Publications

Boogu-Image-0.1

Boogu Team
Project Lead

Technical Report, 2026

report/project/code/models

Boogu-Image-0.1 is the first release of the Boogu project, an open effort toward unified multimodal image understanding and generation.

SimCMF: A Simple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality

Chenyang Lei, Liyi Chen, Jun Cen, Xiao Chen, Zhen Lei, Felix Heide, Qifeng Chen, Zhaoxiang Zhang

arXiv, 2024

paper/project/code

A simple and effective framework to study the transferability from vision foundation models trained on natural RGB images to other image modalities with different physical properties (e.g., polarization).

Vision-Language-Camera: Introducing Vision Language Models for Unleashing the Power of Camera Manual Mode

Zian Qian, Zhili Chen, Mengxi Sun, Zhaoxiang Zhang, Qifeng Chen, Chenyang Lei

In submission, 2024

code

The Vision-Language-Camera Model (VLC) introduces vision-language models to camera manual mode, offering guidance on how to adjust camera parameters tailored to the user's needs.

FIRM: Flexible Interactive Reflection ReMoval

Xiao Chen, Xudong Jiang, Yunkang Tao, Zhen Lei, Qing Li, Chenyang Lei†, Zhaoxiang Zhang†

AAAI, 2024

A framework for flexible interactive reflection removal with various forms of guidance, where users provide sparse visual guidance (points, boxes, or strokes) or text descriptions for better reflection removal.

Polarization Wavefront Lidars: Learning to Recover Large-Scale Scene Information from Polarized Wavefronts

Dominik Scheuble*, Chenyang Lei*, Mario Bijelic, Seung-Hwan Baek, Felix Heide

CVPR, 2024

paper/project/code

A novel long-range polarization wavefront lidar sensor (PolLidar) that modulates the polarization of the emitted and received light.

Robust Depth Enhancement via Polarization Prompt Fusion Tuning

Kei Ikemura*, Yiming Huang*, Felix Heide, Zhaoxiang Zhang, Qifeng Chen, Chenyang Lei†

CVPR, 2024

paper/project/code

A general framework that leverages polarization imaging to improve inaccurate depth measurements from various depth sensors.

Automatic Controllable Colorization by Imagination

Xiaoyan Cong, Yue Wu, Qifeng Chen, Chenyang Lei†

CVPR, 2024

paper/project/code

A novel approach to automatic image colorization by imitating the imagination process of human experts.

Neural Spline Fields for Burst Image Fusion and Layer Separation

Ilya Chugunov, David Shustin, Ruyu Yan, Chenyang Lei, Felix Heide

CVPR, 2024

paper/project/code

We use burst image stacks for layer separation, representing a burst with a two-layer alpha-composited image plus flow model constructed with neural spline fields.

Thin On-Sensor Nanophotonic Array Cameras

Praneeth Chakravarthula, Jipeng Sun, Xiao Li, Chenyang Lei, Gene Chou, Mario Bijelic, Johannes Froech, Arka Majumdar, Felix Heide

SIGGRAPH Asia, 2023

paper/project

A thin nanophotonic imager that employs a learned array of metalenses to capture a scene in-the-wild.

Randomized Quantization: A Generic Augmentation for Data Agnostic Self-supervised Learning

Huimin Wu*, Chenyang Lei*, Xiao Sun, Peng-Shuai Wang, Qifeng Chen, Kwang-Ting Cheng, Stephen Lin, Zhirong Wu

ICCV, 2023

arXiv/code

A modality-agnostic augmentation for contrastive learning, applicable to image, audio, point clouds, sensors, and other modalities.

FateZero: Fusing Attentions for Zero-shot Text-based Video Editing

Chenyang Qi, Xiaodong Cun, Yong Zhang, Chenyang Lei, Xintao Wang, Ying Shan, Qifeng Chen

ICCV, 2023

arXiv/project/code

A zero-shot text-driven video style and local attribute editing model.

Blind Video Deflickering by Neural Filtering with a Flawed Atlas

Chenyang Lei, Xuanchi Ren, Zhaoxiang Zhang, Qifeng Chen

CVPR, 2023

arXiv/project/code

A general postprocessing framework that removes different types of flicker from various videos, including videos from capturing, processing, and generation.

High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization

Jiaxin Xie*, Hao Ouyang*, Jingtan Piao, Chenyang Lei, Qifeng Chen

CVPR, 2023

arXiv/project/code

A high-fidelity 3D GAN inversion framework that synthesizes photo-realistic novel views while preserving specific details of the input image.

Deep Video Prior for Video Consistency and Propagation

Chenyang Lei, Yazhou Xing, Hao Ouyang, Qifeng Chen

TPAMI, 2022

code

We extend the deep video prior (NeurIPS 2020) to video propagation and improve its training efficiency.

Shape from Polarization for Complex Scenes in the Wild

Chenyang Lei*, Chenyang Qi, Jiaxin Xie, Na Fan, Vladlen Koltun, Qifeng Chen

CVPR, 2022

arXiv/project/code

A data-driven approach with physics-based priors to scene-level normal estimation from a single polarization image.

Robust Reflection Removal with Reflection-free Flash-only Cues

Chenyang Lei, Qifeng Chen

CVPR, 2021

arXiv/code/project

A simple yet effective reflection-free cue for robust reflection removal from a pair of flash and ambient images, exploiting a flash-only image obtained in raw data space.

Neural Camera Simulators

Hao Ouyang*, Zifan Shi*, Chenyang Lei, Ka Lung Law, Qifeng Chen

CVPR, 2021

paper/code

A controllable camera simulator based on deep neural networks to synthesize raw image data under different camera settings, including exposure time, ISO, and aperture.