AI Paper Atlas

Research map / Video / Video segmentation and tracking

Featurising Pixels from Dynamic 3D Scenes with Linear In-Context Learners

Nikita Araslanov, Martin Sundermeyer, Hidenobu Matsuki, David Joseph Tan, Federico Tombari

CVPR 2026 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 1 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 linear in-context learning instead of ERM distillation of the same cues (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 61.1 -> 73.9Improved
add depth and flow cues on top of self-distillation (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 68.6 -> 73.9Improved
add self-distillation cue (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 72.6 -> 73.9Improved
add depth cue (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 72.6 -> 73.9Improved
add optical flow cue (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 72.5 -> 73.9Improved
add flow cue (ablation)LILA (DINOv2-S14) · COCO-StuffmIoU: 59.3 -> 59.6No clear effect
add PAMR refinement of encoder features (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 71.9 -> 73.9Improved
add cropping to synthesise queries (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 72.4 -> 73.9Improved
add temporal sampling of frame pairs (ablation)LILA (DINOv2-S14) · DAVIS-2017J&F (LP / k-NN): 69.3 / 72.4 -> 68.6 / 73.9Mixed
add edge (gradient matching) loss (ablation)LILA (DINOv2-S14) · DAVIS-2017 (k-NN)J&F: 72.9 -> 73.9Improved
train LILA on Kinetics instead of YouTube-VOSLILA (DINOv2-L14) · DAVIS-2017 (linear probing)J&F: 69.0 -> 69.3Improved
train LILA on Kinetics instead of YouTube-VOSLILA (DINOv2-L14) · COCO-StuffmIoU: 62.8 -> 63.3Improved

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