Related papers: Robust Dancer: Long-term 3D Dance Synthesis Using …
In the realm of motion generation, the creation of long-duration, high-quality motion sequences remains a significant challenge. This paper presents our groundbreaking work on "Infinite Motion", a novel approach that leverages long text to…
Annotated datasets are critical for training neural networks for object detection, yet their manual creation is time- and labour-intensive, subjective to human error, and often limited in diversity. This challenge is particularly pronounced…
We propose a novel learning-based approach for robust 3D shape matching. Our method builds upon deep functional maps and can be trained in a fully unsupervised manner. Previous deep functional map methods mainly focus on predicting…
High-quality 4D reconstruction of human performance with complex interactions to various objects is essential in real-world scenarios, which enables numerous immersive VR/AR applications. However, recent advances still fail to provide…
We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes - over 50 times larger than the prior real dataset DL3DV -…
Synthesizing dynamic appearances of humans in motion plays a central role in applications such as AR/VR and video editing. While many recent methods have been proposed to tackle this problem, handling loose garments with complex textures…
Group dance generation from music has broad applications in film, gaming, and animation production. However, it requires synchronizing multiple dancers while maintaining spatial coordination. As the number of dancers and sequence length…
Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models…
Ultrasound (US) is widely used for its advantages of real-time imaging, radiation-free and portability. In clinical practice, analysis and diagnosis often rely on US sequences rather than a single image to obtain dynamic anatomical…
Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based…
Grasp synthesis is one of the challenging tasks for any robot object manipulation task. In this paper, we present a new deep learning-based grasp synthesis approach for 3D objects. In particular, we propose an end-to-end 3D Convolutional…
Objective: Reconstructing freehand ultrasound in 3D without any external tracker has been a long-standing challenge in ultrasound-assisted procedures. We aim to define new ways of parameterising long-term dependencies, and evaluate the…
The emergence of neural networks has revolutionized the field of motion synthesis. Yet, learning to unconditionally synthesize motions from a given distribution remains challenging, especially when the motions are highly diverse. In this…
We study, from an empirical standpoint, the efficacy of synthetic data in real-world scenarios. Leveraging synthetic data for training perception models has become a key strategy embraced by the community due to its efficiency, scalability,…
Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to…
Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…
Large Reconstruction Models (LRMs) have recently become a popular method for creating 3D foundational models. Training 3D reconstruction models with 2D visual data traditionally requires prior knowledge of camera poses for the training…
LongSplat addresses critical challenges in novel view synthesis (NVS) from casually captured long videos characterized by irregular camera motion, unknown camera poses, and expansive scenes. Current methods often suffer from pose drift,…
With the rise of online dance-video platforms and rapid advances in AI-generated content (AIGC), music-driven dance generation has emerged as a compelling research direction. Despite substantial progress in related domains such as…
Deep learning models define the state-of-the-art in Automatic Drum Transcription (ADT), yet their performance is contingent upon large-scale, paired audio-MIDI datasets, which are scarce. Existing workarounds that use synthetic data often…