https://github.com/eckertzhang/text2nerf
공식 코드Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
make to t shirt an Ad with a little bit of action
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections
WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation
Persistent Nature: A Generative Model of Unbounded 3D Worlds
LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
Towards Realistic Scene Generation with LiDAR Diffusion Models
ROOT: VLM based System for Indoor Scene Understanding and Beyond
Solving Motion Planning Tasks with a Scalable Generative Model
RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spaces
CityDreamer: Compositional Generative Model of Unbounded 3D Cities
CityDreamer4D: Compositional Generative Model of Unbounded 4D Cities
GaussianCity: Generative Gaussian Splatting for Unbounded 3D City Generation
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
Supertoroid fitting of objects with holes for robotic grasping and scene generation
SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation
SimWorld: A Unified Benchmark for Simulator-Conditioned Scene Generation via World Model
SceneDreamer360: Text-Driven 3D-Consistent Scene Generation with Panoramic Gaussian Splatting
HERMES: A Unified Self-Driving World Model for Simultaneous 3D Scene Understanding and Generation
$I^{2}$-World: Intra-Inter Tokenization for Efficient Dynamic 4D Scene Forecasting
pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis
FSID: Fully Synthetic Image Denoising via Procedural Scene Generation
Indoor Scene Generation from a Collection of Semantic-Segmented Depth Images
Steerable Scene Generation with Post Training and Inference-Time Search
RetrievalFuse: Neural 3D Scene Reconstruction with a Database
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.