https://github.com/gbstack/cvpr-2022-papers

Unsupervised Activity Segmentation by Joint Representation Learning and Online Clustering(通过联合表示学习和在线聚类进行无监督活动分割) paper

Implicit Motion Handling for Video Camouflaged Object Detection(视频伪装对象检测的隐式运动处理) paper Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection(放大和缩小：用于伪装目标检测的混合尺度三元组网络) paper | code

Bi-directional Object-context Prioritization Learning for Saliency Ranking(显着性排名的双向对象上下文优先级学习) paper | code Democracy Does Matter: Comprehensive Feature Mining for Co-Salient Object Detection() paper

UKPGAN: A General Self-Supervised Keypoint Detector(一个通用的自监督关键点检测器) paper | code

CLRNet: Cross Layer Refinement Network for Lane Detection(用于车道检测的跨层细化网络) paper Rethinking Efficient Lane Detection via Curve Modeling(通过曲线建模重新思考高效车道检测) keywords: Segmentation-based Lane Detection, Point Detection-based Lane Detection, Curve-based Lane Detection, autonomous driving paper | code

EDTER: Edge Detection with Transformer(使用transformer的边缘检测) paper | code

Deep vanishing point detection: Geometric priors make dataset variations vanish(深度消失点检测**：几何先验使数据集变化消失)** paper | code

Learning What Not to Segment: A New Perspective on Few-Shot Segmentation(学习不分割的内容：关于小样本分割的新视角) paper | code CRIS: CLIP-Driven Referring Image Segmentation(CLIP 驱动的参考图像分割) paper Hyperbolic Image Segmentation(双曲线图像分割) paper

Panoptic SegFormer: Delving Deeper into Panoptic Segmentation with Transformers(使用 Transformers 深入研究全景分割) paper | code Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation(弯曲现实：适应全景语义分割的失真感知Transformer) keywords: Semanticand panoramic segmentation, Unsupervised domain adaptation, Transformer paper | code

Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation(用于域自适应语义分割的类平衡像素级自标记) paper | code Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation(弱监督语义分割的区域语义对比和聚合) paper | code Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation(走向稀疏注释的语义分割) paper | code Scribble-Supervised LiDAR Semantic Segmentation paper | code ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation(多目标域自适应语义分割的直接适应策略) paper Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrast(通过像素到原型对比的弱监督语义分割) paper Representation Compensation Networks for Continual Semantic Segmentation(连续语义分割的表示补偿网络) paper | code Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels(使用不可靠伪标签的半监督语义分割) paper | code Weakly Supervised Semantic Segmentation using Out-of-Distribution Data(使用分布外数据的弱监督语义分割) paper | code Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation(弱监督语义分割的自监督图像特定原型探索) paper | code Multi-class Token Transformer for Weakly Supervised Semantic Segmentation(用于弱监督语义分割的多类token Transformer) paper | code Cross Language Image Matching for Weakly Supervised Semantic Segmentation(用于弱监督语义分割的跨语言图像匹配) paper Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers(从注意力中学习亲和力：使用 Transformers 的端到端弱监督语义分割) paper | code ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation(让自我训练更好地用于半监督语义分割) keywords: Semi-supervised learning, Semantic segmentation, Uncertainty estimation paper | code Class Re-Activation Maps for Weakly-Supervised Semantic Segmentation(弱监督语义分割的类重新激活图) paper | code

ContrastMask: Contrastive Learning to Segment Every Thing(对比学习分割每件事) paper Discovering Objects that Can Move(发现可以移动的物体) paper | code E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation(一种基于端到端轮廓的高质量高速实例分割方法) paper | code Efficient Video Instance Segmentation via Tracklet Query and Proposal(通过 Tracklet Query 和 Proposal 进行高效的视频实例分割) paper SoftGroup for 3D Instance Segmentation on Point Clouds(用于点云上的 3D 实例分割) keywords: 3D Vision, Point Clouds, Instance Segmentation paper | code

