AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Alessandro Ruzzi, Xiangwei Shi, Xi Wang, Gengyan Li, Shalini De Mello, Hyung Jin Chang, Xucong Zhang, Otmar Hilliges

CVPR 2023 · 3D vision › NeRF and radiance fields · approach: Single-view and streaming radiance fields · 27 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 separate face and eye streams instead of a single MLP (ablation)GazeNeRF · ETH-XGazeGaze error: 11.427 -> 8.609Improved
Add rotation to the eye stream (ablation)Two-stream GazeNeRF · ETH-XGazeGaze error: 8.609 -> 8.437Improved
Add a rotation matrix to the single-stream feature maps (ablation)vanilla-GazeNeRF · ETH-XGazeGaze error: 11.427 -> 9.279Improved
Add functional loss (ablation)vanilla-GazeNeRF · ETH-XGazeGaze error: 11.427 -> 7.777Improved
Add functional loss to the two-stream, rotated model (ablation)GazeNeRF · ETH-XGazeGaze error: 8.437 -> 6.944Improved
Add perceptual loss to reconstruction-only training (ablation)Two-stream+rotation GazeNeRF · ETH-XGazeGaze error: 28.122 -> 8.861Improved
Add disentanglement loss after reconstruction and perceptual losses (ablation)Two-stream+rotation GazeNeRF · ETH-XGazeHead Pose: 3.456 -> 3.386Improved
Add functional loss after reconstruction, perceptual, and disentanglement losses (ablation)Two-stream+rotation GazeNeRF · ETH-XGazeGaze error: 8.460 -> 6.944Improved
Add functional loss after reconstruction, perceptual, and disentanglement losses (ablation)Two-stream+rotation GazeNeRF · ETH-XGazeFID: 72.044 -> 81.816Hurt
Initialize with pre-trained HeadNeRF rather than train from scratch (ablation)GazeNeRF · ETH-XGazeHead Pose: 3.470 -> 3.080Improved
Initialize with pre-trained HeadNeRF rather than train from scratch (ablation)GazeNeRF · ETH-XGazeGaze error: 6.944 -> 7.134Hurt
Use GazeNeRF instead of HeadNeRFGazeNeRF · MPIIFaceGazeGaze error: 14.320 -> 14.933Hurt

Later papers that compared with this method

1 later accepted paper reports GazeNeRF as a baseline in their results tables; 1 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