Related papers: Harnessing Meta-Learning for Improving Full-Frame …
In this work, we focus on the challenge of temporally consistent human-centric dense prediction across video sequences. Existing models achieve strong per-frame accuracy but often flicker under motion, occlusion, and lighting changes, and…
Multimodal large language models (MLLMs) are typically trained in multiple stages, with video-based supervised fine-tuning (Video-SFT) serving as a key step for improving visual understanding. Yet its effect on the fine-grained evolution of…
Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams. In practice, calibration is a laborious procedure requiring specialized data…
Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…
Video depth estimation aims to infer temporally consistent depth. One approach is to finetune a single-image model on each video with geometry constraints, which proves inefficient and lacks robustness. An alternative is learning to enforce…
We address the task of unsupervised retargeting of human actions from one video to another. We consider the challenging setting where only a few frames of the target is available. The core of our approach is a conditional generative model…
We propose a novel supervised learning technique for summarizing videos by automatically selecting keyframes or key subshots. Casting the problem as a structured prediction problem on sequential data, our main idea is to use Long Short-Term…
A problem deeply investigated by multimedia forensics researchers is the one of detecting which device has been used to capture a video. This enables to trace down the owner of a video sequence, which proves extremely helpful to solve…
Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework named 3DDFA-V2 which makes a balance among speed,…
Novel view synthesis is a long-standing problem in machine learning and computer vision. Significant progress has recently been made in developing neural scene representations and rendering techniques that synthesize photorealistic images…
While flow matching is elegant, its reliance on single-sample conditional velocities leads to high-variance training targets that destabilize optimization and slow convergence. By explicitly characterizing this variance, we identify 1) a…
In this paper, we consider a task of stopping the video stream recognition process of a text field, in which each frame is recognized independently and the individual results are combined together. The video stream recognition stopping…
In recent years, video semantic segmentation has made great progress with advanced deep neural networks. However, there still exist two main challenges \ie, information inconsistency and computation cost. To deal with the two difficulties,…
Predicting future frames of a video sequence has been a problem of high interest in the field of Computer Vision as it caters to a multitude of applications. The ability to predict, anticipate and reason about future events is the essence…
We propose a method for generating a temporally remapped video that matches the desired target duration while maximally preserving natural video dynamics. Our approach trains a neural network through self-supervision to recognize and…
As a widely studied task, video restoration aims to enhance the quality of the videos with multiple potential degradations, such as noises, blurs and compression artifacts. Among video restorations, compressed video quality enhancement and…
Relying on deep supervised or self-supervised learning, previous methods for depth completion from paired single image and sparse depth data have achieved impressive performance in recent years. However, facing a new environment where the…
In this paper, we introduce a new problem of manipulating a given video by inserting other videos into it. Our main task is, given an object video and a scene video, to insert the object video at a user-specified location in the scene video…
Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video relighting still lags, primarily due to the excessive…
Video summarization methods are usually classified into shot-level or frame-level methods, which are individually used in a general way. This paper investigates the underlying complementarity between the frame-level and shot-level methods,…