Research map / 3D vision / Depth and stereo
FlashSSM-3D: A Distilled State Space Model for Lightning-Fast Dense 3D Reconstruction
Nyle Siddiqui, Mubarak Shah
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes FlashSSM-3D, a distilled state space model for fast dense 3D reconstruction, addressing the high compute cost of current SOTA 3D geometry models (abstract only).
Problem
Current SOTA deep 3D reconstruction and camera pose estimation models require industry-level compute, which limits practical deployment; the abstract is truncated before stating the second limitation.
Approach
Uses a distilled state space model to make dense multi-view 3D reconstruction fast; specifics unavailable from the truncated abstract.
Closest papers by meaning
- Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation (NeurIPS 2025 · similarity 0.88)
- Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction (NeurIPS 2026 · similarity 0.87)
- Test3R: Learning to Reconstruct 3D at Test Time (NeurIPS 2025 · similarity 0.87)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.87)
- MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data (CVPR 2025 · similarity 0.87)
- TurboVGGT: Fast Visual Geometry Reconstruction with Adaptive Alternating Attention (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
