RayDer (ECCV 2026) open-sourced: scalable self-supervised novel view synthesis from real-world video
rsasaki0109 · x · 2026-11-10
CompVis (LMU Munich, Björn Ommer's group) open-sourced RayDer, an ECCV 2026 paper with a minimal self-contained PyTorch re-implementation (training and video-generation scripts included).
RayDer removes the static-scene data bottleneck of self-supervised novel view synthesis by consolidating three networks into a single unified transformer, adding dynamic state prediction with dropout, and improving pose learning through autoregressive training. Performance follows power-law scaling (R² > 0.99) in data, model size and compute, analogous to LLMs. Zero-shot comparisons against E-RayZer across DTU, CO3D, Mip360, LLFF and near-zero-overlap extreme settings show consistent gains.
Related event: CompVis Open-Sources RayDer for Self-Supervised Novel View Synthesis(2 posts)→
More from Research
- Four Free Math Books for ML: Linear Algebra, Probability, Optimization, Information Theory — cneuralnetwork · 2026-11-10
- 4 free math books that actually matter for ML: linear algebra to information theory — cneuralnetwork · 2026-11-10
- Meta FAIR's e-means beats k-means in 1/10 epochs with 10-45x GPU speedups — burny_tech · 2026-11-10
- NeurIPS workshop paper: gradient-based data attribution can't reliably filter subliminal learning — ponguru · 2026-11-10
- Yang-Mills Working Group to Release OpenAI's Full Lean Code and Validation Tomorrow — burny_tech · 2026-11-10
- Interpretability researchers reminded: explanation matters, not just predictive power — burny_tech · 2026-11-10