FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models

Documenti analoghi

• UniM$^2$AE: Multi-modal Masked Autoencoders with Unified 3D Representation for 3D Perception in Autonomous Driving
  di: Zou, Jian, et al.
  Pubblicazione: (2023)
• S2AM3D: Scale-controllable Part Segmentation of 3D Point Clouds
  di: Su, Han, et al.
  Pubblicazione: (2025)
• TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields
  di: Huang, Tianyu, et al.
  Pubblicazione: (2023)
• DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior
  di: Huang, Tianyu, et al.
  Pubblicazione: (2023)
• MetricDepth: Enhancing Monocular Depth Estimation with Deep Metric Learning
  di: Liu, Chunpu, et al.
  Pubblicazione: (2024)