⭐
45 SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction 提出SmartRefine以解决运动预测中的计算效率问题 motion prediction ✅
46 Graph-Jigsaw Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection 提出Graph-Jigsaw条件扩散模型以解决骨架视频异常检测问题 human motion
47 Object Segmentation-Assisted Inter Prediction for Versatile Video Coding 提出基于物体分割的帧间预测方法以提升视频编码效率 motion estimation

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
48 DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation 提出DreamSampler以解决图像操作中的模式崩溃问题 manipulation distillation latent optimization ✅
49 GetMesh: A Controllable Model for High-quality Mesh Generation and Manipulation 提出GetMesh以解决高质量网格生成与操控问题 manipulation
50 Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors 提出一种新方法以实现单幅图像的3D编辑 manipulation

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
51 ReGenNet: Towards Human Action-Reaction Synthesis 提出ReGenNet以解决动态人类行为反应合成问题 reaction synthesis

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
52 Generative Motion Stylization of Cross-structure Characters within Canonical Motion Space 提出MotionS以解决跨结构角色的运动风格化问题 motion synthesis

⬅️ 返回 cs.CV 首页 · 🏠 返回主页