TLP: Single-Parameter Point Cloud Registration with Truncated Lp Functions
zhenjun_zhao · x · 2026-10-28
TLP is a robust point cloud registration method with only one tunable parameter, using truncated Lp functions to prioritize correspondences, select and refine hypotheses. GPU-parallel hypothesis evaluation registers thousands of correspondences in under a second on average. On 3DMatch and KITTI benchmarks it beats state-of-the-art single-parameter methods and outperforms widely used multi-parameter methods SC²-PCR and MAC on three of four datasets, which suffer from out-of-memory or excessive runtimes.
More from Research
- Rebuilding 'Democracy Does Cause Growth': long-run GDP effect rises to 33.6% with 2024 data — ChenhaoTan · 2026-10-28
- YC-backed Wondersearch claims OpenAI-level retrieval on FiQA with no embeddings, no vector DB — antoine_chaffin · 2026-10-28
- AAAI/ICLR Reviewer: About Half of Reviews Look AI-Generated, Peer Review in Crisis — dsmirza · 2026-10-28
- A bestiary of chaotic attractors from the Field–Golubitsky map, each with Dₙ symmetry — S_Conradi · 2026-10-28
- Manifold AI's WorldScape R²SI Tops RoboDojo Agent Track by Turning Robot Failures Into Skills — jiqizhixin · 2026-10-28
- AXA Uses NVIDIA Earth-2 to Simulate 1,000+ Cyclone Seasons for Storm Risk Modeling — NVIDIAAI · 2026-10-28