Signals 4 · free daily AI digest

Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence

Paper recorded by Signals 4 on 2026-10-27 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-27 on arXiv · recorded by Signals 4 on 2026-10-28

Category: cs.CV · 计算机视觉 · first seen 2026-10-28

Abstract

Cross-view object correspondence identifies the same object across views. However, existing methods often rely on frame-wise matching or sequential tracking, which can propagate correspondence errors under appearance changes or occlusions. Therefore, we introduce cross-view temporal object correspondence, which requires preserving object identity across both views and time from a query mask. To ad

Read on arXiv →

#83 most recent of 710 cs.CV papers we have recorded · ↑ newer: Can Discrete Tokens Serve as Semantically Lossless Representations of · ↓ older: Know, then Draw: A New Learning Paradigm for Visual Generation
Cite this page: Repurposing Video Diffusion Transformers for Cross-View Temporal Object Correspondence: the #83 most recent of 710 cs.CV papers we have recorded (as of 2026-10-27). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/repurposing-video-diffusion-transformers-for-cross-view-temporal-object-correspo.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CV papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions