725 results about "Video editing" patented technology

The invention provides a method for adapting a text-to-image (T2I) diffusion model for video editing by using spectral decomposition to achieve controlled spectral shifts in the model's weights. This adaptation involves maintaining constant singular vectors while selectively adjusting singular values in response to a text prompt. A spectral shift regularizer constrains adjustments, particularly limiting changes to larger singular values to ensure minimal deviation from the original model's structure. This approach allows efficient, prompt-driven video editing by modifying specific elements according to the prompt while preserving the original video context. By focusing on selective spectral adjustments, the method reduces adaptation time and computational demands, making it suitable for real-time and resource-sensitive applications, such as dynamic video editing for streaming services.

The invention discloses a video editing method and related equipment, and the method comprises the steps: receiving an editing intention of a user, carrying out the semantic analysis of an intention analysis model, and generating an editing copywriting, a style and a structured instruction; the edited copywriting is split according to the edited copywriting; performing cross-modal analysis on video materials by using a video understanding model trained based on an open-source multi-modal model, and accurately positioning sub-lens segments; secondly, editing the sub-lens segments through an editing model to generate a preliminary sheet, performing quantitative scoring through a video scoring model, and obtaining a scoring result according to a multi-dimensional index; and finally, the result is fed back to the editing model, and iterative adjustment is carried out until a final slice is produced. According to the method, the editing efficiency is improved, the manual operation time is shortened, the material adaptability is enhanced, the personalized requirement is met, the editing effect consistency is improved, the video content understanding is deepened, the editing effect is optimized, the technical threshold is reduced, the existing technical problems are solved comprehensively, and an efficient, intelligent and personalized editing scheme is provided.

The present invention relates to a computer-implemented method and system for generating a video editing project using artificial intelligence (AI) and machine learning (ML) techniques. The method includes processing a collection of video clips to generate text-based metadata, receiving selection criteria to identify relevant video clips, and generating a natural language prompt based on the selection criteria. The prompt, comprising instructions and context, is provided to a large language model (LLM), which processes the input and outputs data for constructing a video project data model. The project data model includes timing data for salient snippets within the selected video clips. A dynamic and interactive web-based user interface is rendered to visually represent the project data model, offering a timeline view and editing tools for refining the video project. This system streamlines the video editing process by integrating AI-driven content analysis with user-directed editing, resulting in a tailored video project that aligns with user-defined thematic elements.

The invention discloses a short video intelligent editing method and system based on multi-modal analysis, and relates to the technical field of video editing. The method is used for improving editing efficiency and visual experience and comprises the following steps: extracting lip motion features of a character, visual saliency features of a commodity and a voice emotion intensity value from a target short video stream to form multi-modal time sequence data; afterwards, the voice stream is recorded, a product keyword timestamp is extracted, the alignment degree is calculated through dynamic time warping in combination with a visual saliency peak value, and a preliminary editing point set is generated through weighted evaluation in combination with an emotional intensity value; constructing an editing decision optimization model based on deep reinforcement learning, taking the multi-modal features as state input, adjusting the retention probability of editing points through a joint reward function, and selecting an optimal transition mode; and the lip movement and voice synchronization error before and after the editing point and the emotional and visual continuity of the transition section are analyzed, the discontinuous region is smoothed, and the edited finished product is output, so that precise short video intelligent editing is realized.

The invention relates to an automatic video editing method based on semantic analysis, and belongs to the technical field of video editing. The method comprises the following steps: extracting anchor point information of text content in a streaming media file based on a knowledge graph, establishing a support relationship, and determining a main anchor point, a sub anchor point and a argument anchor point by combining the support relationship and the anchor point information; constructing a dynamic trigger mechanism, setting a verification direction of the dynamic trigger mechanism, determining a semantic extension direction of the anchor point information according to the verification direction, and verifying whether a precondition chain supporting the anchor point information exists or not; and setting a credibility scoring strategy, determining the credibility of the anchor point information according to the logic complexity, the language confidence and the text consistency, forming a sequence set of the anchor point information, and splicing to form a logically coherent video editing text result. According to the method, automatic and intelligent editing of the video is realized based on semantic analysis, and the editing efficiency and quality are remarkably improved.

