AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Efficiently Reconstructing Dynamic Scenes One D4RT at a Time

Chuhan Zhang, Guillaume Le Moing, Skanda Koppula, Ignacio Rocco, Liliane Momeni, Junyu Xie, Shuyang Sun, Rahul Sukthankar, Joëlle K. Barral, Raia Hadsell, Zoubin Ghahramani, Andrew Zisserman and 2 more

CVPR 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 30 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 local RGB appearance patch to decoder queries (ablation)D4RT ViT-L · Sintel video depthAbsRel (S): 0.366 -> 0.302Improved
add local RGB appearance patch to decoder queries (ablation)D4RT ViT-L · Sintel camera poseATE: 0.173 -> 0.091Improved
initialize encoder from VideoMAE instead of random weights (ablation)D4RT · Sintel video depthAbsRel (S): 0.738 -> 0.302Improved
initialize encoder from VideoMAE instead of random weights (ablation)D4RT · Sintel camera poseRPE-R: 1.126 -> 0.245Improved
scale encoder from ViT-B to ViT-g (ablation)D4RT · Sintel video depthAbsRel (S): 0.319 -> 0.191Improved
add 2D position auxiliary loss (ablation)D4RT · Sintel video depthAbsRel (S): +0.071 when removedImproved
add normal auxiliary loss (ablation)D4RT · Sintel video depthAbsRel (S): +0.043 when removedImproved
add confidence auxiliary loss (ablation)D4RT · Sintel camera poseATE: +0.126 when removedImproved
add confidence auxiliary loss (ablation)D4RT · Sintel video depthAbsRel (SS): -0.025 when removedHurt
add visibility auxiliary loss (ablation)D4RT · Sintel camera pose and depthRPE-R / AbsRel (SS): +0.022 RPE-R, -0.025 AbsRel (SS) when removedMixed
add displacement auxiliary loss (ablation)D4RT · Sintel video depth and poseAbsRel (S) / ATE: +0.011 AbsRel (S), +0.011 ATE when removedImproved
add RGB patches at original resolution at decoding (ablation)D4RT ViT-g · Sintel depth boundaryPDBE (scale): 2.254 -> 2.193Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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