LLaVA$^3$: Representing 3D Scenes like a Cubist Painter to Boost 3D Scene Understanding of VLMs

Documenti analoghi

• DiSCO-3D : Discovering and segmenting Sub-Concepts from Open-vocabulary queries in NeRF
  di: Petit, Doriand, et al.
  Pubblicazione: (2025)
• RING-NeRF : Rethinking Inductive Biases for Versatile and Efficient Neural Fields
  di: Petit, Doriand, et al.
  Pubblicazione: (2023)
• LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding
  di: Zhou, Hanyu, et al.
  Pubblicazione: (2025)
• LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
  di: Shu, Fangxun, et al.
  Pubblicazione: (2024)
• 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
  di: Deng, Jiajun, et al.
  Pubblicazione: (2025)