Related papers: SMF: Template-free and Rig-free Animation Transfer…

We introduce Neural Riemannian Motion Fields (NRMF), a novel 3D generative human motion prior that enables robust, temporally consistent, and physically plausible 3D motion recovery. Unlike existing VAE or diffusion-based methods, our…

Transferring articulated motion from monocular videos to rigged 3D characters is challenging due to pose ambiguity in 2D observations and morphological differences between source and target. Existing approaches often follow a…

Recent advances in motion diffusion models have led to remarkable progress in diverse motion generation tasks, including text-to-motion synthesis. However, existing approaches represent motions as dense frame sequences, requiring the model…

We present a sparse coding-based framework for motion style decomposition and synthesis. Dynamic Time Warping is firstly used to synchronized input motions in the time domain as a pre-processing step. A sparse coding-based decomposition has…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Motion forecasting represents a critical challenge in autonomous driving systems, requiring accurate prediction of surrounding agents' future trajectories. While existing approaches predict future motion states with the extracted scene…

Typical deep neural video compression networks usually follow the hybrid approach of classical video coding that contains two separate modules: motion coding and residual coding. In addition, a symmetric auto-encoder is often used as a…

Pre-training video transformers generally requires a large amount of data, presenting significant challenges in terms of data collection costs and concerns related to privacy, licensing, and inherent biases. Synthesizing data is one of the…

Human animation aims to generate temporally coherent and visually consistent videos over long sequences, yet modeling long-range dependencies while preserving frame quality remains challenging. Inspired by the human ability to leverage past…

Unregistered surface meshes, especially raw 3D scans, present significant challenges for automatic computation of plausible deformations due to the lack of established point-wise correspondences and the presence of noise in the data. In…

Traditional single-modality sensing faces limitations in accuracy and capability, and its decoupled implementation with communication systems increases latency in bandwidth-constrained environments. Additionally, single-task-oriented…

Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner, but requires precise annotations. To reduce the annotation cost and maintain satisfactory performance, in…

Text-to-motion generation has recently garnered significant research interest, primarily focusing on generating human motion sequences in blank backgrounds. However, human motions commonly occur within diverse 3D scenes, which has prompted…

We present Motion Marionette, a zero-shot framework for rigid motion transfer from monocular source videos to single-view target images. Previous works typically employ geometric, generative, or simulation priors to guide the transfer…

The emergence of Neural Radiance Fields (NeRF) has greatly impacted 3D scene modeling and novel-view synthesis. As a kind of visual media for 3D scene representation, compression with high rate-distortion performance is an eternal target.…

Diffusion-based video motion customization facilitates the acquisition of human motion representations from a few video samples, while achieving arbitrary subjects transfer through precise textual conditioning. Existing approaches often…

Weakly Supervised Semantic Segmentation (WSSS) with image level labels aims to produce pixel level predictions without requiring dense annotations. While recent approaches have leveraged generative models to augment existing data, they…

In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…

Recent neural view synthesis methods have achieved impressive quality and realism, surpassing classical pipelines which rely on multi-view reconstruction. State-of-the-Art methods, such as NeRF, are designed to learn a single scene with a…

We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are limited by (a)…