AI Paper Atlas

Research map / 3D vision / Depth and stereo

Dark3R: Learning Structure from Motion in the Dark

Andrew Y. Guo, Anagh Malik, SaiKiran Tedla, Yutong Dai, Yiqian Qin, Zach Salehe, Benjamin Attal, Sotiris Nousias, Kiriakos N. Kutulakos, David B. Lindell

CVPR 2026 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 4 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
use LoRA instead of full fine-tuning (ablation)Dark3R · low-light SfM (120 images)ATE: 0.476 -> 0.050Improved
use raw inputs instead of sRGB (ablation)Dark3R · low-light SfM (120 images)ATE: 0.087 -> 0.050Improved
supervise with clean raw pairs instead of clean sRGB pairs (ablation)Dark3R · low-light SfM (120 images)ATE: 0.064 -> 0.050Mixed
train on both simulated and captured data instead of simulated only (ablation)Dark3R · low-light SfM (120 images)ATE: 0.078 -> 0.050Improved
add L_clean regularization on clean pairs (ablation)Dark3R · low-light SfM (120 images)ATE: 0.051 -> 0.050No clear effect
fine-tune encoder, decoder and head vs encoder only (ablation)Dark3R · low-light SfM (120 images)ATE / RPE R: ATE 0.030 -> 0.050; RPE R 0.149 -> 0.121Mixed
Dark3R teacher-student adaptation vs MASt3R-SfMMASt3R-SfM · low-light SfM (120 images)ATE: 0.088 -> 0.050Improved
scale from 120 to full image set (bundle adjustment relied on more)Dark3R · low-light SfMATE: 0.050 -> 0.139Hurt
add depth supervision from Dark3R pointmaps (ablation)Dark3R-NeRF · low-light view synthesisPSNR: 34.91 -> 36.17Improved
avoid black level clipping (ablation)Dark3R-NeRF · low-light view synthesisPSNR: 34.98 -> 36.17Improved
add stochastic preconditioning (ablation)Dark3R-NeRF · low-light view synthesisPSNR: 36.05 -> 36.17Improved
Dark3R-NeRF vs LE3D on SSIMDark3R-NeRF · low-light view synthesisSSIM: 0.878 -> 0.866Hurt

Later papers that compared with this method

1 later accepted paper reports Dark3R as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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