AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering

Mingfei Chen, Jianfeng Zhang, Xiangyu Xu, Lijuan Liu, Yujun Cai, Jiashi Feng, Shuicheng Yan

ECCV 2022 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 41 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
add geometry-guided attention to aggregate multi-view features (QG vs G) (ablation)GP-NeRF · ZJU-MoCap uniform camerasPSNR: 23.47 -> 23.68Improved
add pixel-aligned image features (P vs G) (ablation)GP-NeRF · ZJU-MoCap uniform camerasPSNR: 23.47 -> 26.09Improved
add geometry features QG to pixel-aligned features (QG+P vs P) (ablation)GP-NeRF · ZJU-MoCap uniform camerasPSNR: 26.09 -> 26.69Improved
add geometry features QG to pixel-aligned features (QG+P vs P) (ablation)GP-NeRF · ZJU-MoCap uniform camerasSSIM: 0.915 -> 0.924Improved
decouple density and appearance networks into progressive pipeline (35k steps) (ablation)GP-NeRF · ZJU-MoCap uniform camerasPSNR: 26.69 -> 26.65No clear effect
decouple density and appearance networks (5k steps) (ablation)GP-NeRF · ZJU-MoCap uniform camerasPSNR: 26.05 -> 26.13Improved
use P-only appearance network in progressive pipeline (5k steps) (ablation)GP-NeRF · ZJU-MoCap uniform camerasSSIM: 0.917 -> 0.920Improved
use QG+P instead of QG for density network (35k steps) (ablation)GP-NeRF · ZJU-MoCap uniform camerasPSNR: 26.40 -> 26.67Improved
use progressive rendering with fewer sampling points (GP-NeRF 1x vs NB 2x)GP-NeRF · ZJU-MoCaprendering time (ms): 611 -> 175Improved
use progressive rendering with fewer sampling points (GP-NeRF 2x vs NB 2x)GP-NeRF · ZJU-MoCapmemory (GB): 21.80 -> 9.88Improved
add progressive rendering to GP-NeRF vs vanilla rendering (2x)GP-NeRF · ZJU-MoCaptime (ms): 567 -> 243Improved
train on THUman-all instead of THUman-7GP-NeRF · ZJU-3 cross-datasetPSNR: 24.74 -> 25.60Improved

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