AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Improving the Convergence of Dynamic NeRFs via Optimal Transport

Sameera Ramasinghe, Violetta Shevchenko, Gil Avraham, Hisham Husain, Anton van den Hengel

ICLR 2024 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes using optimal transport as a regularizer to improve convergence and novel-view synthesis quality of dynamic NeRFs, as an alternative to intricate geometric regularizers.

Problem

Novel view synthesis for dynamic scenes from RGB inputs is severely under-constrained, and existing NeRF methods rely on intricate geometric regularizers (scene flow, depth, learned perceptual similarity) to mitigate ill-posedness.

Approach

Uses optimal transport as a regularization signal for dynamic NeRF training in place of handcrafted geometric priors; based on the abstract only, the specific formulation is not stated.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy