相关论文: PanFlow: Decoupled Motion Control for Panoramic Vi…
Streaming video generation, as one fundamental component in interactive world models and neural game engines, aims to generate high-quality, low-latency, and temporally coherent long video streams. However, most existing work suffers from…
Audio-driven bimanual piano motion generation requires precise modeling of complex musical structures and dynamic cross-hand coordination. However, existing methods often rely on acoustic-only representations lacking symbolic priors, employ…
Video generation requires modeling a vast spatiotemporal space, which demands significant computational resources and data usage. To reduce the complexity, the prevailing approaches employ a cascaded architecture to avoid direct training…
Generating 360-degree panoramas from narrow field of view (NFoV) image is a promising computer vision task for Virtual Reality (VR) applications. Existing methods mostly assess the generated panoramas with InceptionNet or CLIP based…
Optical flow is the motion of a pixel between at least two consecutive video frames and can be estimated through an end-to-end trainable convolutional neural network. To this end, large training datasets are required to improve the accuracy…
Recent advances in generative modeling have led to promising results in robot motion planning, particularly through diffusion and flow matching (FM)-based models that capture complex, multimodal trajectory distributions. However, these…
Recent advancements in human video synthesis have enabled the generation of high-quality videos through the application of stable diffusion models. However, existing methods predominantly concentrate on animating solely the human element…
We address the problem of synthesizing new video frames in an existing video, either in-between existing frames (interpolation), or subsequent to them (extrapolation). This problem is challenging because video appearance and motion can be…
For visual estimation of optical flow, a crucial function for many vision tasks, unsupervised learning, using the supervision of view synthesis has emerged as a promising alternative to supervised methods, since ground-truth flow is not…
Generating realistic, context-aware two-person motion conditioned on diverse modalities remains a fundamental challenge for graphics, animation and embodied AI systems. Real-world applications such as VR/AR companions, social robotics and…
Reconstructing High Dynamic Range (HDR) video from image sequences captured with alternating exposures is challenging, especially in the presence of large camera or object motion. Existing methods typically align low dynamic range sequences…
Obtaining the ground truth labels from a video is challenging since the manual annotation of pixel-wise flow labels is prohibitively expensive and laborious. Besides, existing approaches try to adapt the trained model on synthetic datasets…
It is hard to estimate optical flow given a realworld video sequence with camera shake and other motion blur. In this paper, we first investigate the blur parameterization for video footage using near linear motion elements. we then combine…
We present Diffuse-CLoC, a guided diffusion framework for physics-based look-ahead control that enables intuitive, steerable, and physically realistic motion generation. While existing kinematics motion generation with diffusion models…
Deblurring can not only provide visually more pleasant pictures and make photography more convenient, but also can improve the performance of objection detection as well as tracking. However, removing dynamic scene blur from images is a…
This paper introduces a novel technique for smooth and efficient zooming and panning based on dynamical systems in hyperbolic space. Unlike the technique of van Wijk and Nuij, the animations produced by our technique are smooth at the…
Motion generation, the task of synthesizing realistic motion sequences from various conditioning inputs, has become a central problem in computer vision, computer graphics, and robotics, with applications ranging from animation and virtual…
Previous dominant methods for scene flow estimation focus mainly on input from two consecutive frames, neglecting valuable information in the temporal domain. While recent trends shift towards multi-frame reasoning, they suffer from rapidly…
Generating human motion with precise spatial control is a challenging problem. Existing approaches often require task-specific training or slow optimization, and enforcing hard constraints frequently disrupts motion naturalness. Building on…
We consider the problem of filling in missing spatio-temporal regions of a video. We provide a novel flow-based solution by introducing a generative model of images in relation to the scene (without missing regions) and mappings from the…