AI Paper Atlas

Research map / 3D vision / Depth and stereo

Extending Foundational Monocular Depth Estimators to Fisheye Cameras with Calibration Tokens

Suchisrit Gangopadhyay, Jung-Hee Kim, Xien Chen, Patrick Rim, Hyoungseob Park, Alex Wong

ICCV 2025 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 9 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
add layer-wise Calibration Tokens (unique per encoder layer) instead of a single token set (ablation)UniDepth + Calibration Tokens · ScanNet++RMSE: 0.254 -> 0.244Improved
add layer-wise Calibration Tokens instead of a single token set (ablation)UniDepth + Calibration Tokens · KITTI-360RMSE: 2.065 -> 2.040Improved
use LogL1 loss instead of L1 (ablation)UniDepth + Calibration Tokens · ScanNet++RMSE: 0.260 -> 0.254Improved
compute loss in perspective frame (inverse-warp fisheye output) instead of fisheye frame (ablation)UniDepth + Calibration Tokens · ScanNet++RMSE: 0.280 -> 0.244Improved
use unique tokens per layer rather than one same token re-added every block (ablation)UniDepth + Calibration Tokens · ScanNet++RMSE: 0.290 -> 0.244Improved
train tokens with ground-truth depth rather than self-supervised FMDE pseudo-labels (ablation)UniDepth + Calibration Tokens · KITTI-360RMSE: 2.040 -> 1.994Improved
use Calibration Tokens instead of full finetuning on synthetic fisheye imagesMiDaS · KITTI-360RMSE: 9.289 -> 2.348Improved
add Calibration Tokens to DepthAnythingDepthAnything · KITTI-360delta1: 0.839 -> 0.810Mixed
add Calibration Tokens to UniDepthUniDepth · KITTI-360delta1: 0.663 -> 0.664No clear effect
add Calibration Tokens to UniDepthUniDepth · ScanNet++RMSE: 0.279 -> 0.244Improved

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