Search Results

Neural shape representation, such as neural signed distance field (NSDF), becomes more and more popular in shape modeling as its ability to deal with complex topology and arbitrary resolution. Due to the implicit manner to use features for shape ...

Single-view 3D hair reconstruction is challenging, due to the wide range of shape variations among diverse hairstyles. Current state-of-the-art methods are specialized in recovering un-braided 3D hairs and often take braided styles as their failure cases, ...

MVImgNet is a large-scale dataset that contains multi-view images of ~220k real-world objects in 238 classes. As a counterpart of ImageNet, it introduces 3D visual signals via multi-view shooting, making a soft bridge between 2D and 3D vision. This paper ...

This work addresses the challenge of high-quality surface normal estimation from monocular colored inputs (i.e., images and videos), a field which has recently been revolutionized by repurposing diffusion priors. However, previous attempts still struggle ...

Neural implicit functions have brought impressive advances to the state-of-the-art of clothed human digitization from multiple or even single images. However, despite the progress, current arts still have difficulty generalizing to unseen images with ...

Text-to-3D generation has recently seen significant progress. To enhance its practicality in real-world applications, it is crucial to generate multiple independent objects with interactions, similar to layer-compositing in 2D image editing. ...

Point cloud registration is a fundamental problem for large-scale 3D scene scanning and reconstruction. With the help of deep learning, registration methods have evolved significantly, reaching a nearly-mature stage. As the introduction of Neural ...$\mathrm{}$

This paper studies visual representation learning with diffusion-generated synthetic images. We start by uncovering that diffusion models’ cross-attention layers inherently provide annotation-free attention masks aligned with corresponding text ...

While recent advances in 3D-aware Generative Adversarial Networks (GANs) have aided the development of near-frontal view human face synthesis, the challenge of comprehensively synthesizing a full 3D head viewable from all angles still persists. ...

Previous low-light image enhancement (LLIE) approaches, while employing frequency decomposition techniques to address the intertwined challenges of low frequency (e.g., illumination recovery) and high frequency (e.g., noise reduction), primarily ...

It is very challenging to accurately reconstruct sophisticated human geometry caused by various poses and garments from a single image. Recently, works based on pixel-aligned implicit function (PIFu) have made a big step and achieved state-of-the-...

A comparative study of two force perception skill learning approaches for robot‐assisted spinal surgery, the impedance model method and the imitation learning (IL) method, is presented. The impedance model method develops separate models for the ...

In this paper, we address a complex but practical scenario in Active Learning (AL) known as open-set AL, where the unlabeled data consists of both in-distribution (ID) and out-of-distribution (OOD) samples. Standard AL methods will fail in this scenario ...

Neural radiance fields (NeRF) have shown great success in novel view synthesis. However, recovering high-quality details from real-world scenes is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration ...

The past two years have witnessed a significant increase in interest concerning NeRF-based human body rendering. While this surge has propelled considerable advancements, it has also led to an influx of methods and datasets. This explosion complicates ...

The generalization capability of machine learning systems degenerates notably when the test distribution drifts from the training distribution. Recently, Domain Generalization (DG) has been gaining momentum in enabling machine learning models to ...

Neural Radiance Fields (NeRFs) have emerged as promising digital mediums of 3D objects and scenes, sparking a surge in research to extend the editing capabilities in this domain. The task of seamless editing and merging of multiple NeRFs, resembling the ...

Eyebrows play a critical role in facial expression and appearance. Although the 3D digitization of faces is well explored, less attention has been drawn to 3D eyebrow modeling. In this work, we propose EMS, the first learning-based framework for single-...

Semantic segmentation of point cloud usually relies on dense annotation that is exhausting and costly, so it attracts wide attention to investigate solutions for the weakly supervised scheme with only sparse points annotated. Existing works start ...

Display Omitted

• A consistency training framework for efficient learning from sparse semantic labels.
• Propose to probe and well exploit super-points to promote the pseudo-label quality.
• Extensive experiments validate the effectiveness and ...

Radiance fields have gradually become a main representation of media. Although its appearance editing has been studied, how to achieve view-consistent recoloring in an efficient manner is still under explored. We present RecolorNeRF, a novel user-...