GazeShift: Unsupervised Gaze Estimation and Dataset for VR | Signal Canvas | ScienceToStartup

← Back to Paper

GazeShift: Unsupervised Gaze Estimation and Dataset for VR

Stale68d agoVerification pending / evidence receipt incomplete

Export Brief Open in Build Loop Connect with Author

Viability

0.0/10

Compared to this week’s papers

Verification pending

Use This Via API or MCP

Use Signal Canvas as the narrative proof surface

Signal Canvas is the citation-first public layer for turning one paper into a structured commercialization narrative. Use it to hand off into REST, MCP, Build Loop, and launch-pack execution without losing source lineage.

Signal Canvas API Paper Proof Page Open Build Loop Launch Pack Example

Use This Via API or MCP

Use this Signal Canvas via API or MCP

Route this paper proof surface into REST, MCP, or developer workflows while preserving the same evidence receipt and related-resource context.

Signal Canvas guide REST guide MCP guide

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr

stale

Proof freshness: stale
Proof status: unverified
Display score: 8/10
Last proof check: 2026-04-02
Score updated: 2026-04-02
Score fresh until: 2026-05-02
References: 0
Source count: 0
Coverage: 17%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

GazeShift: Unsupervised Gaze Estimation and Dataset for VR

Canonical ID gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr | Route /signal-canvas/gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr",
    "query_text": "Summarize GazeShift: Unsupervised Gaze Estimation and Dataset for VR"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "GazeShift: Unsupervised Gaze Estimation and Dataset for VR",
  "normalized_query": "2603.07832",
  "route": "/signal-canvas/gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr",
  "paper_ref": "gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Paper mode· single-doc scopescope: gazeshift-unsupervised-gaze-estimation-and-dataset-for-vr

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 7Mixed 0Weak 0

Evidencepartial
we introduce VRGaze - the first large-scale off-axis gaze estimation dataset for VR - comprising 2.1 million near-eye infrared images collected from 68 participants.
Implicationpartial
The abstract explicitly states this and provides the dataset size and participant count.
Verificationpartial
partial
Evidencepartial
we further propose GazeShift, an attention-guided unsupervised framework for learning gaze representations without labeled data.
Implicationpartial
The abstract clearly defines GazeShift's nature and its unsupervised learning approach.
Verificationpartial
partial
Evidencepartial
achieving a 1.84-degree mean error on VRGaze.
Implicationpartial
The abstract provides a specific numerical result for GazeShift's performance on the VRGaze dataset.
Verificationpartial
partial
Evidencepartial
On the remote-camera MPIIGaze dataset, the model achieves a 7.15-degree person-agnostic error
Implicationpartial
The abstract provides a specific numerical result for GazeShift's performance on the MPIIGaze dataset.
Verificationpartial
partial
Evidencepartial
doing so with 10x fewer parameters and 35x fewer FLOPs than baseline methods.
Implicationpartial
The abstract quantifies the efficiency of GazeShift compared to baselines with specific multipliers.
Verificationpartial
partial
Evidencepartial
Deployed natively on a VR headset GPU, inference takes only 5 ms.
Implicationpartial
The abstract provides a specific inference time for GazeShift in a VR deployment context.
Verificationpartial
partial
Evidencepartial
Combined with demonstrated robustness to illumination changes, these results highlight GazeShift as a label-efficient, real-time solution for VR gaze tracking.
Implicationpartial
The abstract explicitly mentions this characteristic as a demonstrated result.
Verificationpartial
partial

Startup potential card

Startup potential card preview

Share on X LinkedIn