Uploaded March 2023 | Updated November 2026, 2 days ago
Project: lerf.io
Learn more about LeRF: link.medium.com/NVC1fyw9jEb
LeRF optimizes a dense, multi-scale language 3D field by volume rendering CLIP embeddings along training rays, supervising these embeddings with multi-scale CLIP features across multi-view training images. After optimization, LeRF can extract 3D relevancy maps for language queries interactively in real-time. LeRF enables pixel-aligned queries of the distilled 3D CLIP embeddings without relying on region proposals, masks, or fine-tuning, supporting long-tail open-vocabulary queries hierarchically across the volume.
Project: lerf.io
Learn more about LeRF: link.medium.com/NVC1fyw9jEb
LeRF optimizes a dense, multi-scale language 3D field by volume rendering CLIP embeddings along training rays, supervising these embeddings with multi-scale CLIP features across multi-view training images. After optimization, LeRF can extract 3D relevancy maps for language queries interactively in real-time. LeRF enables pixel-aligned queries of the distilled 3D CLIP embeddings without relying on region proposals, masks, or fine-tuning, supporting long-tail open-vocabulary queries hierarchically across the volume.










