AI Paper Atlas

Research map / 3D vision / Depth and stereo

Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction

Edgar Sucar, Zihang Lai, Eldar Insafutdinov, Andrea Vedaldi

ICCV 2025 · 3D vision › Depth and stereo · approach: Feed-forward 3D 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
replace MonST3R with DPM for two-view depth (Kubric)MonST3R · Two-view depth, KubricAbs Rel: 0.166 -> 0.078Improved
replace MonST3R with DPM for two-view depth (Bonn)MonST3R · Two-view depth, BonnAbs Rel: 0.071 -> 0.082Hurt
replace MonST3R with DPM for two-view depth (Sintel)MonST3R · Two-view depth, SintelAbs Rel: 0.347 -> 0.321Improved
replace MonST3R with DPM for video depth (KITTI)MonST3R · Video depth, KITTIAbs Rel: 0.104 -> 0.140Hurt
replace MonST3R with DPM for video depth (KITTI crop)MonST3R · Video depth, KITTI (crop)Abs Rel: 0.111 -> 0.097Improved
remove optical flow loss from bundle adjustment when using DPMDPM video depth · Video depthAbs RelNo clear effect
predict cross-time point maps with DPM instead of MonST3R+RAFTMonST3R+RAFT · Kubric-F dynamic reconstructionL_rel P1(t2): 0.394 -> 0.049Improved
predict cross-time point maps with DPM (Kubric-G)MonST3R+RAFT · Kubric-G dynamic reconstructionL_rel P1(t2): 0.346 -> 0.079Improved
use DPM for object pose trackingMonST3R+RAFT · Kubric-F object poseRPE rot: 56.1 -> 33.7Improved
use DPM for scene flow instead of MonST3RMonST3R · Scene flow, Kubric-G forward3D EPE: 0.334 -> 0.104Improved
use RGB-only DPM instead of RGBD RAFT-3D for scene flow (Kubric-F)RAFT-3D · Scene flow forward, Kubric-F3D EPE: 0.051 -> 0.081Hurt
use RGB-only DPM instead of RGBD RAFT-3D for scene flow (Waymo)RAFT-3D · Scene flow forward, Waymo3D EPE: 0.150 -> 0.051Improved

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