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