AI Paper Atlas

Research map / Video / Video segmentation and tracking

Tracking by Predicting 3-D Gaussians Over Time

Tanish Baranwal, Himanshu Gaurav Singh, Jathushan Rajasegaran, Jitendra Malik

CVPR 2026 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 0 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
integrate mean (motion) deltas during pretraining (ablation)Video-GMAE large · TAP-Vid Davis (large, finetuned)AJ: 39.1 -> 44.4Improved
add RGB deltas on top of mean deltas (ablation)Video-GMAE large · TAP-Vid Davis (large, finetuned)AJ: 44.4 -> 44.7No clear effect
integrate RGB deltas only (ablation)Video-GMAE large · TAP-Vid Davis (large, finetuned)AJ: 39.1 -> 42.5Improved
pretrain on 24 frames instead of 2 (stride = frames) (ablation)Video-GMAE base · TAP-Vid Davis (base, finetuned), stride = framesAJ: 55.4 -> 24.7Hurt
pretrain on 4 or 8 frames vs 2, evaluated at stride 2 (ablation)Video-GMAE base · TAP-Vid Davis (base, finetuned), stride 2AJ: 55.4 -> 64.2 (4), 63.5 (8); 57.5 (16), 52.4 (24)Mixed
correspondence-aware Gaussian decoder instead of patch reconstructionMAE-ST/VideoMAE · TAP-Vid Kinetics (frozen encoder)AJ: 46.9 -> 65.1 (vs VideoMAE)Improved
finetune encoder instead of freezing (ablation)Video-GMAE large · TAP-Vid KineticsAJ: 65.1 -> 75.1Improved
scale base to large (frozen encoder) (ablation)Video-GMAE · TAP-Vid DavisAJ: 45.2 -> 46.7Improved
fine-tuned Video-GMAE vs supervised trackersVideo-GMAE large finetune · TAP-Vid DavisAJ: 57.9 vs CoTracker3 63.8Hurt
zeroshot Gaussian tracking vs GMRW-CVideo-GMAE zeroshot · TAP-Vid KineticsAJ: 31.9 -> 60.1Improved

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