AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Forward Flow for Novel View Synthesis of Dynamic Scenes

Xiang Guo, Jiadai Sun, Yuchao Dai, Guanying Chen, Xiaoqing Ye, Xiao Tan, Errui Ding, Yumeng Zhang, Jingdong Wang

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Dynamic and editable NeRF · 61 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
use forward flow warping of canonical field instead of backward flowdynamic NeRF · Lego Complete canonical interpolationPSNR: 19.90 -> 25.63 (vs NDVG)Improved
forward flow on D-NeRF dataset vs physical canonical baselinesdynamic NeRF · D-NeRF datasetPSNR: 30.54 -> 32.68 (vs NDVG)Improved
add inpaint network (ablation)forward-flow NeRF · D-NeRF datasetPSNR: 31.78 -> 32.68Improved
add upsampling in inpaint network (ablation)forward-flow NeRF · D-NeRF datasetPSNR: 32.03 -> 32.68Improved
add total variation losses (ablation)forward-flow NeRF · D-NeRF datasetPSNR / LPIPS: PSNR 33.09 -> 32.68; LPIPS 0.046 -> 0.037Mixed
add total variation losses (ablation)forward-flow NeRF · HyperNeRF datasetPSNR: 23.84 -> 24.23Improved
add photometric loss on upsampled grid (ablation)forward-flow NeRF · D-NeRF 4 scenesPSNR: 31.56 -> 33.75Improved
add flow loss (ablation)forward-flow NeRF · D-NeRF 4 scenesPSNR: 33.74 -> 33.75No clear effect
set canonical time to middle frame instead of first frame (ablation)forward-flow NeRF · D-NeRF 4 scenesPSNR: 33.75 -> 34.09Improved
voxel resolution limited to 70^3 versus 160^3 baselinesforward-flow NeRF · HyperNeRF datasetPSNR: 24.2 vs 24.3 (TiNeuVox-B)Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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