cs.CV（2023-11-29）

📊 共 46 篇论文 | 🔗 12 篇有代码

🎯 兴趣领域导航

支柱三：空间感知与语义 (Perception & Semantics) (14 🔗6) 支柱九：具身大模型 (Embodied Foundation Models) (12 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (10 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (3 🔗1) 支柱一：机器人控制 (Robot Control) (3 🔗1) 支柱四：生成式动作 (Generative Motion) (2) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱三：空间感知与语义 (Perception & Semantics) (14 篇)

#题目一句话要点标签🔗⭐
1 GaussianShader: 3D Gaussian Splatting with Shading Functions for Reflective Surfaces 提出GaussianShader以解决反射表面渲染问题 3D gaussian splatting gaussian splatting splatting
2 Language-conditioned Detection Transformer 提出语言条件检测变换器以解决开放词汇检测问题 open-vocabulary open vocabulary language conditioned ✅
3 One-Shot Open Affordance Learning with Foundation Models 提出单例开放可供性学习以解决数据稀缺问题 affordance foundation model
4 CG3D: Compositional Generation for Text-to-3D via Gaussian Splatting 提出CG3D以解决文本驱动3D生成中的多对象场景问题 gaussian splatting splatting
5 The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding 提出动态词汇生成评估协议以提升开放词汇物体检测能力 open-vocabulary open vocabulary ✅
6 HUGS: Human Gaussian Splats 提出HUGS以解决动态人类建模问题 3D gaussian splatting 3DGS gaussian splatting ✅
7 NeRFTAP: Enhancing Transferability of Adversarial Patches on Face Recognition using Neural Radiance Fields 提出NeRFTAP以增强人脸识别中的对抗性补丁的可转移性 NeRF neural radiance field
8 PViT-6D: Overclocking Vision Transformers for 6D Pose Estimation with Confidence-Level Prediction and Pose Tokens 提出PViT-6D以简化6D姿态估计问题 6D pose estimation
9 DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model 提出DifFlow3D以解决动态场景流估计中的不确定性问题 scene flow ✅
10 FisherRF: Active View Selection and Uncertainty Quantification for Radiance Fields using Fisher Information 提出FisherRF以解决辐射场中的主动视角选择与不确定性量化问题 NeRF neural radiance field
11 Volumetric Cloud Field Reconstruction 提出深度学习框架以重建体积云场 stereo depth 3D reconstruction
12 SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis 提出SyncTalk以解决谈话头合成中的同步问题 NeRF neural radiance field ✅
13 ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction 提出ALSTER以解决在线3D语义重建问题 semantic map
14 SigFormer: Sparse Signal-Guided Transformer for Multi-Modal Human Action Segmentation 提出SigFormer以解决多模态人类动作分割中的稀疏信号融合问题 optical flow ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (12 篇)

#题目一句话要点标签🔗⭐
15 Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels? 提出VIM以解决多模态大语言模型在图像指令下的理解问题 large language model multimodal instruction following
16 Can Multimodal Large Language Models Truly Perform Multimodal In-Context Learning? 提出MMICES方法以提升多模态大语言模型的上下文学习能力 large language model multimodal ✅
17 OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation 提出OPERA以解决多模态大语言模型的幻觉问题 large language model ✅
18 M$^{2}$Chat: Empowering VLM for Multimodal LLM Interleaved Text-Image Generation 提出M$^{2}$Chat以解决多模态文本-图像生成的对齐问题 multimodal ✅
19 MMA-Diffusion: MultiModal Attack on Diffusion Models 提出MMA-Diffusion以解决文本到图像模型的安全隐患问题 multimodal
20 MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning 提出MM-Narrator以解决长视频音频描述生成问题 multimodal
21 ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model 提出ShapeGPT以解决3D形状生成与多模态融合问题 large language model multimodal
22 Back to 3D: Few-Shot 3D Keypoint Detection with Back-Projected 2D Features 提出基于反投影2D特征的少样本3D关键点检测方法 foundation model
23 Contextual Knowledge Pursuit for Faithful Visual Synthesis 提出上下文知识追求框架以解决视觉合成中的幻觉问题 large language model
24 DAP: Domain-aware Prompt Learning for Vision-and-Language Navigation 提出域感知提示学习框架以解决视觉-语言导航中的领域差距问题 VLN
25 VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models 提出VITATECS以解决视频语言模型的时间概念理解问题 large language model
26 Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning 提出Symbol-LLM以解决视觉人类活动推理中的符号系统构建问题 large language model

