Stars
A curated list of awesome egocentric (first-person) video datasets, papers, benchmarks and resources.
Convert 2D videos and photos into interactive 3D scenes using ML-SHARP and Rerun. Explore your videos in 3D space with depth maps, navigation tools, and creative effects.
Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"
This is a collection of recent papers on reasoning in video generation models.
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…
Official PyTorch implementation of the paper "Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs"
A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone
[CVPR 2025] Official PyTorch code of "Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation".
[ICCV 2023] UniVTG: Towards Unified Video-Language Temporal Grounding
A curated list for awesome discrete diffusion models resources.
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
Building simple diffusion models for image generation. More so for understanding and learning.
[WACV'25] Temporal Instructional Diagram Grounding in Unconstrained Videos
A collection of my book notes on various subjects, mainly computer science
[ECCV2024] Gated Temporal Action Anticipation for Stochastic Long-Term Anticipation
Code and data release for the paper "Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment" (NeurIPS 2023)
React + Next.js template for research websites (for PhD students, researchers, etc)
Visualizing the learned space-time attention using Attention Rollout
Collection of AWESOME vision-language models for vision tasks
It is my belief that you, the postgraduate students and job-seekers for whom the book is primarily meant will benefit from reading it; however, it is my hope that even the most experienced research…
A curated list of awesome prompt/adapter learning methods for vision-language models like CLIP.