相关论文: From Frames to Sequences: Temporally Consistent Hu…
Inspired by the performance and scalability of autoregressive large language models (LLMs), transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a…
Visual effects (VFX) production often struggles with slow, resource-intensive mask generation. This paper presents an automated video segmentation pipeline that creates temporally consistent instance masks. It employs machine learning for:…
Temporally consistent dense video annotations are scarce and hard to collect. In contrast, image segmentation datasets (and pre-trained models) are ubiquitous, and easier to label for any novel task. In this paper, we introduce a method to…
Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and tracking all humans in a complex video, including pedestrians…
Data-driven modeling of human motions is ubiquitous in computer graphics and computer vision applications, such as synthesizing realistic motions or recognizing actions. Recent research has shown that such problems can be approached by…
Long-term video understanding requires interpreting complex temporal events and reasoning over procedural activities. While instructional video corpora, like HowTo100M, offer rich resources for model training, they present significant…
Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latency and high dynamic range, capture brightness changes asynchronously, offering a unique…
This paper addresses the challenges of estimating a continuous-time human motion field from a stream of events. Existing Human Mesh Recovery (HMR) methods rely predominantly on frame-based approaches, which are prone to aliasing and…
Distilling knowledge from human demonstrations is a promising way for robots to learn and act. Existing methods, which often rely on coarsely-aligned video pairs, are typically constrained to learning global or task-level features. As a…
In multi-view 3D human pose estimation, models typically rely on images captured simultaneously from different camera views to predict a pose at a specific moment. While providing accurate spatial information, this traditional approach…
Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly…
Video matting has traditionally been limited by the lack of high-quality ground-truth data. Most existing video matting datasets provide only human-annotated imperfect alpha and foreground annotations, which must be composited to background…
We present a new pose transfer method for synthesizing a human animation from a single image of a person controlled by a sequence of body poses. Existing pose transfer methods exhibit significant visual artifacts when applying to a novel…
Recent advances in diffusion models have significantly improved conditional video generation, particularly in the pose-guided human image animation task. Although existing methods are capable of generating high-fidelity and time-consistent…
Self-supervised learning of image representations by predicting future frames is a promising direction but still remains a challenge. This is because of the under-determined nature of frame prediction; multiple potential futures can arise…
We present THFM, a unified video foundation model for human-centric perception that jointly addresses dense tasks (depth, normals, segmentation, dense pose) and sparse tasks (2d/3d keypoint estimation) within a single architecture. THFM is…
Deep video models, for example, 3D CNNs or video transformers, have achieved promising performance on sparse video tasks, i.e., predicting one result per video. However, challenges arise when adapting existing deep video models to dense…
Large pre-trained video diffusion models excel in video frame interpolation but struggle to generate high fidelity frames due to reliance on intrinsic generative priors, limiting detail preservation from start and end frames. Existing…
Recent works on dynamic 3D neural field reconstruction assume the input from synchronized multi-view videos whose poses are known. The input constraints are often not satisfied in real-world setups, making the approach impractical. We show…
Recent diffusion-based human image animation techniques have demonstrated impressive success in synthesizing videos that faithfully follow a given reference identity and a sequence of desired movement poses. Despite this, there are still…