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
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
- RegNeRF: Regularizing Neural Radiance Fields for View Synthesis From Sparse Inputs (CVPR 2022 · similarity 0.92)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (AAAI 2024 · similarity 0.91)
- NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild (CVPR 2024 · similarity 0.90)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 2024 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.89)
- Mask-Based Modeling for Neural Radiance Fields (ICLR 2024 · similarity 0.89)
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.
