High Dynamic Range (HDR) Imaging via Multi-Exposure Fusion L1-079
Unclaimed Principle — open for contribution
This Principle is declared in the catalog but has no reference solver, no pinned dataset, and is not registered on-chain. There is no reward pool. Submitting a cert against this Principle today will record the cert for reproducibility but pay zero PWM.
To claim it as a Bounty #7 contribution: open a PR adding (1) a reference solver, (2) ≥1 dataset pinned to IPFS, (3) updates to the L3 manifest with dataset CIDs. After verifier-agent triple-review, the founders' 3-of-5 multisig signs PWMRegistry.register() and the Principle becomes mineable.
Forward model E
A camera captures K images at distinct exposures t_k of a high-dynamic-range scene with irradiance E(u,v). Each frame y_k passes through the camera response function g (typically non-linear, per-channel) and saturates at the ADC limit. HDR reconstruction recovers E and (optionally) inverts g.
L-DAG
Well-posedness W
- Existence:
- true
- Uniqueness:
- true
- Stability:
- conditional
- κ:
- 600
Well-conditioned when saturation is avoided at some exposure for every pixel (dynamic-range cover). Degrades when (a) motion causes ghosting, (b) all exposures saturate in hotspots, (c) CRF calibration drifts. Under-covered bins (no exposure contains them unsaturated) are unrecoverable.
Solvability C
- Solver class:
- Debevec-Malik weighted fusion + inverse CRF, Mertens exposure fusion, HDR-CNN / Kalantari-Ramamoorthi deep HDR, HDR-GAN
- Convergence rate q:
- 2
- Complexity:
- O(K * H * W) for weighted fusion; O(K * H * W * log) for Mertens pyramid