Publications

GenVDM: Generating Vector Displacement Maps from a Single Image

Yuezhi Yang, Qimin Chen, Vladimir (Vova) Kim, Siddhartha Chaudhuri, Qixing Huang, Zhiqin Chen

Progressive autoregressive video diffusion models

Desai Xie, Zhan Xu, Yicong Hong, Hao Tan, Difan Liu, Feng Liu, Arie Kaufman, Yang Zhou

TIDE: Training Locally Interpretable Domain Generalization Models Enables Test-time Correction

Aishwarya Agarwal, Srikrishna Karanam, Vineet Gandhi

Highlight Poster

Composing Parts for Expressive Object Generation

Harsh Rangwani, Aishwarya Agarwal, Kuldeep Kulkarni, R. Venkatesh Babu, Srikrishna Karanam

Training-free Color-Style Disentanglement for Constrained Text-to-Image Synthesis

Aishwarya Agarwal, Srikrishna Karanam, Balaji Vasan Srinivasan

Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers

Haoran You, Connelly Barnes, Yuqian Zhou, Yan Kang, Zhenbang Du, Wei Zhou, Lingzhi Zhang, Yotam Nitzan, Xiaoyang Liu, Zhe Lin, Eli Shechtman, Sohrab Amirghodsi, Yingyan Celine Lin

ObjectMover: Generative Object Movement with Video Prior

Xin Yu, Tianyu (Steve) Wang, Soo Ye Kim, Paul Guerrero, Xi Chen, Qing Liu, Zhe Lin, Xiaojuan Qi

Instant3dit: Multiview Inpainting for Fast Editing of 3D Objects

Amir Barda, Matheus Gadelha, Vladimir (Vova) Kim, Noam Aigerman, Amit Haim Bermano, Thibault Groueix

ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion

Nissim Maruani, Yifan Wang, Matt Fisher, Pierre Alliez, Mathieu Desbrun

Motion Modes: What Could Happen Next?

Karran Pandey, Matheus Gadelha, Yannick Hold-Geoffroy, Karan Singh, Niloy J. Mitra, Paul Guerrero