https://github.com/728388808/alpha-neus
공식 코드From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $α$-NeuS
Multi-Label Stereo Matching for Transparent Scene Depth Estimation
NeuralLabeling: A versatile toolset for labeling vision datasets using Neural Radiance Fields
RGB-D Local Implicit Function for Depth Completion of Transparent Objects
ClearGrasp: 3D Shape Estimation of Transparent Objects for Manipulation
SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo
TransMatting: Enhancing Transparent Objects Matting with Transformers
Exploring the Interactive Guidance for Unified and Effective Image Matting
KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects
TOM-Net: Learning Transparent Object Matting from a Single Image
TranSplat: Surface Embedding-guided 3D Gaussian Splatting for Transparent Object Manipulation
Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes
ClearPose: Large-scale Transparent Object Dataset and Benchmark
Polarimetric Inverse Rendering for Transparent Shapes Reconstruction
Trans2k: Unlocking the Power of Deep Models for Transparent Object Tracking
TDCNet: Transparent Objects Depth Completion with CNN-Transformer Dual-Branch Parallel Network
Spider: A Unified Framework for Context-dependent Concept Segmentation
TODE-Trans: Transparent Object Depth Estimation with Transformer
TOM-Net: Learning Transparent Object Matting from a Single Image
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.