AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Unconstrained Scene Generation With Locally Conditioned Radiance Fields

Terrance DeVries, Miguel Angel Bautista, Nitish Srivastava, Graham W. Taylor, Joshua M. Susskind

ICCV 2021 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 119 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 local latent grid conditioning instead of a global latent code (ablation)GSN · Replica 64x64FID: 68.42 -> 41.75Improved
add local latent grid conditioning instead of a global latent code (ablation)GSN · Replica 64x64SwAV-FID: 6.14 -> 4.14Improved
use local coordinate system for local radiance fields instead of global (ablation)GSN · Replica 64x64 latent grid rotationFIDImproved
train with long camera trajectories instead of short ones (ablation)GSN · Replica 64x64FID on long trajectoriesImproved
add depth input to the discriminator (any resolution) versus no depth (ablation)GSN · Replica 64x64FID: 311.35 -> 41.75Improved
reduce depth resolution from 32 to a single pixel (ablation)GSN · Replica 64x64FID: 41.75 -> 41.57No clear effect
reduce depth resolution from 32 to 4 (ablation)GSN · Replica 64x64FID: 41.75 -> 44.18No clear effect
add R1 gradient penalty to the discriminator (ablation)GSN · Replica 64x64FID: 52.9 -> 41.75Improved
add discriminator reconstruction penalty (ablation)GSN · Replica 64x64FID: 274.3 -> 41.75Improved
add data augmentation to discriminator training (ablation)GSN · Replica 64x64FID: 412.25 -> 41.75Improved
use GSN with locally conditioned radiance field instead of GRAFGRAF · VizDoom 64x64FID: 47.50 -> 37.21Improved
use GSN instead of GRAFGRAF · Replica 64x64FID: 65.37 -> 41.75Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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