https://github.com/wkentaro/morefusion
공식 코드MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
MoreFusion: Multi-object Reasoning for 6D Pose Estimation from Volumetric Fusion
ReorientBot: Learning Object Reorientation for Specific-Posed Placement
VirtualPose: Learning Generalizable 3D Human Pose Models from Virtual Data
A Plug-in Method for Representation Factorization in Connectionist Models
Learning A Coarse-to-Fine Diffusion Transformer for Image Restoration
DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera
Scalable Factorized Hierarchical Variational Autoencoder Training
End-to-End Zero-Shot Voice Conversion with Location-Variable Convolutions
Creative Birds: Self-Supervised Single-View 3D Style Transfer
Creative Birds: Self-Supervised Single-View 3D Style Transfer
PREGAN: Pose Randomization and Estimation for Weakly Paired Image Style Translation
Free-SurGS: SfM-Free 3D Gaussian Splatting for Surgical Scene Reconstruction
A Visual Navigation Perspective for Category-Level Object Pose Estimation
PSGAN++: Robust Detail-Preserving Makeup Transfer and Removal
PoseTrans: A Simple Yet Effective Pose Transformation Augmentation for Human Pose Estimation
GlobalPointer: Large-Scale Plane Adjustment with Bi-Convex Relaxation
Universal Prompt Optimizer for Safe Text-to-Image Generation
Robust Category-Level 6D Pose Estimation with Coarse-to-Fine Rendering of Neural Features
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
Speech-Driven 3D Face Animation with Composite and Regional Facial Movements
DeProPose: Deficiency-Proof 3D Human Pose Estimation via Adaptive Multi-View Fusion
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model
Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images
POMATO: Marrying Pointmap Matching with Temporal Motion for Dynamic 3D Reconstruction
Training-Free Text-Guided Image Editing with Visual Autoregressive Model
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Diverse Text Generation via Variational Encoder-Decoder Models with Gaussian Process Priors
Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement Matters
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.