Related papers: OnlyFlow: Optical Flow based Motion Conditioning f…
We introduce an approach for augmenting text-to-video generation models with customized motions, extending their capabilities beyond the motions depicted in the original training data. By leveraging a few video samples demonstrating…
One-shot imitation is the vision of robot programming from a single demonstration, rather than by tedious construction of computer code. We present a practical method for realizing one-shot imitation for manipulation tasks, exploiting…
This paper introduces a new method for inter-frame coding based on two complementary autoencoders: MOFNet and CodecNet. MOFNet aims at computing and conveying the Optical Flow and a pixel-wise coding Mode selection. The optical flow is used…
Learning to localize the sound source in videos without explicit annotations is a novel area of audio-visual research. Existing work in this area focuses on creating attention maps to capture the correlation between the two modalities to…
Text-to-video editing aims to edit the visual appearance of a source video conditional on textual prompts. A major challenge in this task is to ensure that all frames in the edited video are visually consistent. Most recent works apply…
Audio-Visual Foundation Models, which are pretrained to jointly generate sound and visual content, have recently shown an unprecedented ability to model multi-modal generation and editing, opening new opportunities for downstream tasks.…
We tackle the long video generation problem, i.e.~generating videos beyond the output length of video generation models. Due to the computation resource constraints, video generation models can only generate video clips that are relatively…
In this paper, we address the open research problem of surgical gesture recognition using motion cues from video data only. We adapt Optical flow ConvNets initially proposed by Simonyan et al.. While Simonyan uses both RGB frames and dense…
Image-to-3D generation faces inherent semantic ambiguity under occlusion, where partial observation alone is often insufficient to determine object category. In this work, we formalize text-driven amodal 3D generation, where text prompts…
Camera control, which achieves diverse visual effects by changing camera position and pose, has attracted widespread attention. However, existing methods face challenges such as complex interaction and limited control capabilities. To…
Real-time motion detection in non-stationary scenes is a difficult task due to dynamic background, changing foreground appearance and limited computational resource. These challenges degrade the performance of the existing methods in…
Generating geometrically consistent videos remains an open challenge: text-to-video diffusion models trained on web-scale data treat geometry only implicitly, leading to object deformation, texture drift, and non-rigid backgrounds under…
Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and rely primarily on textual instructions, limiting their…
Following the advancements in text-guided image generation technology exemplified by Stable Diffusion, video generation is gaining increased attention in the academic community. However, relying solely on text guidance for video generation…
Motions in a video primarily consist of camera motion, induced by camera movement, and object motion, resulting from object movement. Accurate control of both camera and object motion is essential for video generation. However, existing…
Human motion generation is a significant pursuit in generative computer vision with widespread applications in film-making, video games, AR/VR, and human-robot interaction. Current methods mainly utilize either diffusion-based generative…
Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions. In this…
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for…
Despite impressive advancements in diffusion-based video editing models in altering video attributes, there has been limited exploration into modifying motion information while preserving the original protagonist's appearance and…
Understanding and predicting object motion from egocentric video is fundamental to embodied perception and interaction. However, generating physically consistent 6DoF trajectories remains challenging due to occlusions, fast motion, and the…