Signals 4 · free daily AI digest

BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives

Paper recorded by Signals 4 on 2026-08-31 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-31 on arXiv · recorded by Signals 4 on 2026-09-01

Category: cs.CV · 计算机视觉 · first seen 2026-09-01

Abstract

We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular video and a static object mesh, BLARM predicts a temporally coherent animated mesh whose motion follows the video. Rather than relying on explicit rigs or directly regressing high-dimensional vertex motion, we represent animation using a compact set of learned, time-varying rigid motion components and t

Read on arXiv →

#194 most recent of 237 cs.CV papers we have recorded · ↑ newer: BRF-GS: Hyperspectral Bidirectional Reflectance Factor Modeling and Im · ↓ older: VeriCam: A Verification Baseline for the Classification of Unknown Dat
Cite this page: BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives: the #194 most recent of 237 cs.CV papers we have recorded (as of 2026-08-31). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/blarm-animating-3d-objects-from-video-via-blending-latent-rigid-motion-primitive.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