paper-with-me

Papers

StableMotion: Repurposing Diffusion-Based Image Priors for Motion Estimation

2025-05-10 · Ziyi Wang, Haipeng Li, Lin Sui, Tianhao Zhou, Hai Jiang, Lang Nie, Shuaicheng Liu

We present StableMotion, a novel framework leverages knowledge (geometry and content priors) from pretrained large-scale image diffusion models to perform motion estimation, solving single-image-based image rectification tasks such as Stitched Image Rectangling (SIR) and Rolling Shutter Correction (RSC). Specifically, StableMotion framework takes text-to-image Stable Diffusion (SD) models as backbone and repurposes it into an image-to-motion estimator. To mitigate inconsistent output produced by diffusion models, we propose Adaptive Ensemble Strategy (AES) that consolidates multiple outputs into a cohesive, high-fidelity result. Additionally, we present the concept of Sampling Steps Disaster (SSD), the counterintuitive scenario where increasing the number of sampling steps can lead to poorer outcomes, which enables our framework to achieve one-step inference. StableMotion is verified on two image rectification tasks and delivers state-of-the-art performance in both, as well as showing strong generalizability. Supported by SSD, StableMotion offers a speedup of 200 times compared to previous diffusion model-based methods.

📄 PDF Abstract BibTeX arXiv:2505.06668

Code (0)

등록된 구현이 없습니다.

Tasks

Motion EstimationRolling Shutter Correction

Methods 이 논문이 사용한 방법론

Non Maximum Suppression Non Maximum Suppression is a computer vision method that selects a single entity out of many overlapping entities (for example bounding boxes in object detection). The…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
SSD SSD is a single-stage object detection method that discretizes the output space of bounding boxes into a set of default boxes over different aspect ratios and scales per…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data

2025-05-06 · Yuxuan Mu, Hung Yu Ling, Yi Shi, Ismael Baira Ojeda 외

Motion capture (mocap) data often exhibits visually jarring artifacts due to inaccurate sensors and post-processing. Cleaning this corrupted data can require substantial manual effort from human experts, which can be a c…

Motion Generation

Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards

2025-05-27 · Aakash Garg, Libing Zeng, Andrii Tsarov, Nima Khademi Kalantari

In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a diffusion model from scratch is not feasib…

TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

2026-05-12 · Jisu Nam, Jahyeok Koo, Soowon Son, Jaewoo Jung 외 arxiv

Dense 3D tracking from monocular video is fundamental to dynamic scene understanding. While recent 3D foundation models provide reliable per-frame geometry, recovering object motion in this geometry remains challenging a…

Scene Understanding3D Reconstruction

FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography

2026-04-01 · Wei Qian, Dan Guo, Jinxing Zhou, Bochao Zou 외 arxiv

Remote photoplethysmography (rPPG) enables contactless physiological monitoring by capturing subtle skin-color variations from facial videos. However, most existing methods predominantly rely on time-domain modeling, mak…

Representation Learning

DVD: Deterministic Video Depth Estimation with Generative Priors

2026-03-12 · Hongfei Zhang, Harold Haodong Chen, Chenfei Liao, Jing He 외 arxiv

Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand massive labeled datasets to resolve sem…

Depth Estimation