The invention discloses a video portrait consistency editing method based on optical flow guidance and text driving, and the method comprises the steps: firstly, employing a face key point extraction method and a depth estimation method to extract a face key point and a depth map of each frame of an input video, and guaranteeing the consistency of the facial expression of an edited portrait and a source image; a diffusion control network is used to edit and generate the face depth map, the key points and the user input text description as conditions, and the consistency of multi-view editing is realized through the potential code alignment of an attention mechanism and the guidance of optical flow change; thirdly, constructing a diffusion model with consistent time by utilizing the inter-frame optical flow change and the depth map change; through the above steps, the problems of multi-view and time consistency in video editing are solved, and high-quality video portrait editing is realized.

The present technology provides for AI-assisted video editing tools that implement a novel method of processing video which includes transcribing segments of a video and labeling the segments based on the contents of the segments. A smart edit can be generated based on the labelled segments. The smart edit can serve as a rough cut for a user to make further edits.

The invention discloses a short video editing synthesis method based on fuzzy logic. The method comprises the following steps: S1, carrying out digital video preprocessing on an input original short video; s2, forming a short video feature data set; s3, generating a fuzzy logic decision result; s4, performing multi-target and multi-parameter optimization on the fuzzy logic decision result by adopting a random score programming method to form an optimized editing parameter set; s5, generating a preliminarily synthesized short video; s6, generating a video quality evaluation result; and S7, carrying out iterative optimization on the preliminarily synthesized short video according to a video quality evaluation result, adjusting the editing parameters and re-executing the editing synthesis step until the video quality evaluation result meets a preset standard, and generating a final edited finished product. According to the method, the editing scheme can achieve the best balance in the aspects of visual rhythm, information integrity and emotion expression consistency.

The invention provides an intelligent self-adaptive video editing method and system based on deep learning, and relates to the technical field of video processing.The method comprises the steps that firstly, a semantic mapping relation between a to-be-edited video material and a preset editing requirement is established, and an editing requirement mapping result is generated, the preset editing demand comprises a content style and a rhythm control demand, and then semantic feature association processing is carried out based on the mapping result to obtain a semantic association feature set comprising lens unit content semantic features and rhythm association features; then calling a pre-trained editing decision model (including a semantic matching module and a rhythm adjusting module) to carry out editing strategy matching on the set, generating a preliminary editing strategy set, generating an initial video editing scheme according to the preliminary editing strategy set, carrying out parameter adjustment on the initial scheme according to a strategy optimization suggestion output by the model, and carrying out video editing on the initial scheme; and a final video editing scheme is obtained, and intelligent self-adaptive editing of the video is realized.

The invention discloses a video editing and artistic creation system based on AI intelligence, which relates to the technical field of video editing and comprises a data acquisition module, a feature analysis module, a feature library construction module, a rule matching module and a split mirror generation module, the data acquisition module is used for acquiring traditional opera stage video data and corresponding audience feedback audio waveform data, and the feature analysis module is used for extracting spatial-temporal feature vectors of stylized actions from the traditional opera stage video data. The feature library construction module is used for constructing an action feature library containing action type codes and music beat deviation level codes according to the spatio-temporal feature vectors; the method has the beneficial effects that dynamic association analysis is performed by constructing the action feature library and combining audience feedback audio data, the short video sequence conforming to the art rule is automatically generated, and the method has the advantage of improving the Chinese opera performance video editing efficiency and the art expressive force.

A disclosed computer-implemented method may include presenting, within a video creation interface, a list of video styles, each video style within the list of video styles representative of a trained model, the trained model trained to apply different aesthetic attributes to video content in accordance with a different video style. The method may also include receiving, via user input to the video creation interface, a selection of a particular video style from the list of video styles and, in response to receiving the selection, applying, to video content received via the video creation interface, a video editing technique corresponding to the particular video style. Various other methods, systems, and devices are also disclosed.

The invention relates to the technical field of video analysis, in particular to a video editing method based on grid layout alternate diffusion and multi-attention control, and the method comprises the steps: segmenting an original video frame sequence into a plurality of grids, each grid comprising a plurality of pixel space video frames which are continuously arranged, and forming grid data; mapping the gridding data to a low-dimensional submerged space through an encoder, and generating initial submerged space feature data; the initial submerged space feature data are edited, the editing process comprises a diffusion process and a sampling process, the diffusion process is based on a pre-trained stable diffusion model, and a time attention module is embedded in the diffusion process; in the sampling process, executing an odd-even time step alternate replacement strategy on the grid layout to promote cross-grid global consistency, and dynamically fusing attention maps of a reconstruction branch and an editing branch according to a timestamp threshold to generate de-noised data; and decoding, splitting and recombining the de-noised data through a decoder to generate an edited continuous video frame sequence.

