Related papers: Pomo3D: 3D-Aware Portrait Accessorizing and More
This work targets to construct a robust human pose prior. However, it remains a persistent challenge due to biomechanical constraints and diverse human movements. Traditional priors like VAEs and NDFs often exhibit shortcomings in realism…
Face stylization refers to the transformation of a face into a specific portrait style. However, current methods require the use of example-based adaptation approaches to fine-tune pre-trained generative models so that they demand lots of…
Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync…
Face image manipulation via three-dimensional guidance has been widely applied in various interactive scenarios due to its semantically-meaningful understanding and user-friendly controllability. However, existing 3D-morphable-model-based…
Neural network-based visuomotor policies enable robots to perform manipulation tasks but remain susceptible to perceptual attacks. For example, conventional 2D adversarial patches are effective under fixed-camera setups, where appearance is…
Humans can resort to long-form inspection to build intuition on predicting the 3D configurations of unseen objects. The more we observe the object motion, the better we get at predicting its 3D state immediately. Existing systems either…
With the booming of virtual reality (VR) technology, there is a growing need for customized 3D avatars. However, traditional methods for 3D avatar modeling are either time-consuming or fail to retain similarity to the person being modeled.…
Advancing robotic manipulation of deformable objects can enable automation of repetitive tasks across multiple industries, from food processing to textiles and healthcare. Yet robots struggle with the high dimensionality of deformable…
With the recent advancements in single-image-based human mesh recovery, there is a growing interest in enhancing its performance in certain extreme scenarios, such as occlusion, while maintaining overall model accuracy. Although obtaining…
In this paper, we propose a novel framework, Combo, for harmonious co-speech holistic 3D human motion generation and efficient customizable adaption. In particular, we identify that one fundamental challenge as the…
Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video.…
Recently, extensive research on image customization (e.g., identity, subject, style, background, etc.) demonstrates strong customization capabilities in large-scale generative models. However, most approaches are designed for specific…
Our method studies the complex task of object-centric 3D understanding from a single RGB-D observation. As it is an ill-posed problem, existing methods suffer from low performance for both 3D shape and 6D pose and size estimation in complex…
6D pose estimation of rigid objects from RGB-D images is crucial for object grasping and manipulation in robotics. Although RGB channels and the depth (D) channel are often complementary, providing respectively the appearance and geometry…
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses. In this…
At the core of portrait photography is the search for ideal lighting and viewpoint. The process often requires advanced knowledge in photography and an elaborate studio setup. In this work, we propose Holo-Relighting, a volumetric…
Recent advancements in image customization exhibit a wide range of application prospects due to stronger customization capabilities. However, since we humans are more sensitive to faces, a significant challenge remains in preserving…
The appearance of a human in clothing is driven not only by the pose but also by its temporal context, i.e., motion. However, such context has been largely neglected by existing monocular human modeling methods whose neural networks often…
Deep generative models have been recently extended to synthesizing 3D digital humans. However, previous approaches treat clothed humans as a single chunk of geometry without considering the compositionality of clothing and accessories. As a…
3D pose estimation has recently gained substantial interests in computer vision domain. Existing 3D pose estimation methods have a strong reliance on large size well-annotated 3D pose datasets, and they suffer poor model generalization on…