AI Paper Atlas

Research map / 3D vision / Depth and stereo

R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras

Aron Schmied, Tobias Fischer, Martin Danelljan, Marc Pollefeys, Fisher Yu

ICCV 2023 · 3D vision › Depth and stereo · approach: Feed-forward 3D reconstruction · 35 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 multi-camera DBA to geometric estimation (ablation)R3D3 geometric estimation · DDADATE** (m): 2.134 -> 0.435Improved
add VKITTI fine-tuning of geometric estimation (ablation)R3D3 geometric estimation · DDADAbs Rel: 0.442 -> 0.320Improved
add VKITTI fine-tuning (ablation)R3D3 geometric estimation · DDADATE (m, absolute scale): 1.672 -> 2.356Hurt
add depth refinement network on top of geometric estimation (ablation)R3D3 · DDADAbs Rel: 0.320 -> 0.162Improved
add geometric estimation prior to refinement network (ablation)R3D3 · DDADdelta_1.25: 0.715 -> 0.811Improved
add confidence weights as refinement network input (ablation)depth refinement network · DDADAbs Rel: 0.181 -> 0.173Improved
sparsify input depth by w_i < beta in addition to confidence (ablation)depth refinement network · DDADAbs Rel: 0.173 -> 0.162Improved
use new co-visibility graph construction instead of original algorithm (ablation)R3D3 · DDADinference time (s): 3.23 -> 0.35Improved
new co-visibility graph versus original on pose accuracy (ablation)R3D3 · DDADATE (m): 0.982 -> 1.235Hurt
full R3D3 versus single-camera multi-frame methods on front cameraR3D3 · DDAD front cameraAbs Rel: 0.135 -> 0.128 (Abs Rel); RMSE 12.477 vs 13.214Mixed
combine geometric estimation with refinement; effect on side-view cameras (ablation)R3D3 · DDAD per-cameraAbs Rel (Front Left): 0.213 -> 0.160 (refinement only vs full)Improved

Later papers that compared with this method

3 later accepted papers report R3D3 as a baseline in their results tables; 3 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