Mildenhall and colleagues: neural radiance fields for view synthesis

What changed

High-quality novel views could be synthesized from sparse posed images by optimizing a continuous neural field.

Scientific scope

Exact six-author 2020 ECCV static-scene work; dynamic/accelerated variants and all 3D products excluded.

Evidence

The linked sources identify this contribution and its scope. WRS has not independently reconstructed the scientific claims. The record is the exact 2020 ECCV NeRF paper and its static-scene view-synthesis experiments. Earlier neural rendering, later dynamic or accelerated NeRF variants, general 3D reconstruction and downstream products remain separate.

Contributors

• Ben Mildenhall · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Pratul P. Srinivasan · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Matthew Tancik · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Jonathan T. Barron · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Ravi Ramamoorthi · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.
• Ren Ng · SCIENCE: Named source author of the scoped work; individual effort shares are not measured.

• Mildenhall et al., NeRF
• Crossref record for NeRF

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