Alexander Schwing

About

Alexander Schwing is an Associate Professor in the Electrical and Computer Engineering department at the University of Illinois Urbana-Champaign. His research interests include machine learning and computer vision, with a focus on artificial intelligence. He has taught courses such as Machine Learning and Pattern Recognition, and his work involves developing advanced microscopy techniques to improve in vitro fertilization (IVF) processes, as well as exploring tactics in computer vision aimed at advancing AI development and democratizing new solutions. Schwing has received recognition for his research, and he collaborates on interdisciplinary projects, including joint research initiatives with colleagues from the Hebrew University of Jerusalem to accelerate economic development through innovative technologies.

Research topics

• Artificial Intelligence
• Computer Science
• Computer vision
• Geography
• Machine Learning
• Multimedia
• Engineering
• Pure mathematics
• Programming language
• Mathematics

Selected publications

• Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2020 · 217 citations

  Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2) detectors tend to focus on discriminative parts rather than entire objects; (3) without ground truth, object proposals have to be redundant for high recalls, causing significant memory consumption. Addressing these challenges is difficult, as it often requires t…

  DOI

• SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation

  2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · 2023 · 173 citations

  In this work, we present a novel framework built to sim-plify 3D asset generation for amateur users. To enable interactive generation, our method supports a variety of input modalities that can be easily provided by a human, in-cluding images, text, partially observed shapes and combinations of these, further allowing to adjust the strength of each input. At the core of our approach is an encoder-decoder, compressing 3D shapes into a compact latent representation, upon which a diffusion model is…

  DOI

• GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh

  2024-06-16 · 36 citations

  article

  We introduce GoMAvatar, a novel approach for real-time, memory-efficient, high-quality animatable human modeling. GoMAvatar takes as input a single monocular video to create a digital avatar capable of re-articulation in new poses and real-time rendering from novel view-points, while seamlessly integrating with rasterization-based graphics pipelines. Central to our method is the Gaussians-on-Mesh (GoM) representation, a hybrid 3D model combining rendering quality and speed of Gaussian splatting…

  PublisherDOI

• MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

  2025-06-10 · 13 citations

  article

  We propose to synthesize high-quality and synchronized audio, given video and optional text conditions, using a novel multimodal joint training framework (MMAudio). In contrast to single-modality training conditioned on (limited) video data only, MMAudio is jointly trained with larger-scale, readily available text-audio data to learn to generate semantically aligned high-quality audio samples. Additionally, we improve audio-visual synchrony with a conditional synchronization module that aligns v…

  PublisherDOI

• MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds

  2025-06-10 · 11 citations

  article

  Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When dealing with more than two views, a combinatorial number of error prone pairwise reconstructions are usually followed by an expensive global optimization, which often fails to rectify the pairwise reconstruction errors. To handle more views, reduce errors, and impr…

  PublisherDOI

Frequent coauthors

• Raquel Urtasun

  31 shared

• Unnat Jain

  Carnegie Mellon University

  30 shared

• Raymond A. Yeh

  30 shared

• Svetlana Lazebnik

  24 shared

• Zhongzheng Ren

  24 shared

• Tamir Hazan

  22 shared

• Yuan-Ting Hu

  Heilongjiang Electric Power Workers University

  19 shared

• Colin Graber

  18 shared

Labs

• Siebel School of Computing and Data SciencePI

Education

• Ph.D., Computer Science

  University of Illinois at Urbana-Champaign

  2005

• M.S., Computer Science

  University of Illinois at Urbana-Champaign

  2001

• B.S., Computer Science

  University of Illinois at Urbana-Champaign

  1999

Awards & honors

• NIH awards Illinois $2.5M to improve IVF with advanced micro…

Similar researchers at University of Illinois Urbana-Champaign

• Jiawei Hanh-146
• Kaiyu Guanh-86
• ChengXiang Zhaih-83