Papers with Code 아카이브
Inverse Rendering
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 7
Inverse Rendering is the task of recovering the properties of a scene, such as shape, material, and lighting, from an image or a video. The goal of inverse rendering is to determine the properties of a scene given an observation of it, and to generate new images or videos based on these properties.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/RudyQ/InverseFaceRender
https://github.com/bring728/MAIR_Open
MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation
https://github.com/compphoto/MIDIntrinsics
https://github.com/google/samurai
SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections
https://github.com/laura-a-n-n/tf-nlr
https://github.com/m-schuetz/compute_rasterizer
https://github.com/nvlabs/tiny-cuda-nn
Extracting Triangular 3D Models, Materials, and Lighting From Images
https://github.com/senguptaumd/SfSNet
SfSNet: Learning Shape, Reflectance and Illuminance of Faces in the Wild
https://github.com/taconite/intrinsicavatar
https://github.com/thunguyenphuoc/RenderNet
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
https://github.com/zju3dv/invrender
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.