EgoLabel: Zero-Shot Egocentric Auto-Labeling with Cross-Modal Consistency
Overview
This research introduces EgoLabel, a zero-shot pipeline for egocentric auto-labeling that combines off-the-shelf models to ensure cross-modal consistency in depth, camera pose, object, and human-pose estimates without requiring target-domain labeled training.
Generated from attributed reports · Updated 3 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Data origin: human egocentric
“arXiv:2611.12149v1 Announce Type: cross Abstract: Egocentric auto-labeling requires depth, camera pose, object, and human-pose estimates to agree across independently developed models. Differences in units, coordinate conventions, and scale can make individually plausible predictions geometrically inconsistent. We present \textbf{EgoLabel}, a zero-shot pipeline that combines off-the-shelf models without target-domain”
Exact source · revision 1Source owner not reported
Reported quantity · pooled median hand depth residual: 84.6 other · Basis not reported
“an hand--depth residuals by $23\%$ relative to a single global scale, yielding a pooled median of $84.6\,\mathrm{mm}$ against a $20.5\,\mathrm{mm}$ ground-truth reference. Hand PA-MPJPE is $14.53\pm1.29\,\mathrm{mm}$, whereas absolute MPJPE is $119.1\pm31.3\,\mathrm{mm}$, revealing a substantial gap between aligned and metric accuracy. On three RGB-only sequences, camera ATE is $1.40\pm0.29\,\mathrm{cm}$ after $\math”
Exact source · revision 1Source owner not reported
Reported quantity · ground-truth reference hand depth residual: 20.5 other · Basis not reported
“an hand--depth residuals by $23\%$ relative to a single global scale, yielding a pooled median of $84.6\,\mathrm{mm}$ against a $20.5\,\mathrm{mm}$ ground-truth reference. Hand PA-MPJPE is $14.53\pm1.29\,\mathrm{mm}$, whereas absolute MPJPE is $119.1\pm31.3\,\mathrm{mm}$, revealing a substantial gap between aligned and metric accuracy. On three RGB-only sequences, camera ATE is $1.40\pm0.29\,\mathrm{cm}$ after $\math”
Exact source · revision 1Source owner not reported
Reported quantity · hand PA-MPJPE: 14.53 other · Basis not reported
“an hand--depth residuals by $23\%$ relative to a single global scale, yielding a pooled median of $84.6\,\mathrm{mm}$ against a $20.5\,\mathrm{mm}$ ground-truth reference. Hand PA-MPJPE is $14.53\pm1.29\,\mathrm{mm}$, whereas absolute MPJPE is $119.1\pm31.3\,\mathrm{mm}$, revealing a substantial gap between aligned and metric accuracy. On three RGB-only sequences, camera ATE is $1.40\pm0.29\,\mathrm{cm}$ after $\math”
Exact source · revision 1Source owner not reported
Reported quantity · absolute MPJPE: 119.1 other · Basis not reported
“an hand--depth residuals by $23\%$ relative to a single global scale, yielding a pooled median of $84.6\,\mathrm{mm}$ against a $20.5\,\mathrm{mm}$ ground-truth reference. Hand PA-MPJPE is $14.53\pm1.29\,\mathrm{mm}$, whereas absolute MPJPE is $119.1\pm31.3\,\mathrm{mm}$, revealing a substantial gap between aligned and metric accuracy. On three RGB-only sequences, camera ATE is $1.40\pm0.29\,\mathrm{cm}$ after $\math”
Exact source · revision 1Source owner not reported
Reported quantity · camera ATE: 1.4 other · Basis not reported
“an hand--depth residuals by $23\%$ relative to a single global scale, yielding a pooled median of $84.6\,\mathrm{mm}$ against a $20.5\,\mathrm{mm}$ ground-truth reference. Hand PA-MPJPE is $14.53\pm1.29\,\mathrm{mm}$, whereas absolute MPJPE is $119.1\pm31.3\,\mathrm{mm}$, revealing a substantial gap between aligned and metric accuracy. On three RGB-only sequences, camera ATE is $1.40\pm0.29\,\mathrm{cm}$ after $\math”
Exact source · revision 1Source owner not reported
Reported quantity · number of sequences evaluated: 20 other · reported trials
“labeled training and provides explicit cross-modal registration and consistency diagnostics. The pipeline integrates MonST3R for geometry, LocateAnything with GMC-BoT-SORT and SAM~2 for objects, and V-HPOT for hands; FisheyeViT provides a separate whole-body compatibility demonstration. Our main hand evaluation uses H2O sensor depth. Across 20 sequences, per-hand depth anchoring reduces the mean of per-sequence medi”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalEgoLabel: Zero-Shot Egocentric Auto-Labeling with Cross-Modal Consistency
This research introduces EgoLabel, a zero-shot pipeline for egocentric auto-labeling that combines off-the-shelf models to ensure cross-modal consistency in depth, camera pose, object, and human-pose estimates without requiring target-domain labeled training.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).