Newest papers

Moving Regions, Not Moving Objects: Segmenting What Actually Moves under Camera Motion

Wenhua Jin, Tiancheng Chen, Sheng Tang, Jiahao Li, Yupeng Liu, Weiqi Zhang, Juntong Fang, Zesong Li · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31209 · cited by 0 works (OpenAlex) · open-access PDF

Indonesian

Segmentasi objek bergerak dari segmentasi kamera bergerak secara konvensional diformulasikan pada tingkat urutan dan objek, menandai seluruh instansi sebagai bergerak setelah bergerak ke mana-mana dalam sebuah video. Formulasi instan terbaru membedakan bergerak dari interval statis, tetapi masih menghasilkan topeng di tingkat objek melalui model dasar segmentasi beku. Karena topeng ini berasal dari proposal tingkat instansi, gerakan biasanya dikaitkan dengan seluruh instansi, bukannya terlokalisasi pada premis yang benar-benar bergerak. Selain itu, prediksi gerakan tingkat instansi seperti itu dapat menghasilkan topeng bahkan ketika tidak ada bagian dari instansi benar-benar bergerak, mengungkapkan masalah yang lebih fundamental: gerakan bukanlah properti intrinsik dari sebuah instansi; itu hanya dapat ditentukan dengan membandingkan setidaknya dua bingkai. Membangun pada premis ini, kami memperkenalkan MoRSe, yang secara bersama-sama menafsirkan dua bingkai gerakan untuk memp

Machine translation (Meta M2M100); the English original follows.

Abstract

Moving object segmentation is conventionally formulated at the sequence and object level, marking an entire instance as moving once it moves anywhere in a video. Recent instantaneous formulations distinguish moving from stationary intervals, but still generate masks at the object level through frozen segmentation foundation models. Because the mask is derived from an instance-level proposal, motion is typically attributed to the entire instance rather than localized to the regions that actually move. Moreover, such instance-level predictions can produce masks even when no part of the instance is actually moving, revealing a more fundamental issue: motion is not an intrinsic property of an instance; it can only be determined by comparing at least two frames. Building on this premise, we introduce MoRSe, which jointly interprets two frames to predict a moving-region mask, distinguishing actual scene motion from apparent motion induced by the camera. A single RGB encoder replaces multi-stage foundation stacks, so no optical flow, point tracks, or separate mask generator is needed at inference. We release MoRSe-5K, a benchmark of 42 sequences with Static, Dynamic-Static, and Dynamic settings designed to evaluate the model's ability to distinguish and localize moving and stationary regions under different camera and scene motion conditions. MoRSe outperforms both specialized moving object segmentation methods and dense 4D reconstruction methods with motion-thresholded predictions, while producing the fewest false positives on sequences where nothing moves.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer vision, Artificial intelligence, Segmentation, Computer science, Motion (physics), Object (grammar)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange