Yawar Siddiqui

prof_pic.jpg

yawarnihal[at]gmail[dot]com

Hi! I’m Yawar. I am a Research Scientist at Reality Labs, Meta in Munich. I did my PhD at the Visual Computing and Artificial Intelligence group of Prof. Matthias Niessner at the Technical University of Munich, Germany. My work focuses on 3D reconstruction, scene understanding and 3D generative models.

Before my PhD, I did a Masters in Informatics at TUM, Germany, and my Bachelors in Computer Science at Jamia Millia Islamia, New Delhi, India, graduating with high distinction and at the top of the class respectively.

In the past, I have worked with Adobe Systems in India as a software engineer. During my time at TUM, I’ve had the pleasure of interning with Thabo Beeler and Derek Bradley at Disney Research in Zurich, with Peter Konschieder at Meta Reality Labs also in Zurich, and with Andrea Vedaldi, David Novotny, Roman Shapovalov and Natalia Nevarova at GenAI, Meta in London.


Research

  1. Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
    arXiv preprint arXiv:2407.02445, 2024
  2. MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2024
  3. PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models
    arXiv preprint arXiv:2312.11417, 2023
  4. Text2Tex: Text-driven Texture Synthesis via Diffusion Models
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023
  5. Panoptic Lifting for 3D Scene Understanding with Neural Fields
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023
  6. DiffRF: Rendering-Guided 3D Radiance Field Diffusion
    Norman MüllerYawar SiddiquiLorenzo Porzi, Samuel Rota Bulò, Peter Kontschieder, and Matthias Nießner
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023
  7. Texturify: Generating textures on 3d shape surfaces
    In Computer Vision–ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part III, 2022
  8. Retrievalfuse: Neural 3d scene reconstruction with a database
    In Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021
  9. Spsg: Self-supervised photometric scene generation from rgb-d scans
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021
  10. Viewal: Active learning with viewpoint entropy for semantic segmentation
    Yawar SiddiquiJulien Valentin, and Matthias Nießner
    In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020
  11. Clustering with deep learning: Taxonomy and new methods
    Elie AljalboutVladimir GolkovYawar Siddiqui, Maximilian Strobel, and Daniel Cremers
    arXiv preprint arXiv:1801.07648, 2018

Invited Talks

  • [Google Munich, September 2024]   Creating Relightable 3D Assets in Less Than a Minute
  • [Autodesk AI, July 2024]   3D Content Creation using Reconstruction and Generation
  • [CVPR 3DMV Workshop, June 2024]   MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
  • [Apple, 3D Reconstruction Team, December 2023]   MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
  • [Talking Papers Podcast, July 2023]   Panoptic Lifting for 3D Scene Understanding with Neural Fields
  • [CVPR Workshop for Compositional 3D Vision, June 2023]   Panoptic Lifting for 3D Scene Understanding with Neural Fields
  • [CVPR Workshop for Scene Understanding, June 2023]   Panoptic Lifting for 3D Scene Understanding with Neural Fields
  • [HiGraphics, February 2023]  Panoptic Lifting for 3D Scene Understanding with Neural Fields

Teaching



Reviewer Experience

Reviewed in the past for NeurIPS24, CVPR24, CVPR23, ICCV21, ECCV22, SIGGRAPH24, SIGGRAPH-Asia24, SIGGRAPH-Asia23, VMV24.