Research map / 3D vision / 3D generation
GFIE: A Dataset and Baseline for Gaze-Following From 2D to 3D in Indoor Environments
Zhengxi Hu, Yuxue Yang, Xiaolin Zhai, Dingye Yang, Bohan Zhou, Jingtai Liu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use stereo FoV perception and the proposed 2D/3D gaze-following approach instead of Chong | GFIE baseline · GFIE test | 3D Dist.: 0.455 -> 0.311 | Improved |
| Add the encoder-decoder module and use it to generate the gaze heatmap (ablation) | GFIE · GFIE test | L2 Dist.: 0.129 -> 0.065 | Improved |
| Add the stereo FoV heatmap module (ablation) | GFIE · GFIE test | 3D Dist.: 0.452 -> 0.311 | Improved |
| Use two stereo FoV heatmaps rather than one (ablation) | GFIE · GFIE test | L2 Dist.: 0.079 -> 0.065 | Improved |
| Add cosine-loss supervision for the gaze vector (ablation) | GFIE · GFIE test | 3D Dist.: 0.821 -> 0.311 | Improved |
| Combine predicted gaze vector with the proposed 3D inference strategy instead of using the vector alone (ablation) | GFIE · GFIE test | 3D Dist.: 0.543 -> 0.311 | Improved |
| Combine predicted heatmap with the proposed 3D inference strategy instead of using the heatmap alone (ablation) | GFIE · GFIE test | 3D Dist.: 0.333 -> 0.311 | Improved |
Later papers that compared with this method
2 later accepted papers report GFIE as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding (CVPR 2025 · better on 2 of 2 shared results)
- Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels (CVPR 2025 · better on 1 of 1 shared result)
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.
- Gaze360 — Gaze360: Physically Unconstrained Gaze Estimation in the Wild (ICCV 2019) · better on 4 of 4 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
- GA3CE: Unconstrained 3D Gaze Estimation with Gaze-Aware 3D Context Encoding (CVPR 2025 · similarity 0.87)
- Toward Semantic Gaze Target Detection (NeurIPS 2024 · similarity 0.87)
- Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels (CVPR 2025 · similarity 0.86)
- OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild (NeurIPS 2025 · similarity 0.85)
- Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders (CVPR 2025 · similarity 0.85)
- Gaze from Origin: Learning for Generalized Gaze Estimation by Embedding the Gaze Frontalization Process (AAAI 2024 · similarity 0.85)
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.