Language as Queries for Referring Video Object Segmentation(语言作为引用视频对象分割的查询) paper | code

DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting(具有上下文感知提示的语言引导密集预测) paper | code

Neural Compression-Based Feature Learning for Video Restoration(用于视频复原的基于神经压缩的特征学习) paper

M3L: Language-based Video Editing via Multi-Modal Multi-Level Transformers(M3L：通过多模式多级transformer进行基于语言的视频编辑) paper

Depth-Aware Generative Adversarial Network for Talking Head Video Generation(用于说话头视频生成的深度感知生成对抗网络) paper | code Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning(告诉我什么并告诉我如何：通过多模式调节进行视频合成) paper | code

Global Matching with Overlapping Attention for Optical Flow Estimation(具有重叠注意力的全局匹配光流估计) paper | code CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation(用于联合光流和场景流估计的双向相机-LiDAR 融合) paper

Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation(基于自适应相关的级联循环网络的实用立体匹配) paper Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light(结合双目立体和单目结构光的深度估计) paper | code RGB-Depth Fusion GAN for Indoor Depth Completion(用于室内深度完成的 RGB 深度融合 GAN) paper Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective(从特征一致性的角度重新审视域广义立体匹配网络) paper Deep Depth from Focus with Differential Focus Volume(具有不同焦点体积的焦点深度) paper ChiTransformer:Towards Reliable Stereo from Cues(从线索走向可靠的立体声) paper Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss(重新思考多视图立体的深度估计：统一表示和焦点损失) paper | code ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networks(立体匹配网络中自动避免捷径和域泛化的信息论方法) keywords: Learning-based Stereo Matching Networks, Single Domain Generalization, Shortcut Learning paper Attention Concatenation Volume for Accurate and Efficient Stereo Matching(用于精确和高效立体匹配的注意力连接体积) keywords: Stereo Matching, cost volume construction, cost aggregation paper | code Occlusion-Aware Cost Constructor for Light Field Depth Estimation(光场深度估计的遮挡感知成本构造函数) paper | [code](https://github.com/YingqianWang/OACC- Net) NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation(用于单目深度估计的神经窗口全连接 CRF) keywords: Neural CRFs for Monocular Depth paper OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion(通过几何感知融合进行 360 度单目深度估计) keywords: monocular depth estimation(单目深度估计),transformer paper

Local Texture Estimator for Implicit Representation Function(隐式表示函数的局部纹理估计器) paper A Text Attention Network for Spatial Deformation Robust Scene Text Image Super-resolution(一种用于空间变形鲁棒场景文本图像超分辨率的文本注意网络) paper | code Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution(一种真实图像超分辨率的局部判别学习方法) paper | code Blind Image Super-resolution with Elaborate Degradation Modeling on Noise and Kernel(对噪声和核进行精细退化建模的盲图像超分辨率) paper | code Reflash Dropout in Image Super-Resolution(图像超分辨率中的闪退dropout) paper Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence(迈向双向任意图像缩放：联合优化和循环幂等) paper HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening(用于全色锐化的纹理和光谱特征融合Transformer) paper | code HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging(光谱压缩成像的高分辨率双域学习) keywords: HSI Reconstruction, Self-Attention Mechanism, Image Frequency Spectrum Analysis paper

Exploring and Evaluating Image Restoration Potential in Dynamic Scenes(探索和评估动态场景中的图像复原潜力) paper Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction(通过随机收缩加速逆问题的条件扩散模型) paper Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction(用于高效高光谱图像重建的掩模引导光谱变换器) paper | code Restormer: Efficient Transformer for High-Resolution Image Restoration(用于高分辨率图像复原的高效transformer) paper | code Event-based Video Reconstruction via Potential-assisted Spiking Neural Network(通过电位辅助尖峰神经网络进行基于事件的视频重建) paper

AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network(通过非对称 PD 和盲点网络对真实世界图像进行自监督去噪) paper | code IDR: Self-Supervised Image Denoising via Iterative Data Refinement(通过迭代数据细化的自监督图像去噪) paper | code Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots(具有可见盲点的自监督图像去噪) paper | code E-CIR: Event-Enhanced Continuous Intensity Recovery(事件增强的连续强度恢复) keywords: Event-Enhanced Deblurring, Video Representation paper | code

High-Fidelity GAN Inversion for Image Attribute Editing(用于图像属性编辑的高保真 GAN 反演) paper | code Style Transformer for Image Inversion and Editing(用于图像反转和编辑的样式transformer) paper | code MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting(用于高保真图像修复的多级交互式 Siamese 过滤) paper | code HairCLIP: Design Your Hair by Text and Reference Image(通过文本和参考图像设计你的头发) keywords: Language-Image Pre-Training (CLIP), Generative Adversarial Networks paper Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encoding(增量transformer结构增强图像修复与掩蔽位置编码) keywords: Image Inpainting, Transformer, Image Generation paper | code

Globetrotter: Connecting Languages by Connecting Images(通过连接图像连接语言) paper QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation(图像翻译中对比学习的查询选择注意) paper | code FlexIT: Towards Flexible Semantic Image Translation(迈向灵活的语义图像翻译) paper Exploring Patch-wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks(探索图像到图像翻译任务中对比学习的补丁语义关系) keywords: image translation, knowledge transfer,Contrastive learning paper

Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization(任意风格迁移和域泛化的精确特征分布匹配) paper | code Style-ERD: Responsive and Coherent Online Motion Style Transfer(响应式和连贯的在线运动风格迁移) paper CLIPstyler: Image Style Transfer with a Single Text Condition(具有单一文本条件的图像风格转移) keywords: Style Transfer, Text-guided synthesis, Language-Image Pre-Training (CLIP) paper

Cross-Modal Perceptionist: Can Face Geometry be Gleaned from Voices?(跨模态感知者：可以从声音中收集面部几何形状吗？) paper Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data(利用 3D 合成数据去除人像眼镜和阴影) paper | code HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network(分层解析胶囊网络的无监督人脸部分发现) paper FaceFormer: Speech-Driven 3D Facial Animation with Transformers(FaceFormer：带有transformer的语音驱动的 3D 面部动画) paper | code Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning(用于鲁棒人脸对齐和地标固有关系学习的稀疏局部补丁transformer) paper | code

Privacy-preserving Online AutoML for Domain-Specific Face Detection(用于特定领域人脸检测的隐私保护在线 AutoML) paper An Efficient Training Approach for Very Large Scale Face Recognition(一种有效的超大规模人脸识别训练方法) paper | code

FENeRF: Face Editing in Neural Radiance Fields(神经辐射场中的人脸编辑) paper GCFSR: a Generative and Controllable Face Super Resolution Method Without Facial and GAN Priors(一种没有面部和 GAN 先验的生成可控人脸超分辨率方法) paper Sparse to Dense Dynamic 3D Facial Expression Generation(稀疏到密集的动态 3D 面部表情生成) keywords: Facial expression generation, 4D face generation, 3D face modeling paper

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing(通过 Shuffled Style Assembly 进行域泛化以进行人脸反欺骗) paper | code Voice-Face Homogeneity Tells Deepfake paper | code Protecting Celebrities with Identity Consistency Transformer(使用身份一致性transformer保护名人) paper