The invention relates to the technical field of editing and special effect generation, in particular to a digital media content intelligent editing and special effect generation system based on artificial intelligence. Comprising a content understanding analysis module, an editing decision module, a special effect generation preview module, an audio processing module, a dynamic transition special effect module, a subtitle generation editing module, a virtual interaction module and a content distribution optimization module. The content understanding analysis module is used for video content identification and sentiment analysis; and the editing decision module is used for recommending an editing point and providing a dynamic editing strategy. The video content can be automatically analyzed, the editing point and the special effect adding position can be identified, the editing and special effect generation efficiency is greatly improved, the editing strategy and the special effect type can be dynamically adjusted according to the video content and the sentiment analysis result, the editing and the special effect can better meet the user requirement and the video content, and the user experience is improved. Abundant editing and special effect options are provided, and the editing and special effect generation process is simplified.

The invention relates to an intelligent video editing method fusing human face features and human voice features, which comprises the steps of input preprocessing, multi-modal analysis, fusion scoring and automatic editing, and adopts a multi-modal mode for analysis, so that the recall rate of key segments is improved, and the efficiency of editing is improved. A personalized editing strategy is supported, facial expression changes and voice emotion peak values are aligned through dynamic time warping, a CLIP-like structure is used for training a bimodal encoder, the human face and the voice are mapped to a unified vector space, the association weight of the human face and the voice is automatically learned, and the intelligent degree of editing is improved.

A processor-implemented method performed for text-based video editing includes receiving a video input and a text prompt. The video input includes a sequence of video frames. Features of the video input are extracted to generate a latent representation of the video input. Noise is injected to the latent representation of the video input to generate a noise injected latent. The noise is conditioned on the video input. An artificial neural network (ANN) model processes the noise injected latent based on the text prompt to adapt the video input according to the text prompt.

A computer-implemented method includes determination of n noised codes corresponding to n video frames of an original video. A text code corresponding to a description text guiding video editing is determined. Denoising processing, using n Unet models obtained by using the text code and copying a Unet model, is performed on the n noised codes, where a pre-trained text-to-image model includes the Unet model, which includes a self-attention layer connected after a target network layer, and where the denoising processing includes performing, in a self-attention layer of any ith Unet model, attention calculation based on an output of a target network layer of the ith Unet model and an output of a target network layer in a predetermined target Unet model. Decoding processing is separately performed on the n denoised codes by an image decoder to obtain n target images to form an edited target video.

The invention discloses a video editing method and device, electronic equipment and a nonvolatile storage medium. The method comprises the following steps: acquiring an audio data stream of a target video, and segmenting the audio data stream into a plurality of audio clips; determining a classification result corresponding to the audio clip, and determining a time period corresponding to the audio clip as a candidate ball hitting time period when the classification result is that the audio clip contains the ball hitting sound; acquiring a video frame corresponding to the candidate ball hitting time period in the target video, and judging that the candidate ball hitting time period is a real ball hitting time period under the condition that the visual feature of the video frame is matched with a preset ball hitting rule; and determining an editing time point according to the real ball hitting time period, and editing the target video according to the editing time point to obtain a ball hitting round video clip. The technical problem that the accuracy of ball hitting detection segment detection is low due to the fact that ball hitting detection is conducted only through sound and is easily interfered by environmental noise in the prior art is solved.

The present invention provides a multi-modal portrait video editing method, which can be applied to the technical field of video editing. The method comprises: given a portrait video, preprocessing same to obtain camera parameters, a human identity coefficient, a human expression coefficient, a human pose coefficient, a human semantic segmentation map, and a two-dimensional portrait mask; on the basis of a neural Gaussian texture mechanism, embedding a learnable three-dimensional Gaussian feature into a parameterized human geometric surface, using a neural renderer to convert a three-dimensional Gaussian splatting feature map into an image, and optimizing the reconstruction of a three-dimensional portrait on the basis of RGB and segmentation map information of the video; and using an iterative dataset update technique to distill knowledge of a multi-modal two-dimensional image generation model into three-dimensional portrait editing, and using expression similarity guidance and a face-aware portrait editing model to improve editing quality. The method elevates a two-dimensional editing task to three-dimensional space, and ensures good three-dimensional consistency and temporal consistency. By means of the knowledge of the multi-modal generation model, high-quality portrait video editing functions can be achieved.

The embodiment of the invention provides a video editing method and device, a storage medium and a program product. In the embodiment of the invention, a first video template used for describing a rendering rule and a hierarchical relationship of a group of video materials is downloaded to local terminal equipment, and video editing software is imported; opening the first video template in an editing area of the video editing software, and displaying a first video generated based on the first video template in a preview area of the video editing software; further, determining a modified rendering rule in any target materialized template and / or a modified position relationship between any two target materialized templates by responding to a modification operation on the first video template, and editing the first video according to the modified rendering rule and / or the modified position relationship, according to the video editing method and device, the video production efficiency and diversity can be improved, the dependence on professional equipment and manual intervention is reduced, and the diversified video requirements of high efficiency and low cost are met.

The present disclosure provides an artificial intelligence device comprising: a communication unit for communicating with the outside; an input / output unit for receiving a signal from a user and outputting a process result; and a control unit. The control unit: outputs a conversational interface for conversation with the user when the user accesses a video editing system; receives, through the conversational interface, a video uploaded by the user; outputs, through the conversational interface, a conversation for editing the video; extracts, from the conversation, a keyword for editing the video; and edits the video on the basis of the extracted keyword.

A video editing system leverages a generative artificial intelligence (AI) model to identify songs to overlay on a video. The video editing system extracts a set of key frames from the video and prompts the generative AI model to generate a video narrative for the video. A video narrative is a text description of the plot, theme, feel, or other characteristics of the video. The video editing system uses the video narrative to prompt the generative AI model again to generate a set of descriptor tags for the video based on the video narrative. Descriptor tags are strings that represent themes, features, or characteristics of the song. The video editing system uses an audio tagging system to score a set of songs based on the set of descriptor tags and presents a selected subset of the set of songs based on the scores of the songs.

The invention discloses a multi-mode-based short episode video editing method, system and device and a medium, and the method comprises the steps: carrying out the preprocessing of an original short episode video, and obtaining a second short episode video, subtitles and a subtitle timestamp; analyzing the subtitles, and generating a short episode abstract according to an analysis result of the subtitles; according to the short episode abstract and the highlight editing prompt, performing plot analysis and editing on the second short episode video, and performing editing to form a first video set; scoring videos in the first video set according to a multi-dimensional scoring rule, and screening out M highlight video clips before scoring; and adjusting the timestamps of the M highlight video clips according to the subtitle timestamps, and outputting the adjusted M highlight video clips. According to the method and the device, the full link from short video input to short play mixed video output is constructed, a user only needs to input the to-be-edited short play video, the mixed video can be automatically generated, and the video editing efficiency is improved while the video editing threshold is reduced.

The invention discloses a video processing method and device, a medium and a program product, and relates to the technical field of computers. According to the method, the diffusion model can sense the adjacent frame optical flow motion information in the real initial video, and the adjacent frame optical flow motion information corresponds to the time sequence motion related information in the video, so that the diffusion model edits the initial video into a new video according to the editing information and the adjacent frame optical flow motion information; according to the scheme, the diffusion model has the editing capability of a real video, the video editing precision is improved by means of time sequence motion related information in the video, model parameters do not need to be adjusted, calculation resources and model reasoning time are saved, and therefore the video editing efficiency is improved.

The invention discloses a video editing method and device, electronic equipment and a storage medium. The method comprises the following steps: segmenting a to-be-edited video to obtain a plurality of video clips; understanding text generation and subtitle generation are carried out on each video clip, and a clip understanding text and a clip subtitle of each video clip are obtained; determining a target description text based on fragment understanding texts and / or fragment subtitles corresponding to a plurality of target video fragments selected from the plurality of video fragments; and performing video synthesis based on the plurality of target video clips and the target description text to obtain a target video corresponding to the to-be-edited video. According to the method provided by the invention, the video editing efficiency is relatively high, and the video editing cost is relatively low.

