AI Paper Atlas

Research map / 3D vision / Depth and stereo

Real2Sim2Real: RetinalDepth-64K for Depth Estimation in Posterior Segment Ophthalmic Surgery

Bingwen Dong, Gan Liu, Xiaoxi Lu, Guangcheng Chen, Jialu Zhang, Yan Hu, Xiaoqing Zhang, Jiang Liu

CVPR 2026 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth

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
fine-tune Depth Anything on RetinalDepthDepth Anything · RetinalDepth single-image test (whole scene)d1: 0.591 -> 0.975Improved
fine-tune VGGT on RetinalDepthVGGT · RetinalDepth single-image test (whole scene)Abs Rel: 0.322 -> 0.061Improved
fine-tune Marigold on RetinalDepthMarigold · RetinalDepth single-image test (whole scene)d1: 0.587 -> 0.885Improved
fine-tune DUSt3R on RetinalDepthDUSt3R · RetinalDepth single-image test (whole scene)d1: 0.015 -> 0.872Improved
fine-tune MoGE on RetinalDepthMoGE · RetinalDepth single-image test (whole scene)d1: 0.430 -> 0.935Improved
fine-tune stereo models and evaluate on instrument regionVGGT · RetinalDepth single-image test (instrument region)d1: 0.612 (whole, zero-shot) -> 0.339 (instrument, fine-tuned)Mixed
fine-tune monocular models and evaluate on instrument regionDepth Anything V2 · RetinalDepth single-image test (instrument region)d1: 0.889Improved
use stereo VGGT instead of monocular models zero-shotVGGT · RetinalDepth single-image test (zero-shot)d1: 0.591 -> 0.612Improved
use fine-tuned single-image models frame-by-frame instead of zero-shot video modelsVGGT · RetinalDepth video testd1: 0.228 -> 0.956Improved
use video-specific model VDA-L instead of fine-tuned VGGT for temporal stabilityVDA-L · RetinalDepth video testTDV: 5.870 -> 0.044Improved
use frame-by-frame stereo VGGT for temporal consistencyVGGT · RetinalDepth video testTDV: 5.870Hurt

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