Transforming Model Prediction for Tracking(转换模型预测以进行跟踪) paper | code MixFormer: End-to-End Tracking with Iterative Mixed Attention(具有迭代混合注意力的端到端跟踪) paper | code Unsupervised Domain Adaptation for Nighttime Aerial Tracking(夜间空中跟踪的无监督域自适应) paper | code Iterative Corresponding Geometry: Fusing Region and Depth for Highly Efficient 3D Tracking of Textureless Objects(迭代对应几何：融合区域和深度以实现无纹理对象的高效 3D 跟踪) paper | [code](https://github.com/DLR- RM/3DObjectTracking) TCTrack: Temporal Contexts for Aerial Tracking(空中跟踪的时间上下文) paper | code Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds(超越 3D 连体跟踪：点云中 3D 单对象跟踪的以运动为中心的范式) keywords: Single Object Tracking, 3D Multi-object Tracking / Detection, Spatial-temporal Learning on Point Clouds paper Correlation-Aware Deep Tracking(相关感知深度跟踪) paper

Bridging Video-text Retrieval with Multiple Choice Questions(桥接视频文本检索与多项选择题) paper | code BEVT: BERT Pretraining of Video Transformers(视频Transformer的 BERT 预训练) keywords: Video understanding, Vision transformers, Self-supervised representation learning, BERT pretraining paper | code

E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition(用于以自我为中心的动作识别的运动增强事件流) paper Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos(寻找变化：从未修剪的网络视频中学习对象状态和状态修改操作) paper | code DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition(鲁棒动作识别的 Transformer 方法中的定向注意) paper Self-supervised Video Transformer(自监督视频transformer) paper | code Spatio-temporal Relation Modeling for Few-shot Action Recognition(小样本动作识别的时空关系建模) paper | code RCL: Recurrent Continuous Localization for Temporal Action Detection(用于时间动作检测的循环连续定位) paper OpenTAL: Towards Open Set Temporal Action Localization(走向开放集时间动作定位) paper | code End-to-End Semi-Supervised Learning for Video Action Detection(视频动作检测的端到端半监督学习) paper Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos(模态特定注释视频上多模态动作识别的可学习不相关模态丢失) paper Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation(通过代表性片段知识传播的弱监督时间动作定位) paper | code Colar: Effective and Efficient Online Action Detection by Consulting Exemplars(通过咨询示例进行有效且高效的在线动作检测) keywords: Online action detection(在线动作检测) paper

Cascade Transformers for End-to-End Person Search(用于端到端人员搜索的级联transformer) paper | code

Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources(通过在线资源对上下文外图像进行开放域、基于内容、多模式的事实检查) paper | code Hierarchical Modular Network for Video Captioning(用于视频字幕的分层模块化网络) paper | code X -Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning(使用 Transformer 进行 3D 密集字幕的跨模式知识迁移) paper

ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image Classification(半监督医学图像分类的反课程伪标签) paper Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces from 3D MRI Scans with Geometric Deep Neural Networks(使用几何深度神经网络从 3D MRI 扫描中快速显式重建皮质表面) paper | code Generalizable Cross-modality Medical Image Segmentation via Style Augmentation and Dual Normalization(通过风格增强和双重归一化的可泛化跨模态医学图像分割) paper | code Adaptive Early-Learning Correction for Segmentation from Noisy Annotations(从噪声标签中分割的自适应早期学习校正) keywords: medical-imaging segmentation, Noisy Annotations paper | code Temporal Context Matters: Enhancing Single Image Prediction with Disease Progression Representations(时间上下文很重要：使用疾病进展表示增强单图像预测) keywords: Self-supervised Transformer, Temporal modeling of disease progression paper

SwinTextSpotter: Scene Text Spotting via Better Synergy between Text Detection and Text Recognition(通过文本检测和文本识别之间更好的协同作用进行场景文本定位) paper | code Fourier Document Restoration for Robust Document Dewarping and Recognition(用于鲁棒文档去扭曲和识别的傅里叶文档恢复) paper | code XYLayoutLM: Towards Layout-Aware Multimodal Networks For Visually-Rich Document Understanding(迈向布局感知多模式网络，以实现视觉丰富的文档理解) paper

