AI Paper Atlas

Research map / Detection and segmentation / Tracking

Multi-Object System Identification from Videos

Chunjiang Liu, Xiaoyuan Wang, Qingran Lin, Albert Xiao, Haoyu Chen, Shizheng Wen, Hao Zhang, Lu Qi, Ming-Hsuan Yang, Laszlo A. Jeni, Min Xu, Yizhou Zhao

ICLR 2026 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT

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
optimize continuous per-object material parameters instead of selecting from a fixed material libraryMOSIV vs OmniPhysGS-RGB · MOSIV synthetic dataset, observable simulationPSNR: 25.93 -> 30.51Improved
optimize continuous per-object parametersMOSIV vs OmniPhysGS-RGB · MOSIV synthetic dataset, future simulationPSNR: 19.00 -> 28.26Improved
give OmniPhysGS-RGB the ground-truth per-object material models (oracle) (ablation)OmniPhysGS-RGB · MOSIV synthetic dataset, observable simulationChamfer distance: 11.79 -> 43.50Hurt
use object-wise Chamfer and silhouette losses instead of scene-wise losses (ablation)MOSIV · MOSIV 6-scene subsetChamfer distance: 22.13 -> 0.696Improved
use object-wise Chamfer and silhouette losses instead of scene-wise losses (ablation)MOSIV · MOSIV 6-scene subsetPSNR: 27.89 -> 30.24Improved
add silhouette alpha loss to object-aware Chamfer loss (ablation)MOSIV · MOSIV 6-scene subsetChamfer distance: 1.17 -> 0.696Improved
add Chamfer loss to object-aware silhouette loss (ablation)MOSIV · MOSIV 6-scene subsetChamfer distance: 0.985 -> 0.696Improved
use MOSIV rather than reproduced CoupNeRF implicit representationMOSIV vs CoupNeRF* · MOSIV dataset, future simulationPSNR: 20.62 -> 28.92Improved
use MOSIV with Gaussian-based explicit representation instead of CoupNeRFMOSIV · training cost per 30-frame sequenceTraining time (s): 9591.09 -> 5021.46Improved
increase noise added to reconstructed Gaussians from 0.005 to 0.05 (ablation)MOSIV · sensitivity, i.i.d. noise, observable simulationPSNR: 27.86 -> 23.73Hurt
extend to three-object scenesMOSIV · MOSIV dataset extension (3 objects)PSNR: observable 23.98, future 19.81Hurt

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