Embodiments of the present invention provide systems, methods, and computer storage media for a visual and text search interface used to navigate a video transcript. In an example embodiment, a freeform text query triggers a visual search for frames of a loaded video that match the freeform text query (e.g., frame embeddings that match a corresponding embedding of the freeform query), and triggers a text search for matching words from a corresponding transcript or from tags of detected features from the loaded video. Visual search results are displayed (e.g., in a row of tiles that can be scrolled to the left and right), and textual search results are displayed (e.g., in a row of tiles that can be scrolled up and down). Selecting (e.g., clicking or tapping on) a search result tile navigates a transcript interface to a corresponding portion of the transcript.

The invention provides an online video instance segmentation method and system based on mask propagation, and the method comprises the following steps: S1, achieving the cross-frame propagation of a target mask through a mask propagation model, obtaining a prediction mask of a current frame, and achieving the correlation of a target through the calculation of the intersection-union ratio of the prediction mask; and S2, performing back propagation on the target by using the mask propagation model so as to complement the missed target mask and enhance the continuity of the track. Objects between different frames are associated on the basis of a mask propagation mechanism and in combination with the intersection-to-union ratio of masks, and meanwhile, in order to relieve the scene that a segmentation model fails to segment shielded objects, non-significant objects and the like, a reverse mask propagation technology is provided to complement the failed frames. The method aims at performing fine segmentation and continuous tracking on various scenes such as intelligent monitoring, automatic driving, augmented reality and video editing on the target in the video, and has wide research and application prospects.

The invention provides a video editing model based on text and image common editing and a construction method thereof. The video editing model introduces an optical flow guide mask fusion module and a multi-modal feature recognition and segmentation module into a denoising diffusion implicit model; the method comprises the following steps: inputting an original video into a denoising diffusion implicit model to carry out forward diffusion noise addition to obtain a multi-frame submerged space generation frame, and inputting the multi-frame submerged space generation frame into an optical flow guide mask fusion module to carry out inter-frame feature alignment to obtain a time consistency submerged space generation frame; a text prompt, an image prompt and an original video are input into a multi-modal feature recognition and segmentation module to be aligned and positioned to obtain a condition vector, the condition vector and a time consistency submerged space generation frame are subjected to iterative denoising to generate a target editing video, and dynamic feature modulation is performed in each denoising process; a video editing model based on text and image common editing efficiently edits a video under combined guidance of text and image prompts.

The invention relates to an editing processing method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: displaying a video editing interface, the video editing interface comprises a material region and a timeline region, and when a material package option displayed in the material region is in a selected state, the timeline region is a timeline region; at least one material package identifier is also displayed in the material area, each material package identifier is used for indicating one material package resource, and each material package resource is a material package in a composite fragment form generated by a plurality of materials; in response to a target triggering operation on a target material package identifier in the plurality of material package identifiers, converting a target material package resource indicated by the target material package identifier into a target material package combination, and displaying the target material package combination in a timeline area; wherein the target material package combination is a combination of a plurality of target materials corresponding to the target material package identifier.

Methods and systems are described to create transitions between a set of video clips according to a style choice and to pick a next video clip in a sequence of ordered clips. In one embodiment, a device receives a plurality of video clips. In addition, the device may encode the plurality of video clips. The device further may compute a set of predicted transition embeddings using the target style and the encoded plurality of video clips. Furthermore, the device may determine a set of transitions for the plurality of video clips using the set of predicted transition embeddings in a recurrent manner.

The invention provides a diffusion model video local editing method and system based on mask guidance. The method comprises the following steps: encoding a video sequence of a target video to obtain a first video frame submerged space feature; performing coarse-grained mask labeling on a target editing area in the target video to obtain mask information; determining a space attention weight according to the first video frame potential space feature; determining a second video frame potential space feature according to the first video frame potential space feature, the mask information and the space attention weight; determining a time attention weight according to the second video frame potential space feature; determining a third video frame potential space feature according to the mask information, the second video frame potential space feature and the time attention weight; and decoding the hidden space feature of the third video frame to generate an edited video. According to the method, frame-by-frame accurate masking is not needed, the time-space consistency of local editing of the video can be effectively enhanced, an unedited area is kept unchanged, and a high-quality and stable video editing effect is achieved.