Subspace Adversarial Training(子空间对抗训练) paper | code DTA: Physical Camouflage Attacks using Differentiable Transformation Network(使用可微变换网络的物理伪装攻击) paper | code Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input(通过基于对象的多样化输入提高目标对抗样本的可迁移性) paper | code Towards Practical Certifiable Patch Defense with Vision Transformer(使用 Vision Transformer 实现实用的可认证补丁防御) paper Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment(基于松弛空间结构对齐的小样本生成模型自适应) paper Enhancing Adversarial Training with Second-Order Statistics of Weights(使用权重的二阶统计加强对抗训练) paper | code Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack(通过自适应自动攻击对对抗鲁棒性的实际评估) paper Frequency-driven Imperceptible Adversarial Attack on Semantic Similarity(对语义相似性的频率驱动的不可察觉的对抗性攻击) paper Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon(阴影可能很危险：自然现象的隐秘而有效的物理世界对抗性攻击) paper Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer(保护面部隐私：通过风格稳健的化妆转移生成对抗性身份面具) paper Adversarial Texture for Fooling Person Detectors in the Physical World(物理世界中愚弄人探测器的对抗性纹理) paper Label-Only Model Inversion Attacks via Boundary Repulsion(通过边界排斥的仅标签模型反转攻击) paper

Modulated Contrast for Versatile Image Synthesis(用于多功能图像合成的调制对比度) paper | code Attribute Group Editing for Reliable Few-shot Image Generation(属性组编辑用于可靠的小样本图像生成) paper | code Text to Image Generation with Semantic-Spatial Aware GAN(使用语义空间感知 GAN 生成文本到图像) paper | code Playable Environments: Video Manipulation in Space and Time(可播放环境：空间和时间的视频操作) paper | code FLAG: Flow-based 3D Avatar Generation from Sparse Observations(从稀疏观察中生成基于流的 3D 头像) paper Dynamic Dual-Output Diffusion Models(动态双输出扩散模型) paper Exploring Dual-task Correlation for Pose Guided Person Image Generation(探索姿势引导人物图像生成的双任务相关性) paper | code 3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces(基于小批量特征交换的三维形状变化自动编码器潜在解纠缠) paper | code Interactive Image Synthesis with Panoptic Layout Generation(具有全景布局生成的交互式图像合成) paper Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values(极性采样：通过奇异值对预训练生成网络的质量和多样性控制) paper Autoregressive Image Generation using Residual Quantization(使用残差量化的自回归图像生成) paper | code

Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them from 2D Renderings(在 3D 网格中嵌入消息并从 2D 渲染中提取它们) paper X -Trans2Cap: Cross-Modal Knowledge Transfer using Transformer for 3D Dense Captioning(使用 Transformer 进行 3D 密集字幕的跨模式知识迁移) paper

IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment(通过深度嵌入对齐的动态 3D 点云插值) paper | code No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces(没有痛苦，收获很大：通过拟合特征级时空表面，用静态模型对动态点云序列进行分类) paper | code AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation(通用 3D 零件分割的中间监督搜索) paper Geometric Transformer for Fast and Robust Point Cloud Registration(用于快速和稳健点云配准的几何transformer) paper | code Contrastive Boundary Learning for Point Cloud Segmentation(点云分割的对比边界学习) paper | code Shape-invariant 3D Adversarial Point Clouds(形状不变的 3D 对抗点云) paper | code ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation(通过对抗旋转提高点云分类器的旋转鲁棒性) paper Lepard: Learning partial point cloud matching in rigid and deformable scenes(Lepard：在刚性和可变形场景中学习部分点云匹配) paper | code A Unified Query-based Paradigm for Point Cloud Understanding(一种基于统一查询的点云理解范式) paper CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding(用于 3D 点云理解的自监督跨模态对比学习) keywords: Self-Supervised Learning, Contrastive Learning, 3D Point Cloud, Representation Learning, Cross-Modal Learning paper | code

