EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding
Paper
• 2603.04254 • Published
• 1
Seungjun Lee
onandon
AI & ML interests
3D Computer Vision, Scene Understanding, Open-Vocabulary, Multi-Modality, LLM and etc.
Recent Activity
authored
a paper
about 23 hours ago
EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding submitted
a paper
1 day ago
EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding commented on
a paper
25 days ago
Pairwise Distance Distillation for Unsupervised Real-World Image Super-Resolution Organizations
None yet
authored a paper about 23 hours ago
submitted a paper to Daily Papers 1 day ago
authored a paper 25 days ago
authored 3 papers 28 days ago
Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation
Paper
• 2505.11383 • Published
• 1
D3D-VLP: Dynamic 3D Vision-Language-Planning Model for Embodied Grounding and Navigation
Paper
• 2512.12622 • Published
Segment Any Events with Language
Paper
• 2601.23159 • Published
authored a paper 11 months ago
authored a paper almost 2 years ago