Explanipedia

MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training Open

Xue, Haotian, Chen Qi, Wang Zhong-hao, Huang Xun, Shechtman, Eli , et al. · 2025

Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics. A key limitation is that the standard denoising MSE objec…

Respiratory Motion Compensation and Haptic Feedback for X-ray-Guided Teleoperated Robotic Needle Insertion Open

Cordon-Avila, Ana, Selim, Mostafa, Abayazid, Momen · 2025

Respiratory motion limits the accuracy and precision of abdominal percutaneous procedures. In this paper, respiratory motion is compensated robotically using motion estimation models. Additionally, a teleoperated insertion is performed usi…

Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance Open

Wang, Haoxuan, Tao, Jiachen, WU Junyi, Liu, Gaowen, Kompella, Ramana Rao , et al. · 2025

We present Motion Marionette, a zero-shot framework for rigid motion transfer from monocular source videos to single-view target images. Previous works typically employ geometric, generative, or simulation priors to guide the transfer proc…

ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding Open

Park, Byeongjun, Kim Byung Hoon, Chung, Hyungjin, Ye, Jong Chul · 2025

We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions o…

MotionV2V: Editing Motion in a Video Open

Burgert, Ryan, Herrmann, Charles, Cole, Forrester, Ryoo, Michael S., Wadhwa, Neal , et al. · 2025

While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance text-to-vi…

Augmented Reality Surgical Guidance System with Adaptive Depth-Based Registration Algorithms Open

James R. Whitmore, Sophie L. Bennett, Thomas K. Hughes, Amelia J. Clarke, Charlotte M. Foster · 2025

Intraoperative patient motion degrades static registration. We propose an adaptive AR guidance system with feedback-driven registration updates. The system employs particle filter-based motion compensation and multi-scale ICP refinement. I…

Motion Marionette: Rethinking Rigid Motion Transfer via Prior Guidance Open

Wang, Haoxuan, Tao, Jiachen, WU Junyi, Liu, Gaowen, Kompella, Ramana Rao , et al. · 2025

We present Motion Marionette, a zero-shot framework for rigid motion transfer from monocular source videos to single-view target images. Previous works typically employ geometric, generative, or simulation priors to guide the transfer proc…

MotionV2V: Editing Motion in a Video Open

Burgert, Ryan, Herrmann, Charles, Cole, Forrester, Ryoo, Michael S., Wadhwa, Neal , et al. · 2025

While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance text-to-vi…

ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding Open

Park, Byeongjun, Kim Byung Hoon, Chung, Hyungjin, Ye, Jong Chul · 2025

We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions o…

STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution Open

Chen Jun-Yang, Dong, Jiangxin, Sun Long, Yang Yixin, Pan, Jinshan · 2025

We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main ch…

STCDiT: Spatio-Temporally Consistent Diffusion Transformer for High-Quality Video Super-Resolution Open

Chen Jun-Yang, Dong, Jiangxin, Sun Long, Yang Yixin, Pan, Jinshan · 2025

We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main ch…

Point-to-Point: Sparse Motion Guidance for Controllable Video Editing Open

Song, Yeji, Lee， Jae-Hyun, Koo Mi-Jin, Lee， Jun-Hoo, Kwak, Nojun · 2025

Accurately preserving motion while editing a subject remains a core challenge in video editing tasks. Existing methods often face a trade-off between edit and motion fidelity, as they rely on motion representations that are either overfitt…

Point-to-Point: Sparse Motion Guidance for Controllable Video Editing Open

Song, Yeji, Lee， Jae-Hyun, Koo Mi-Jin, Lee， Jun-Hoo, Kwak, Nojun · 2025

Accurately preserving motion while editing a subject remains a core challenge in video editing tasks. Existing methods often face a trade-off between edit and motion fidelity, as they rely on motion representations that are either overfitt…

EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses Open

Pallotta, Enrico, Azar Sina Mokhtarzadeh, Doorenbos, Lars, Ozsoy, Serdar, Iqbal, Umar , et al. · 2025

Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusio…

MotionDuet: Dual-Conditioned 3D Human Motion Generation with Video-Regularized Text Learning Open

Zhang Yi-yang, Sun Tengjiao, Fang Pengcheng, Wang, Deng-Bao, Cai, Xiaohao , et al. · 2025

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent obse…

EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses Open

Pallotta, Enrico, Azar Sina Mokhtarzadeh, Doorenbos, Lars, Ozsoy, Serdar, Iqbal, Umar , et al. · 2025

Egocentric video generation with fine-grained control through body motion is a key requirement towards embodied AI agents that can simulate, predict, and plan actions. In this work, we propose EgoControl, a pose-controllable video diffusio…

MotionDuet: Dual-Conditioned 3D Human Motion Generation with Video-Regularized Text Learning Open

Zhang Yi-yang, Sun Tengjiao, Fang Pengcheng, Wang, Deng-Bao, Cai, Xiaohao , et al. · 2025

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent obse…

Show Me: Unifying Instructional Image and Video Generation with Diffusion Models Open

Pu, Yujiang, Huang ZhanBo, Boddeti, Vishnu, Kong Yu · 2025

Generating visual instructions in a given context is essential for developing interactive world simulators. While prior works address this problem through either text-guided image manipulation or video prediction, these tasks are typically…

Planning with Sketch-Guided Verification for Physics-Aware Video Generation Open

Huang Yidong, Wang, Zun, Lin Han, Kim, Dong-Ki, Omidshafiei, Shayegan , et al. · 2025

Recent video generation approaches increasingly rely on planning intermediate control signals such as object trajectories to improve temporal coherence and motion fidelity. However, these methods mostly employ single-shot plans that are ty…

Flow-Guided Implicit Neural Representation for Motion-Aware Dynamic MRI Reconstruction Open

Li Baoqing, Liu Yuanyuan, Liu Congcong, Zhu Qingyong, Cheng Jing , et al. · 2025

Dynamic magnetic resonance imaging (dMRI) captures temporally-resolved anatomy but is often challenged by limited sampling and motion-induced artifacts. Conventional motion-compensated reconstructions typically rely on pre-estimated optica…

Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features Open

Xu, Jingyi, Zheng Meisong, Chen Ying, Qiao, Minglang, Deng, Xin , et al. · 2025

Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, they suffer from error accumulation, spatial artifacts, and a trade-off between perceptual quality and fidelity, primarily c…

Planning with Sketch-Guided Verification for Physics-Aware Video Generation Open

Huang Yidong, Wang, Zun, Lin Han, Kim, Dong-Ki, Omidshafiei, Shayegan , et al. · 2025

Recent video generation approaches increasingly rely on planning intermediate control signals such as object trajectories to improve temporal coherence and motion fidelity. However, these methods mostly employ single-shot plans that are ty…

PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention Open

Chen Yi-peng, Ye Zhichao, Fang, Zhenzhou, Chen, Xinyu, Zhang Xiao-yu , et al. · 2025

We propose PostCam, a framework for novel-view video generation that enables post-capture editing of camera trajectories in dynamic scenes. We find that existing video recapture methods suffer from suboptimal camera motion injection strate…