AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Invertible Neural Warp for NeRF

Shin-Fang Chng, Ravi Garg, Hemanth Saratchandran, Simon Lucey

ECCV 2024 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 3 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
enforce approximate invertibility with an auxiliary backward network (ablation)MLP ray warp · 2D planar image alignmentsuccess rate: 0.00 -> 0.65Improved
use an explicitly invertible INN instead of an implicit-invertible MLP (ablation)MLP ray warp · 2D planar image alignmentsuccess rate: 0.65 -> 0.75Improved
use explicit INN warp instead of SE(3) pose parameterizationBARF · 2D planar image alignmentcorner error (px): 29.63 -> 4.70Improved
naive MLP overparameterization without invertibility (ablation)ray warp · 2D planar image alignmentsuccess rate: 0.30 (BARF) -> 0.00 (Naive)Hurt
replace SE(3) pose with INN overparameterized warp on LLFFBARF · LLFFrotation error (deg): 0.90 -> 0.31Improved
INN versus L2G after test-time pose refinementLLFF novel view synthesis · LLFFPSNR: 24.35 (L2G) vs 24.28 (INN)No clear effect
replace SE(3) pose with INN warp on noisy DTU initializationBARF · DTUrotation error (deg): 2.52 -> 1.17Improved
INN versus L2G on DTU geometry qualitypose-NeRF joint optimization · DTUChamfer distance: 6.53 -> 4.89Improved
single shared INN with per-frame latent code instead of one network per frame (ablation)INN warp · 2D planar image alignmentconvergenceNo clear effect

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