Publications

Preprint:

• Fang Li, Hao Zhang, Narendra Ahuja
  Self-Calibrating 4D Novel View Synthesis from Monocular Videos Using Gaussian Splatting.

2025

• Hao Zhang*, Haolan Xu*, Chun Feng, Varun Jampani, Narendra Ahuja
  PhysRig: Differentiable Physics-Based Skinning and Rigging Framework for Realistic Articulated Object Modeling .
  Proceedings of the International Conference on Computer Vision (ICCV) 2025

• Hao Zhang*, Di Chang*, Fang Li, Mohammad Soleymani, Narendra Ahuja
  MagicPose4D: Crafting Articulated Models with Appearance and Motion Control.
  Proceedings of the Transactions on Machine Learning Research (TMLR) 2025

2024

• Hao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja
  S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video.
  Proceedings of the International Conference on Machine Learning (ICML) 2024

• Hao Zhang, Fang Li, Samyak Rawlekar, Narendra Ahuja
  LIMR: Learning Implicit Representation for Reconstructing Articulated Objects.
  Proceedings of the International Conference on Learning Representations (ICLR) 2024

• Hao Zhang, Fang Li, Lu Qi, Ming-Hsuan Yang, and Narendra Ahuja
  CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen.
  Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) 2024 Rank 1 @ SMIYC-Anomaly Track \& Obstacle Track (w/o OOD) on mean F1

• Hao Zhang, Fang Li, Narendra Ahuja
  Open-NeRF: Towards Open Vocabulary NeRF Decomposition.
  Proceedings of the Winter Conference on Applications of Computer Vision (WACV) 2024

2022

• Hao Zhang, Ruimao Zhang
  Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation.
  Proceedings of the Asian Conference on Computer Vision (ACCV) 2022