English
Related papers

Related papers: Interspatial Attention for Efficient 4D Human Vide…

200 papers

Recent advances in deep learning have enabled the generation of videos from textual descriptions as well as the prediction of future sequences from input videos. Similarly, in human motion modeling, motions can be generated from text or…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Masato Soga , Ryuki Takebayashi

We present 4DiM, a cascaded diffusion model for 4D novel view synthesis (NVS), supporting generation with arbitrary camera trajectories and timestamps, in natural scenes, conditioned on one or more images. With a novel architecture and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Daniel Watson , Saurabh Saxena , Lala Li , Andrea Tagliasacchi , David J. Fleet

Generation of realistic high-resolution videos of human subjects is a challenging and important task in computer vision. In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a…

Computer Vision and Pattern Recognition · Computer Science 2019-10-22 Polina Zablotskaia , Aliaksandr Siarohin , Bo Zhao , Leonid Sigal

Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Shitong Shao , Zikai Zhou , Haopeng Li , Yingwei Song , Wenliang Zhong , Lichen Bai , Zeke Xie

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…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Yipeng Chen , Zhichao Ye , Zhenzhou Fang , Xinyu Chen , Xiaoyu Zhang , Jialing Liu , Nan Wang , Haomin Liu , Guofeng Zhang

Recent text-to-video generation approaches rely on computationally heavy training and require large-scale video datasets. In this paper, we introduce a new task of zero-shot text-to-video generation and propose a low-cost approach (without…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Levon Khachatryan , Andranik Movsisyan , Vahram Tadevosyan , Roberto Henschel , Zhangyang Wang , Shant Navasardyan , Humphrey Shi

In the AIGC era, generating high-quality 4D content has garnered increasing research attention. Unfortunately, current 4D synthesis research is severely constrained by the lack of large-scale 4D datasets, preventing models from adequately…

Computer Vision and Pattern Recognition · Computer Science 2026-03-06 Wei Liu , Shengqiong Wu , Bobo Li , Haoyu Zhao , Hao Fei , Mong-Li Lee , Wynne Hsu

We present a convolution-free approach to video classification built exclusively on self-attention over space and time. Our method, named "TimeSformer," adapts the standard Transformer architecture to video by enabling spatiotemporal…

Computer Vision and Pattern Recognition · Computer Science 2021-06-10 Gedas Bertasius , Heng Wang , Lorenzo Torresani

Recent progress in video diffusion models has spurred growing interest in camera-controlled novel-view video generation for dynamic scenes, aiming to provide creators with cinematic camera control capabilities in post-production. A key…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Min-Jung Kim , Jeongho Kim , Hoiyeong Jin , Junha Hyung , Jaegul Choo

Transformer-based models have achieved state-of-the-art performance in various computer vision tasks, including image and video analysis. However, Transformer's complex architecture and black-box nature pose challenges for explainability, a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-04 Zerui Wang , Yan Liu

To build Video Question Answering (VideoQA) systems capable of assisting humans in daily activities, seeking answers from long-form videos with diverse and complex events is a must. Existing multi-modal VQA models achieve promising…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Difei Gao , Luowei Zhou , Lei Ji , Linchao Zhu , Yi Yang , Mike Zheng Shou

Text-to-video diffusion models deliver impressive results but remain slow because of the sequential denoising of 3D latents. Existing approaches to speed up inference either require expensive model retraining or use heuristic-based step…

Computer Vision and Pattern Recognition · Computer Science 2026-02-19 Joel Mathew Cherian , Ashutosh Muralidhara Bharadwaj , Vima Gupta , Anand Padmanabha Iyer

We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components: 1.) a new video autoencoder with highly-compressed latent space ($64\times64\times4$…

Contemporary diffusion models built upon U-Net or Diffusion Transformer (DiT) architectures have revolutionized image generation through transformer-based attention mechanisms. The prevailing paradigm has commonly employed self-attention…

Computer Vision and Pattern Recognition · Computer Science 2025-05-01 ZiYi Dong , Chengxing Zhou , Weijian Deng , Pengxu Wei , Xiangyang Ji , Liang Lin

Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied…

Computer Vision and Pattern Recognition · Computer Science 2026-02-23 Linxi Xie , Lisong C. Sun , Ashley Neall , Tong Wu , Shengqu Cai , Gordon Wetzstein

Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically…

Computer Vision and Pattern Recognition · Computer Science 2025-11-17 Dor Shmilovich , Tony Wu , Aviad Dahan , Yuval Domb

Existing methods for human motion control in video generation typically rely on either 2D poses or explicit 3D parametric models (e.g., SMPL) as control signals. However, 2D poses rigidly bind motion to the driving viewpoint, precluding…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Zhixue Fang , Xu He , Songlin Tang , Haoxian Zhang , Qingfeng Li , Xiaoqiang Liu , Pengfei Wan , Kun Gai

In this paper, we present DreaMoving, a diffusion-based controllable video generation framework to produce high-quality customized human videos. Specifically, given target identity and posture sequences, DreaMoving can generate a video of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Mengyang Feng , Jinlin Liu , Kai Yu , Yuan Yao , Zheng Hui , Xiefan Guo , Xianhui Lin , Haolan Xue , Chen Shi , Xiaowen Li , Aojie Li , Xiaoyang Kang , Biwen Lei , Miaomiao Cui , Peiran Ren , Xuansong Xie

The recent wave of AI-generated content has witnessed the great development and success of Text-to-Image (T2I) technologies. By contrast, Text-to-Video (T2V) still falls short of expectations though attracting increasing interests. Existing…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Zhen Xing , Qi Dai , Han Hu , Zuxuan Wu , Yu-Gang Jiang

Predicting human gaze in video is fundamental to advancing scene understanding and multimodal interaction. While traditional saliency maps provide spatial probability distributions and scanpaths offer ordered fixations, both abstractions…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Jenna Kang , Colin Groth , Tong Wu , Finley Torrens , Patsorn Sangkloy , Gordon Wetzstein , Qi Sun