ϕ-SfT: Shape-from-Template with a Physics-Based Deformation Model(具有基于物理的变形模型的模板形状) paper | code Input-level Inductive Biases for 3D Reconstruction(用于 3D 重建的输入级归纳偏差) paper AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation(用于 3D 完成、重建和生成的形状先验) paper Interacting Attention Graph for Single Image Two-Hand Reconstruction(单幅图像双手重建的交互注意力图) paper | code OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction(实时动态 3D 重建的遮挡感知运动估计) paper Neural RGB-D Surface Reconstruction(神经 RGB-D 表面重建) paper Neural Face Identification in a 2D Wireframe Projection of a Manifold Object(流形对象的二维线框投影中的神经人脸识别) paper | [code](https://manycore- research.github.io/faceformer) Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction to Treat Diabetic Foot Ulcers(使用伤口分割和重建生成 3D 生物可打印贴片以治疗糖尿病足溃疡) keywords: semantic segmentation, 3D reconstruction, 3D bio-printers paper H4D: Human 4D Modeling by Learning Neural Compositional Representation(通过学习神经组合表示进行人体 4D 建模) keywords: 4D Representation(4D 表征),Human Body Estimation(人体姿态估计),Fine-grained Human Reconstruction(细粒度人体重建) paper

NeRFusion: Fusing Radiance Fields for Large-Scale Scene Reconstruction(用于大规模场景重建的融合辐射场) paper GeoNeRF: Generalizing NeRF with Geometry Priors(用几何先验概括 NeRF) paper | code StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions(室内 3D 场景重建的风格转换) paper | code Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image(向外看：从单个图像合成一致的长期 3D 场景视频) paper | code Point-NeRF: Point-based Neural Radiance Fields(基于点的神经辐射场) paper | code CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields(文本和图像驱动的神经辐射场操作) keywords: NeRF, Image Generation and Manipulation, Language-Image Pre-Training (CLIP) paper | code Point-NeRF: Point-based Neural Radiance Fields(基于点的神经辐射场) paper | code

Decoupled Knowledge Distillation(解耦知识蒸馏) paper | code Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation(小波知识蒸馏：迈向高效的图像到图像转换) paper Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability(知识蒸馏作为高效的预训练：更快的收敛、更高的数据效率和更好的可迁移性) paper | code Focal and Global Knowledge Distillation for Detectors(探测器的焦点和全局知识蒸馏) keywords: Object Detection, Knowledge Distillation paper | code

Implicit Feature Decoupling with Depthwise Quantization(使用深度量化的隐式特征解耦) paper IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization(学习具有类内异质性的合成图像以进行零样本网络量化) paper | code

BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning(学习探索样本关系以进行鲁棒表征学习) keywords: sample relationship, data scarcity learning, Contrastive Self-Supervised Learning, long-tailed recognition, zero-shot learning, domain generalization, self-supervised learning paper | code

TVConv: Efficient Translation Variant Convolution for Layout-aware Visual Processing(用于布局感知视觉处理的高效翻译变体卷积)(动态卷积) paper | code On the Integration of Self-Attention and Convolution(自注意力和卷积的整合) paper Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs(将内核扩展到 31x31：重新审视 CNN 中的大型内核设计) paper | code DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos(视频中稀疏帧差异的端到端 CNN 推断) keywords: sparse convolutional neural network, video inference accelerating paper A ConvNet for the 2020s paper | code

Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning paper | code NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition(在视觉transformer中为视觉识别指定协同上下文) paper | code Delving Deep into the Generalization of Vision Transformers under Distribution Shifts(深入研究分布变化下的视觉Transformer的泛化) keywords: out-of-distribution (OOD) generalization, Vision Transformers paper | code Mobile-Former: Bridging MobileNet and Transformer(连接 MobileNet 和 Transformer) keywords: Light-weight convolutional neural networks(轻量卷积神经网络),Combination of CNN and ViT paper

Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning(MAML 的全局收敛和受理论启发的神经架构搜索以进行 Few-Shot 学习) paper | code β-DARTS: Beta-Decay Regularization for Differentiable Architecture Search(可微架构搜索的 Beta-Decay 正则化) paper