Squeeze3D hits 2,187x mesh and 619x radiance field compression
rishit_dagli · x · 2026-10-07
Applying latent-space bridging to 3D data, Squeeze3D (TMLR 2026) achieves extreme compression: 2,187x for meshes (6.43 MB → 3.01 KB), 58.5x for point clouds (117 KB → 2 KB), and 619x for radiance fields (58.07 MB → 0.09 MB), while preserving visually important details compared to established codecs like Draco.
More from Research
- Book anniversary: Data Mining, Practical Machine Learning Tools and Techniques — FrnkNlsn · 2026-10-08
- Bittensor's SN107 Lets Miners Earn by Running AI Agents to Produce Genomic Data — markjeffrey · 2026-10-08
- CoLM 2026 Poster: Vibe-Voting LLMs and Why Users Distrust Benchmarks — boknilev · 2026-10-08
- Baseten's Base Labs has all 3 papers accepted at NeurIPS workshops — baseten · 2026-10-08
- Open-vocabulary text search fused into Google 3D Tiles across 27M voxels of San Francisco — bilawalsidhu · 2026-10-08
- SEAR research project to debut at COLM 2026, paper and code coming soon — WenhuChen · 2026-10-08