OmniRay reconstructs 3D from a single image without knowing the camera model
anand_bhattad · x · 2026-10-31
OmniRay tackles single-image 3D reconstruction without pinhole assumptions: it works with fisheye, GoPro, or 360° panorama images and requires no camera intrinsics.
The method starts from a radial camera model, learns a smooth correction across the image, then refines individual rays where needed. The team reports strong results across camera types; details in the linked thread.
More from Research
- CS312 course post explains sharpness and the edge of stability in LLM pretraining — tatsu_hashimoto · 2026-10-31
- AI decodes wolf howls: 500K hours of Yellowstone audio analyzed by models — aza · 2026-10-31
- NBER paper: training your AI replacement can actually raise workers' pay — joshgans · 2026-10-31
- Trata's Hedge-Bench: no model tops 50% on real-world financial forecasting — ycombinator · 2026-10-31
- Anthropic's internal Claude model claims 2^o(n) 3-SAT algorithm, purportedly refuting the ETH — ctjlewis · 2026-10-31
- CMU paper unifies pretraining, SFT and RL into one likelihood-based training algorithm — rohanpaul_ai · 2026-10-31