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

#题目一句话要点标签🔗⭐
27 The Importance of Downstream Networks in Digital Pathology Foundation Models 揭示下游网络在数字病理基础模型中的重要性 representation learning foundation model
28 PALM: Predicting Actions through Language Models 提出PALM以解决长时间动作预测问题 representation learning egocentric egocentric vision
29 Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving 提出Drive-WM以解决自动驾驶中的未来事件预测问题 world model world models
30 GenZI: Zero-Shot 3D Human-Scene Interaction Generation 提出GenZI以解决零样本3D人类场景交互生成问题 distillation human-scene interaction
31 Contrastive Vision-Language Alignment Makes Efficient Instruction Learner 提出CG-VLM以解决视觉语言指令学习效率低下问题 contrastive learning large language model instruction following
32 Continual Self-supervised Learning: Towards Universal Multi-modal Medical Data Representation Learning 提出MedCoSS以解决多模态医学数据表示学习的挑战 representation learning distillation ✅
33 Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation 提出双向令牌掩码自编码器以解决图像分割中的语言理解问题 masked autoencoder MAE multimodal
34 Discovering Galaxy Features via Dataset Distillation 通过数据集蒸馏发现星系特征以提升分类性能 distillation
35 Talking Head(?) Anime from a Single Image 4: Improved Model and Its Distillation 提出改进模型以实现单图动漫角色实时控制 distillation
36 Continual Learning for Image Segmentation with Dynamic Query 提出动态查询的持续学习图像分割方法以解决灾难性遗忘问题 representation learning distillation

🔬 支柱六：视频提取与匹配 (Video Extraction) (3 篇)

#题目一句话要点标签🔗⭐
37 W-HMR: Monocular Human Mesh Recovery in World Space with Weak-Supervised Calibration 提出W-HMR以解决单目图像中3D人体重建的焦距依赖问题 human mesh recovery HMR human motion ✅
38 LEAP: LLM-Generation of Egocentric Action Programs 提出LEAP以生成视频基础的自我中心动作程序 egocentric large language model multimodal
39 360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries 提出360Loc数据集以解决跨设备视觉定位问题 feature matching

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
40 MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models 提出MM-SafetyBench以解决多模态大语言模型的安全评估问题 manipulation large language model multimodal ✅
41 Cinematic Behavior Transfer via NeRF-based Differentiable Filming 提出基于NeRF的可微拍摄行为转移方法以解决动态场景中的视觉元素操控问题 manipulation NeRF SMPL
42 Rethinking Image Editing Detection in the Era of Generative AI Revolution 构建GRE数据集以解决生成AI时代图像编辑检测问题 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (2 篇)

#题目一句话要点标签🔗⭐
43 MoMask: Generative Masked Modeling of 3D Human Motions 提出MoMask框架以解决文本驱动的3D人类动作生成问题 text-to-motion motion generation T2M-GPT
44 SpeechAct: Towards Generating Whole-body Motion from Speech 提出SpeechAct以解决从语音生成全身动作的问题 motion generation foot skating VQ-VAE

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

#题目一句话要点标签🔗⭐
45 Dynamic Dense Graph Convolutional Network for Skeleton-based Human Motion Prediction 提出动态密集图卷积网络以解决骨架序列运动预测问题 human motion human motion prediction motion prediction

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
46 A natural language processing-based approach: mapping human perception by understanding deep semantic features in street view images 提出基于自然语言处理的方法以映射人类感知 PULSE

⬅️ 返回 cs.CV 首页 · 🏠 返回主页