AI Paper Atlas

Research map / 3D vision / 3D generation

ViewFormer: NeRF-Free Neural Rendering from Few Images Using Transformers

Jonáš Kulhánek, Erik Derner, Torsten Sattler, Robert Babuška

ECCV 2022 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 59 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
remove the localization (pose estimation) head, i.e. train for view synthesis only (ablation)ViewFormer @ all cat. · CO3D (all categories, avg test)PSNR: 15.3 -> 15.4No clear effect
train on all CO3D categories instead of only 10 categories (ablation)ViewFormer · CO3D (10 categories, avg test)PSNR: 15.6 -> 16.0Improved
increase number of context views from 1 to 9 (ablation)ViewFormer @ all cat. · CO3D (all categories, test)PSNR: 13.7 -> 16.1Improved
remove the perceptual loss from the codebook training (ablation)VQ-VAE codebook · codebook reconstructionimage quality (qualitative)Hurt
use dynamic loss weighting for position and orientation instead of plain sum (ablation)ViewFormer localization · pose losspose accuracyHurt
replace explicit-3D NeRF-based NerFormer by 2D-only ViewFormer (training cost)CO3D all categories · CO3Dtraining GPU-hours: 8400 -> 850 GPU-hoursImproved
replace NerFormer by ViewFormer (render time per view)CO3D · CO3Drender time: 178 s -> 93 msImproved
ViewFormer vs NerFormer on LPIPS (all categories)ViewFormer · CO3D (all categories, avg test)LPIPS: 0.24 -> 0.23Improved
ViewFormer vs NerFormer on PSNR (10 categories)ViewFormer @ all cat. · CO3D (10 categories, avg test)PSNR: 17.6 -> 16.0Hurt
ViewFormer vs GQN-style baselines on SM7ViewFormer · Shepard-Metzler-7-PartsMAE: 2.14 -> 1.61Improved

Later papers that compared with this method

7 later accepted papers report ViewFormer as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

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