← Search

Qixuan Zhang

7 accepted papers

2026

Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects

ICRA 2026poster

A deep understanding of kinematic structures is essential for robot motion and interaction with the environment. Such understanding is captured through articulated objects, which are essential for physical simulation, motion planning, and policy learning. However, creating these models, particularly…

2026

WildCap: Facial Albedo Capture in the Wild via Hybrid Inverse Rendering

CVPR 2026

Existing methods achieve high-quality facial albedo capture under controllable lighting, which increases capture cost and limits usability. We propose WildCap, a novel method for high-quality facial albedo capture from a smartphone video recorded in the wild. To disentangle high-quality albedo from

Cited by 0SourcecodeScholar
2024

Can Machine Unlearning Reduce Social Bias in Language Models?

EMNLP 2024industry

Mitigating bias in language models (LMs) has become a critical problem due to the widespread deployment of LMs in the industry and customer-facing applications. Numerous approaches revolve around data pre-processing and subsequent fine-tuning of language models, tasks that can be both time-consuming…

2024

Visual Prompting in LLMs for Enhancing Emotion Recognition

EMNLP 2024main

Vision Large Language Models (VLLMs) are transforming the intersection of computer vision and natural language processing; however, the potential of using visual prompts for emotion recognition in these models remains largely unexplored and untapped. Traditional methods in VLLMs struggle with spatia…

2023

Relightable Neural Human Assets From Multi-View Gradient Illuminations

CVPR 2023poster

Human modeling and relighting are two fundamental problems in computer vision and graphics, where high-quality datasets can largely facilitate related research. However, most existing human datasets only provide multi-view human images captured under the same illumination. Although valuable for mode…

2021

Neural Video Portrait Relighting in Real-Time via Consistency Modeling

ICCV 2021poster

Video portraits relighting is critical in user-facing human photography, especially for immersive VR/AR experience. Recent advances still fail to recover consistent relit result under dynamic illuminations from monocular RGB stream, suffering from the lack of video consistency supervision. In this p…

Cited by 47PDFcodeScholar
2018

PaintCopter: An Autonomous UAV for Spray Painting on Three-Dimensional Surfaces

RA-L 2018

This letter describes a system for autonomous spray painting using an unmanned aerial vehicle (UAV), suitable for industrial applications. The work is motivated by the potential for such a system to achieve accurate and fast painting results. The PaintCopter is a quadrotor that has been custom fitte

Cited by 55SourceScholar