BWhat changed
Generated pseudo-target views by lifting single images with a frozen monocular-depth estimator, then trained a direct novel-view predictor with losses masked to valid reprojections.
Scientific scope
Generated pseudo-target views by lifting single images with a frozen monocular-depth estimator, then trained a direct novel-view predictor with losses masked to valid reprojections. No paired multi-view training captures are required for this setup, but inherited depth-estimator supervision remains. Geometry-free inference is not geometry-free training, recovered true geometry or guaranteed correct disocclusions.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. No paired multi-view training captures are required for this setup, but inherited depth-estimator supervision remains. Geometry-free inference is not geometry-free training, recovered true geometry or guaranteed correct disocclusions.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
- One View Is Enough! Monocular Training for In-the-Wild Novel View Generation
- Kyutai scientific publications index
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction