Neural Harmonic Textures at ECCV beats all 3DGS and NeRF variants, code open-sourced
ZGojcic · x · 2026-09-10
Neural Harmonic Textures (NHT), presented at ECCV, is a new real-time novel view synthesis method that outperforms all 3DGS and NeRF derivatives—including ZipNeRF for the first time—across all quality benchmarks. The code is released under Apache 2.0. The authors will give an Oral Spotlight talk in room AB at 10:04 and present poster 267 from 10:30.
More from Research
- Acellera tests 7 LLM+harness combos on drug discovery: one RTX 5090 holds up — gdefabritiis · 2026-09-10
- IFM's Code-Reasoning dataset trends on Hugging Face with 100M+ examples — IFM · 2026-09-10
- DeepSeek report: post-training gains come from better data and environments, not RL novelty — realsohamparekh · 2026-09-10
- Engram architecture explained: 500B backbone beats GLM 5.3-class with far smaller KV cache — bookwormengr · 2026-09-10
- Engram embeddings load overlapped with GPU compute, so fetch time costs nothing — bookwormengr · 2026-09-10
- How John Bidwell found the optimal 17-square packing may be lost forever — tak3sh8 · 2026-09-10