← Search

Sharon X. Huang

7 accepted papers

2025

RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data

NeurIPS 2025poster

In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deform…

Cited by 0SourceScholar
2025

Towards In-the-wild 3D Plane Reconstruction from a Single Image

CVPR 2025highlight

3D plane reconstruction from a single image is a crucial yet challenging topic in 3D computer vision. Previous state-of-the-art (SOTA) methods have focused on training their system on a single dataset from either indoor or outdoor domain, limiting their generalizability across diverse testing data.…

2024

MonoPlane: Exploiting Monocular Geometric Cues for Generalizable 3D Plane Reconstruction

IROS 2024poster

This paper presents a generalizable 3D plane detection and reconstruction framework named MonoPlane. Unlike previous robust estimator-based works (which require multiple images or RGB-D input) and learning-based works (which suffer from domain shift), MonoPlane combines the best of two worlds and es…

Cited by 1SourcecodeScholar
2024

TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models

CVPR 2024poster

Text-conditioned image-to-video generation (TI2V) aims to synthesize a realistic video starting from a given image (e.g. a woman's photo) and a text description (e.g. "a woman is drinking water."). Existing TI2V frameworks often require costly training on video-text datasets and specific model desig…

2023

Conditional Image-to-Video Generation With Latent Flow Diffusion Models

CVPR 2023poster

Conditional image-to-video (cI2V) generation aims to synthesize a new plausible video starting from an image (e.g., a person's face) and a condition (e.g., an action class label like smile). The key challenge of the cI2V task lies in the simultaneous generation of realistic spatial appearance and te…

2022

Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop

ICLR 2022poster

This paper investigates unsupervised learning of Full-Waveform Inversion (FWI), which has been widely used in geophysics to estimate subsurface velocity maps from seismic data. This problem is mathematically formulated by a second order partial differential equation (PDE), but is hard to solve. More…

Cited by 60SourcePDFScholar