AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Enhancing NeRF akin to Enhancing LLMs: Generalizable NeRF Transformer with Mixture-of-View-Experts

Wenyan Cong, Hanxue Liang, Peihao Wang, Zhiwen Fan, Tianlong Chen, Mukund Varma, Yi Wang, Zhangyang Wang

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
plug a naive MoE layer into GNT view transformer without PE or smoothness loss (ablation)GNT · LLFF (zero-shot)PSNR: 25.86 -> 25.46Hurt
plug a naive MoE layer into GNT view transformer without PE or smoothness loss (ablation)GNT · NeRF Synthetic (zero-shot)PSNR: 27.29 -> 27.15Hurt
add shared permanent expert to MoE (ablation)GNT + MoE · LLFF (zero-shot)PSNR: 25.46 -> 25.88Improved
add geometry-aware smoothness regularizer to MoE (ablation)GNT + MoE · LLFF (zero-shot)PSNR: 25.46 -> 25.93Improved
add shared permanent expert to MoE (ablation)GNT + MoE · NeRF Synthetic (zero-shot)PSNR: 27.15 -> 27.32Improved
add both permanent expert and smoothness regularizer (ablation)GNT + MoE · LLFF (zero-shot)PSNR: 25.46 -> 26.02Improved
use MoE with 2.5x total parameters instead of widening dense GNT by 2.5x (ablation)GNT · Tanks-and-Temples Truck (zero-shot)PSNR: 18.26 -> 19.71Improved
replace permanent expert with an extra selectable expert at equal params and FLOPs (ablation)GNT-MOVE · Tanks-and-Temples Truck (zero-shot)PSNR: 19.71 -> 18.11Hurt
replace GNT with GNT-MOVE on challenging unbounded scenesGNT · Tanks-and-Temples (4 scenes, zero-shot)PSNR: up to 3 dB PSNRImproved
replace GNT with GNT-MOVE in few-shot finetuningGNT · LLFF few-shotPSNR: +0.13 dB (3-shot), +0.17 dB (6-shot), +0.47 dB (10-shot)Improved
replace GNT with GNT-MOVE on LLFF and NeRF Synthetic SSIM versus GPNRGNT-MOVE · LLFF and NeRF Synthetic (zero-shot)SSIM: LLFF 0.880 (GPNR) vs 0.869; NeRF Synthetic 0.944 (GPNR) vs 0.940Mixed

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