TY - GEN
T1 - Recovering Dense Metric Depth in Indoor Scenes from Monocular Depth Foundation Models and 2D LiDARs
AU - Marsal, Rémi
AU - Chapoutot, Alexandre
AU - Xu, Philippe
AU - Filliat, David
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.
PY - 2025/1/1
Y1 - 2025/1/1
N2 - Recently, the first foundation models for monocular depth estimation such as Depth Anything have emerged . However, by being trained to make affine-invariant predictions, these methods rely on fine-tuning for making metric depth predictions and therefore perform poorly on zero-shot metric depth estimation. In a real use case, the fine-tuning stage is costly because a dedicated dataset with ground truth depth must be created and used as a training set. Additionally, fine-tuning can compromise the model’s generalization ability. This paper proposes to leverage 2D LiDARs to rescale Depth Anything’s predictions in the context of indoor scenes so as to prevent expensive fine-tuning or harming the model capacity. Our experiments demonstrate similar performance with fine-tuned approaches and enhanced results over zero-shot metric depth estimation methods.
AB - Recently, the first foundation models for monocular depth estimation such as Depth Anything have emerged . However, by being trained to make affine-invariant predictions, these methods rely on fine-tuning for making metric depth predictions and therefore perform poorly on zero-shot metric depth estimation. In a real use case, the fine-tuning stage is costly because a dedicated dataset with ground truth depth must be created and used as a training set. Additionally, fine-tuning can compromise the model’s generalization ability. This paper proposes to leverage 2D LiDARs to rescale Depth Anything’s predictions in the context of indoor scenes so as to prevent expensive fine-tuning or harming the model capacity. Our experiments demonstrate similar performance with fine-tuned approaches and enhanced results over zero-shot metric depth estimation methods.
KW - Zero-shot metric monocular depth estimation
UR - https://www.scopus.com/pages/publications/105006622535
U2 - 10.1007/978-3-031-89471-8_36
DO - 10.1007/978-3-031-89471-8_36
M3 - Conference contribution
AN - SCOPUS:105006622535
SN - 9783031894701
T3 - Springer Proceedings in Advanced Robotics
SP - 236
EP - 241
BT - European Robotics Forum 2025 - Boosting the Synergies between Robotics and AI for a Stronger Europe
A2 - Huber, Marco
A2 - Verl, Alexander
A2 - Kraus, Werner
PB - Springer Nature
T2 - 16th European Robotics Forum, ERF 2025
Y2 - 25 March 2025 through 27 March 2025
ER -