CORE-3D: Context-aware Open-vocabulary Retrieval by Embeddings in 3D
"3D场景理解" 相关文章
Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy
Text-Scene: A Scene-to-Language Parsing Framework for 3D Scene Understanding
ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors
Argus: Leveraging Multiview Images for Improved 3-D Scene Understanding With Large Language Models
2025.04.10 | DDT提升图像生成质量；GenDoP优化相机轨迹生成。
