News

Research

• pix2gestalt: Amodal Segmentation by Synthesizing Wholes CVPR 2024

  • Ege Ozguroglu,
  • Ruoshi Liu,
  • Dídac Surís,
  • Dian Chen,
  • Achal Dave,
  • Pavel Tokmakov,
  • Carl Vondrick

  Conference on Computer Vision and Pattern Recognition (CVPR), 2024

  • amodal segmentation
  • diffusion
  • generalization

  pix2gestalt synthesizes whole objects from only partial visible ones, enabling amodal segmentation, recognition, and 3D reconstruction of occluded objects.

  • [paper]
  • [code]
  • [project page]
  • [live demo (soon)]

  
• FSD: Fast Self-Supervised Single RGB-D to Categorical 3D Objects ICRA 2024

  • Mayank Lunayach,
  • Sergey Zakharov,
  • Dian Chen,
  • Rareș Ambruș,
  • Zsolt Kira,
  • Muhammad Zubair Irshad

  International Conference on Robotics and Automation (ICRA), 2024

  • self-supervision
  • 3D geometry
  • 6D pose estimation

  A framework for fast self-supervised categorical 6D pose and size estimation and shape reconstruction.

  • [paper]
  • [code (coming soon)]
  • [project page]

  
• Towards Zero-Shot Scale-Aware Monocular Depth Estimation ICCV 2023

  • Vitor Guizilini,
  • Igor Vasiljevic,
  • Dian Chen,
  • Rareș Ambruș,
  • Adrien Gaidon

  International Conference on Computer Vision (ICCV), 2023

  • 3D geometry
  • depth estimation
  • generalization
  • foundation model

  A step toward a generalizable 3D foundation depth model, which predicts metric depth for arbitrary test images from different domains and camera parameters.

  • [paper]
  • [code]
  • [project page]

  
• Viewpoint Equivariance for Multi-View 3D Object Detection CVPR 2023

  • Dian Chen,
  • Jie Li,
  • Vitor Guizilini,
  • Rareș Ambruș,
  • Adrien Gaidon

  Conference on Computer Vision and Pattern Recognition (CVPR), 2023

  • 3D geometry
  • object detection

  Improve multi-view 3D object detection by injecting 3D geometry as input-level inductive bias to a transformer, and regularizing the multi-view consistency with viewpoint equivariance loss.

  ^{Featured in oral talk in Vision-Centric Autonomous Driving (VCAD) Workshop at CVPR 2023!}

  • [paper]
  • [code]
  • [long video]

  
• Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking CVPR 2023

  • Ziqi Pang,
  • Jie Li,
  • Pavel Tokmakov,
  • Dian Chen,
  • Sergey Zagoruyko,
  • Yu-Xiong Wang

  Conference on Computer Vision and Pattern Recognition (CVPR), 2023

  • temporal learning
  • multi-object tracking

  An end-to-end tracking framework that reasons from the "past" and makes predictions into the "future", featuring drastically lower ID-switches.

  • [paper]
  • [code]
  • [demo]

  
• Depth Is All You Need for Monocular 3d Detection ICRA 2023

  • Dennis Park,
  • Jie Li,
  • Dian Chen,
  • Vitor Guizilini,
  • Adrien Gaidon

  International Conference on Robotics and Automation (ICRA), 2023

  • self-supervision
  • 3D geometry
  • object detection
  • representation learning

  Improve 3D monocular perception by enhancing the model's 3D representation by self-supervised depth pre-training.

  • [paper]
  • [code]

  
• Contrastive Test-Time Adaptation CVPR 2022

  • Dian Chen,
  • Dequan Wang,
  • Sayna Embrahimi,
  • Trevor Darrell

  Conference on Computer Vision and Pattern Recognition (CVPR), 2022

  • self-supervision
  • domain adaptation
  • representation learning

  Exploit self-supervised contrastive learning to adapt the model's representation at test-time upon distribution shifts.

  ^{Featured in keynote talk in Robustness in Sequential Data Workshop at CVPR 2022!}

  • [paper]
  • [code]
  • [video]
  • [project page]

  
• Multi-Frame Self-Supervised Depth with Transformers CVPR 2022

  • Vitor Guizilini,
  • Rareș Ambruș,
  • Dian Chen,
  • Sergey Zakharov,
  • Adrien Gaidon

  Conference on Computer Vision and Pattern Recognition (CVPR), 2022

  • self-supervision
  • 3D geometry
  • depth estimation

  Leverage geometric relationships between frames and attention mechanism, to learn powerful feature matching for points sampled on epipolar lines using transformers.

  • [paper]
  • [code]

  
• Region-Level Active Learning for Cluttered Scenes Arxiv 2021

  • Michael Laielli,
  • Giscard Biamby,
  • Dian Chen,
  • Adam Loeffler,
  • Phat Dat Nguyen,
  • Ross Luo,
  • Trevor Darrell,
  • Sayna Embrahimi

  • active learning
  • object detection

  Combine the best of both image-level and object-level approach into a generalized, region-level active learning framework for satellite image object detection.

  • [paper]

  
• Minimax Active Learning Arxiv 2021

  • Sayna Embrahimi,
  • William Gan,
  • Dian Chen,
  • Giscard Biamby,
  • Kamyar Salahi,
  • Michael Laielli,
  • Shizhan Zhu,
  • Trevor Darrell

  • active learning
  • representation learning

  Active learning via a minimax game on classification entropy.

  • [paper]

  

Service