- Foster collaboration and knowledge exchange in various sub-fields of Computer Vision.
- Explore and discuss cutting-edge research (SOTA) across different areas.
- Provide a platform for brainstorming, peer review, and constructive criticism.
- Develop reading papers & ideation as a habit or hobby.
- Online Sessions : Convenient for everyone.
- Semi-Formal : Develop reading and discussion skills in a relaxed atmosphere.
- Frequency : Weekly (optional for members to present every week).
- Two Papers per Session : Focus on foundational or influential papers relevant to different sub-fields.
- Open Selection : Members can add interesting papers to a shared list (presenter not required to be the recommender).
- Collaborative Exploration : Brief on-the-spot reading and group discussion encouraged. Members are free to prepare beforehand as well.
- Active Participation : Attendees should guide the presenter and contribute to understanding, not just ask questions.
- Ideas Sandbox : Members can present their own ideas for feedback and discussion.
- Minimal Commitment : While regular participation is encouraged, a minimum of two volunteers per week for paper presentations is preferred.
- Constructive Environment : Promote open discussion, respectful debate, and supportive feedback.
- FlowMap: High-Quality Camera Poses, Intrinsics, and Depth via Gradient Descent [Submitted 23 Apr 2024 arxiv] [Paper] [Demo] ~Continue next time
- DreamFusion: Text-to-3D using 2D Diffusion [ICLR 23] [Paper] [Demo]
- LucidDreaming: Controllable Object-Centric 3D Generation [Submitted 30 Nov 2023 arxiv] [Paper] [Demo] [Code]
- Awesome NERF editing
- GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting [Submitted 24 Nov 2023 arxiv] [Paper] [Demo] [Code] [Video]
- Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions [ICCV 23] [Paper] [Demo] [Code]
- DreamBooth3D: Subject-Driven Text-to-3D Generation [ICCV 23] [Paper] [Demo]
- DreamEditor: Text-Driven 3D Scene Editing with Neural Fields [SIGGRAPH 23] [Paper] [Demo] [Code]
- Language Conditioned Spatial Relation Reasoning for 3D Object Grounding [NerIPS 22] [Paper] [Demo] [Code]
- 3D Concept Grounding on Neural Fields [NeurIPS 22] [Paper] [Code]
- Multi-View Transformer for 3D Visual Grounding [CVPR 22] [Paper] [Code]
- Breathing New Life into 3D Assets with Generative Repainting [ICCV 23] [Paper] [Demo] [Code]
- RePaint: Inpainting using Denoising Diffusion Probabilistic Models [CVPR 22] [Paper] [Code]
- Diffusion Probabilistic Models for Scene-Scale 3D Categorical Data [Submitted 2 Jan 23 arxiv] [Paper] [Code]
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis [Paper] [Demo] [Code] [Dataset]
- D-NeRF: Neural Radiance Fields for Dynamic Scenes [CVPR 21] [Paper] [Demo] [Code]
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields [ICCV 21] [Paper] [Code]
- Understanding Diffusion Models: A Unified Perspective. by Calvin Luo [Explainer, arxiv] [Paper]
- LatentPaint: Image Inpainting in Latent Space with Diffusion Models [WACV 24] [Paper] [Video]
- DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation [CVPR 23] [Paper] [Demo] [Dataset] [Tutorial]
- A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT [Submitted 18 Feb 23 arxiv] [Paper]
- NeRF: Neural Radiance Field in 3D Vision, A Comprehensive Review [Submitted 30 Nov 23 arxiv] [Paper]
- A Survey of Embodied AI: From Simulators to Research Tasks [IEEE Txn 22] [Paper]
- Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks [PMLR '21] [Paper]
Understanding Diffusion Models: A Unified Perspective [Submitted 25 Aug 23 arxiv] [Paper]