News

Our work "Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think" has been accepted at WACV'25.

Our work "Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization" has been accepted at IROS'24.

We have two papers accepted at the 2024 IEEE Conference on Computer Vision and Pattern Recognition (CVPR):

• Point-VOS: Pointing Up Video Object Segmentation
• ControlRoom3D: Room Generation using Semantic Proxies

We have two papers accepted at Workshops:

• RGB-D Cube R-CNN: 3D Object Detection with Selective Modality Dropout
• OoDIS: Anomaly Instance Segmentation Benchmark

Our Mask4Former approach has been accepted at the 2024 International Conference on Robotics and Automation (ICRA):

• Mask4Former: Mask Transformer for 4D Panoptic Segmentation

Our AGILE3D approach has been accepted at the 2024 International Conference on Learning Representations (ICLR):

• AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation