AI Paper Atlas

Research map / 3D vision / Depth and stereo

From Perspective to Fisheye Depth Estimation and Open-Vocabulary Segmentation

Rit Gangopadhyay, Alex Wong

ECCV 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 2 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 Distortion Extenders to frozen backboneUniDepthV2 · ScanNet++ (real fisheye depth)RMSE: 0.329 -> 0.200Improved
add Distortion Extenders to frozen backboneUniDepthV2 · KITTI-360 (real fisheye depth)RMSE: 7.093 -> 1.663Improved
add DEX instead of LoRADepthAnything · ScanNet++ (real fisheye depth)RMSE: 0.706 -> 0.414Improved
fine-tune with LoRADepthAnything · ScanNet++ (real fisheye depth)RMSE: 0.705 -> 0.706No clear effect
DEX vs Calibration TokensMiDaS · KITTI-360 (real fisheye depth)delta1: 0.699 -> 0.657Hurt
DEX vs Calibration Tokens on MiDaSMiDaS · KITTI-360 (real fisheye depth)RMSE: 2.588 -> 2.451Improved
DEX vs LoRA on UniDepthV2UniDepthV2 · KITTI-360 (real fisheye depth)delta1: 0.771 -> 0.842Improved
apply DEX to UniDepthV2 vs UniK3DUniDepthV2 · ScanNet++ (real fisheye depth)RMSE: 0.223 -> 0.200Improved
apply DEX to open-vocab segmentationLSeg · WoodScape (open-vocab seg)mIoU: 0.305 -> 0.362Improved
apply DEX to CNN-based SEDSED · WoodScape (open-vocab seg)mIoU: 0.439 -> 0.449Improved
insert DEX at all blocks vs only the first block (ablation)DEX (UniDepthV2) · KITTI-360 (real fisheye depth)RMSE: 1.979 -> 1.663Improved
use per-layer Extenders instead of one shared set (ablation)DEX (UniDepthV2) · KITTI-360 (real fisheye depth)delta1: 0.779 -> 0.842Improved

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.

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

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