4D Gaussian Splatting runtime cut to 5 mins, memory needs halved
janusch_patas · x · 2026-08-27
A developer integrated 4D Gaussian Splatting (4D Anyone) into the Rerun visualization tool.
- Optimized the DiT model to reduce VRAM usage from 50GB to under 32GB, removing the need for enterprise GPUs.
- Slashed runtime for generating 16 views from one video from 40 minutes to about 5 minutes on an RTX 5090.
- Successfully implemented a working version of 4D splatting training.
More from Infra
- vLLM hits 130k tok/s on DeepSeek V4 Pro in AgentX benchmark — AccBalanced · 2026-08-27
- Google Cloud Run Introduces Instances for MicroVM Deployment — steren · 2026-08-27
- Anthropic Signs $4.5B Compute Deal for Nvidia Rubin Chips at Nscale — Beth_Kindig · 2026-08-27
- DeepSeek-v4-Pro Generates 130M Tokens for $1, 77x Cheaper Than Opus — bookwormengr · 2026-08-27
- NVIDIA FLARE Cuts Federated VLM Training Traffic by 99% — dl_weekly · 2026-08-27
- Same Budget: 256GB Mac or Two DGX Sparks for 70B Inference? — Whyme-__- · 2026-08-27