AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

Deformable Neural Radiance Fields using RGB and Event Cameras

Qi Ma, Danda Pani Paudel, Ajad Chhatkuli, Luc Van Gool

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 29 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 pose refinement (ablation)DE-NeRF · Lego, 10 viewsPSNR: 28.85 -> 32.13Improved
add active sampling (ablation)DE-NeRF · Lego, 25 viewsPSNR: 29.91 -> 31.83Improved
add active sampling with 10 views (ablation)DE-NeRF · Lego, 10 viewsPSNR: 28.89 -> 28.85No clear effect
add void sampling (locations without events) (ablation)DE-NeRF · Lego, 10 viewsPSNR: 28.16 -> 28.89Improved
use proposed event integration versus DE-Baseline (ablation)DE-NeRF · Lego, 10 viewsPSNR: 22.21 -> 28.16Improved
use normalized event loss on real dataDE-NeRF · real-world datasetsPSNRHurt
reconstruct frames from events (E2VID) and train with RGB instead of using events directlyNerfies/HyperNeRF · Lego, Umbrella, SelfiePSNR: Lego E2VID 15.17 vs DE-NeRF 35.04Hurt
use event cameras with lower contrast threshold (higher sensitivity) (ablation)DE-NeRF · Legonovel view qualityImproved
DE-NeRF on fluid scenes violating deformation priorDE-NeRF · FluidPSNR: 25.25 -> 26.92No clear effect

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