https://github.com/SadilKhan/MARVEL-FX3D
공식 코드MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
Papers with Code 아카이브
3D Object Captioning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 1
- 보존된 평가 기록
- 6
3D object captioning involves generating a natural language description of an object, given its point cloud representation.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/openrobotlab/pointllm
공식 코드PointLLM: Empowering Large Language Models to Understand Point Clouds
https://github.com/qizekun/ShapeLLM
공식 코드ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/tangyuan96/minigpt-3d
공식 코드MiniGPT-3D: Efficiently Aligning 3D Point Clouds with Large Language Models using 2D Priors
https://huggingface.co/datasets/sankalpsinha77/MARVEL-40M
공식 코드MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation
https://github.com/Pointcept/GPT4Point
https://github.com/Yui010206/CREMA
https://github.com/chenguolin/DiffSplat
https://github.com/crockwell/cap3d
https://github.com/qizekun/ReCon
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/runpeidong/act
ShapeLLM: Universal 3D Object Understanding for Embodied Interaction
https://github.com/umass-foundation-model/3d-llm
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.