[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

3DV 2026 | CVPRW 2025 (T4V)

Code for on-the-fly creation of pseudo video datasets as described in "How Important are Videos for Training Video LLMs?"

Loss Functions in the Era of Semantic Segmentation: A Survey and Outlook

Mask4Former: Mask Transformer for 4D Panoptic Segmentation

[ICCV 2025] DONUT: A Decoder-Only Model for Trajectory Prediction

Estimate absolute 3D human poses from RGB images.

A logging handler allowing logging messages to be sent to Telegram.