AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Light Touch Approach to Teaching Transformers Multi-View Geometry

Yash Bhalgat, João F. Henriques, Andrew Zisserman

CVPR 2023 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 8 citations (OpenAlex)

This paper tried a common change: Add positional encoding

Use explicit Epipolar Positional Encoding instead of implicit Epipolar Loss · CO3D-Retrieve full images · R@1: 90.57 -> 88.53 Hurt

What 646 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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 Epipolar Loss to RRT + R50RRT + R50 · CO3D-Retrieve full imagesR@1: 89.20 -> 90.57Improved
Add Epipolar Loss to RRT + R50RRT + R50 · CO3D-Retrieve masked backgroundsR@1: 83.28 -> 85.07Improved
Add Epipolar Loss to RRT + R50RRT + R50 · Stanford Online ProductsR@1: 84.46 -> 84.74Improved
Add Epipolar Loss to RRT + R50RRT + R50 trained on CO3D-Retrieve · SOP zero-shotR@1: 76.32 -> 76.78Improved
Replace Epipolar Loss with Max-Epipolar Loss (ablation)RRT + R50 · CO3D-Retrieve full imagesR@1: 90.57 -> 90.69Improved
Replace Epipolar Loss with Max-Epipolar Loss (ablation)RRT + R50 · CO3D-Retrieve masked backgroundsR@1: 85.07 -> 85.17Improved
Replace Epipolar Loss with Max-Epipolar Loss (ablation)RRT + R50 · Stanford Online ProductsR@1: 84.74 -> 84.53Hurt
Use explicit Epipolar Positional Encoding instead of implicit Epipolar Loss (ablation)RRT + R50 · CO3D-Retrieve full imagesR@1: 90.57 -> 88.53Hurt
Use explicit Epipolar Positional Encoding instead of implicit Epipolar Loss (ablation)RRT + R50 · Stanford Online ProductsR@1: 84.74 -> 82.57Hurt
Increase local feature resolution from 7×7 to 14×14 (ablation)RRT + R50 trained with LEPI · CO3D-Retrieve full imagesR@1: 90.57 -> 90.71Improved

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