Ivaylo 'Ivo' Boyadzhiev

I am a Senior Applied Science Manager at Zillow Group, where currently I lead a team of Applied Scientists and Machine Learning Engineers working on indoor scene reconstruction and understanding, using scalable off-the-shelf hardware solutions, like smart phones and 360 RGB cameras. I also co-managed the release of our open-source, free for academic research, Zillow Indoor Dataset, published at CVPR 2021.

At Zillow I've worked on Floor Plan Reconstruction for Interactive Floor Plans, Panorama Stitching for 3D Home®, Improving Video Stabilization for Video Walkthrough, Intrinsic Image Decomposition for Zillow Digs. I did my PhD at Cornell University, where I was advised by Kavita Bala and I spent 3 summers 2012-2014 working at Adobe Research under the supervision of Sylvain Paris. My PhD thesis centered around the problems of designing algorithms to assist advanced computational photography tasks, such as lighting design, white balance under mixed lighting, and image filters for material editing.

Email  /  CV  /  Google Scholar

profile photo
Research

I'm interested in computer vision, machine learning, computational photorgraphy and image processing. Much of my recent research is about indoor reconstruction, scene understanding and wide-baseline camera localization in challenging interior settings.

covispose CoVisPose: Co-Visibility Pose Transformer for Wide-Baseline Relative Pose Estimation in 360° Indoor Panoramas
Will Hutchcroft, Yuguang Li, Ivaylo Boyadzhiev, Zhiqiang Wan, Haiyan Wang, Sing Bing Kang,
ECCV, 2022
project page (coming soon) / supplement / bibtex

We present CoVisPose, a new end-to-end supervised learning method for relative camera pose estimation in wide baseline 360° indoor panoramas.

salve SALVe: Semantic Alignment Verification for Floorplan Reconstruction from Sparse Panoramas
John W Lambert, Yuguang Li, Ivaylo Boyadzhiev, Lambert Wixson, Manjunath Narayana, Will Hutchcroft, James Hays, Frank Dellaert, Sing Bing Kang,
ECCV, 2022
project page / supplement / video / code / bibtex

We propose a new system for automatic 2D floorplan reconstruction that is enabled by SALVe, our novel pairwise learned alignment verifier. The inputs to our system are sparsely located 360° panoramas, whose semantic features (windows, doors, and openings) are inferred and used to hypothesize pairwise room adjacency or overlap.

virtual_staging Semantically Supervised Appearance Decomposition for Virtual Staging from a Single Panorama
Tiancheng Zhi, Bowei Chen, Ivaylo Boyadzhiev, Sing Bing Kang, Martial Hebert, Srinivasa G. Narasimhan,
ACM ToG (SIGGRAPH), 2022
project page / supplement / code / bibtex

We describe a novel, weakly-supervised, approach to decompose a single panorama of an empty indoor environment into four appearance components: specular, direct sunlight, diffuse and diffuse ambient without direct sunlight.

itl Generating Topological Structure of Floorplans from Room Attributes
Yu Yin, Will Hutchcroft, Naji Khosravan, Ivaylo Boyadzhiev, Yun Fu, Sing Bing Kang,
ICMR, 2022
paper / video / bibtex

We propose to extract topological information from room attributes using an enhancement of GNNs that we call Iterative and adaptive graph Topology Learning (ITL). ITL progressively predicts multiple relations between rooms; at each iteration, it improves node embeddings, which in turn facilitates the generation of a better topological graph structure.

laser LASER: LAtent SpacE Rendering for 2D Visual Localization
Zhixiang Min, Naji Khosravan, Zachary Bessinger, Manjunath Narayana, Sing Bing Kang, Ivaylo Boyadzhiev
CVPR, 2022 (Oral Presentation)
project page / supplement / video / code / bibtex

We address the problem of multimodal pose estimation, given an RGB image and a 2D schematifc floor-plan. We introduce the concept of latent space rendering, where 2D pose hypotheses on the floor map are directly rendered into a geometrically-structured latent space by aggregating viewing ray features.

psmnet PSMNet: Position-aware Stereo Merging Network for Room Layout Estimation
Haiyan Wang, Will Hutchcroft, Yuguang Li, Zhiqiang Wan, Ivaylo Boyadzhiev, Yingli Tian, Sing Bing Kang,
CVPR, 2022
supplement / bibtex

Given two-view panoramas, we propose the first network to jointly estimate the complete room layout and refine a given coarse relative pose between them.

zind Zillow Indoor Dataset: Annotated Floor Plans With 360° Panoramas and 3D Room Layouts
Steve Cruz, Will Hutchcroft, Yuguang Li, Naji Khosravan, Ivaylo Boyadzhiev, Sing Bing Kang
CVPR, 2021
project page / supplement / bibtex

The Zillow Indoor Dataset (ZInD) is available for download (academic research only)! It features more than 70k omnidirectional panoramas from more than 1.5k unfurnished homes, and has room layout and annotation (windows and doors) information.

panosfm Panoramic Structure from Motion via Geometric Relationship Detection
Satoshi Ikehata, Ivaylo Boyadzhiev, Qi Shan, Yasutaka Furukawa
CoRR arXiv, 2016
arXiv paper / bibtex

We address challenging cases for SfM (in indoor settings) by fusing of single and multi-view reconstruction techniques via geometric relationship detection (e.g., detecting 2D lines as coplanar in 3D).

diy_light_design Do-It-Yourself Lighting Design for Product Videography
Ivaylo Boyadzhiev, Jiawen Chen, Sylvain Paris, Kavita Bala
ICCP, 2016
paper / video / slides / bibtex

We propose a simple do-it-yourself (DIY) setup with a video camera on a tripod recording the product while the user waves an area light source around it for a couple of minutes.

band_sifting Band-Sifting Decomposition for Image Based Material Editing
Ivaylo Boyadzhiev, Sylvain Paris, Kavita Bala, Edward H. Adelson
ACM ToG, 2015
project page / supplement / video / data / bibtex

We propose an extended family of band-sifting filters and study their perceptual effects for image-based material editing.

light_compositing User-assisted Image Compositing for Photographic Lighting
Ivaylo Boyadzhiev, Sylvain Paris, Kavita Bala
SIGGRAPH, 2013
project page / supplement / video / data / bibtex

We propose a novel user-guided lighting design method based on capturing several photos from a fixed viewpoint with a moving light source.

mixed_wb User-guided White Balance for Mixed Lighting Conditions
Ivaylo Boyadzhiev, Kavita Bala, Sylvain Paris, Frédo Durand
SIGGRAPH Asia, 2012
project page / supplement / bibtex

We propose a solution to the ill-posed mixed light white balance problem, based on relative reflectance properties, that are easy for humans to provide in the form of scribbles.

Misc
CVPR Reviewer: 2020-2022
ECCV Reviewer: 2020, 2022
ICCV Reviewer: 2021, outstanding reviewer award
SIGGRAPH Reviewer: 2015-2018, 2022
cs5625 Advanced Interactive Graphics, Spring 2013, Cornell University
Introduction to Computer Graphics, Fall 2011, Cornell Univerity
Scientific Computation, Spring 2011, Cornell University
Introduction to Computer Graphics, Fall 2010, Cornell Univerity
Design and Analysis of Computer Algorithms, 2007 and 2008, Sofia University

Design and source code from Jon Barron's website