Top Important Computer Vision Papers for the Week from 04/12 to 10/12

Stay Updated with Recent Computer Vision Research

Every week, several top-tier academic conferences and journals showcased innovative research in computer vision, presenting exciting breakthroughs in various subfields such as image recognition, vision model optimization, generative adversarial networks (GANs), image segmentation, video analysis, and more.

This article provides a comprehensive overview of the most significant papers published in the Second week of December 2023, highlighting the latest research and advancements in computer vision. Whether you’re a researcher, practitioner, or enthusiast, this article will provide valuable insights into the state-of-the-art techniques and tools in computer vision.

Table of Contents:

1. Stable Diffusion 

2. Vision Language Models 

3. Image Generation & Editing 

4. Video Generation & Editing 

5. Image Segmentation

6. Image Recognition

---

---

1. Stable Diffusion 

1. Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models

2. AnimateZero: Video Diffusion Models are Zero-Shot Image Animators

3. GenTron: Delving Deep into Diffusion Transformers for Image and Video Generation

4. Cache Me if You Can: Accelerating Diffusion Models through Block Caching

5. Context Diffusion: In-Context Aware Image Generation

6. Analyzing and Improving the Training Dynamics of Diffusion Models

7. ImageDream: Image-Prompt Multi-view Diffusion for 3D Generation

8. X-Adapter: Adding Universal Compatibility of Plugins for Upgraded Diffusion Model

9. Orthogonal Adaptation for Modular Customization of Diffusion Models

10. ReconFusion: 3D Reconstruction with Diffusion Priors

11. Alchemist: Parametric Control of Material Properties with Diffusion Models

12. VideoBooth: Diffusion-based Video Generation with Image Prompts

13. DREAM: Diffusion Rectification and Estimation-Adaptive Models

14. HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models

15. DiffiT: Diffusion Vision Transformers for Image Generation

16. StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D

17. DeepCache: Accelerating Diffusion Models for Free

18. Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models

---

2. Vision Language Models

1. Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

2. Language-Informed Visual Concept Learning

3. Describing Differences in Image Sets with Natural Language

4. LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

5. GPT4Point: A Unified Framework for Point-Language Understanding and Generation

6. Rejuvenating image-GPT as Strong Visual Representation Learners

7. Merlin: Empowering Multimodal LLMs with Foresight Minds

---

3. Image Generation & Editing

1. Controllable Human-Object Interaction Synthesis

2. PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

3. HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image

4. Gen2Det: Generate to Detect

5. Scaling Laws of Synthetic Images for Model Training … for Now

6. Relightable Gaussian Codec Avatars

7. Generating Illustrated Instructions

8. DreamComposer: Controllable 3D Object Generation via Multi-View Conditions

9. Self-conditioned Image Generation via Generating Representations

10. Text-Guided 3D Face Synthesis — From Generation to Editing

11. X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation

12. GIVT: Generative Infinite-Vocabulary Transformers

13. Style Aligned Image Generation via Shared Attention

14. Generative Powers of Ten

15. MVHumanNet: A Large-scale Dataset of Multi-view Daily Dressing Human Captures

---

4. Video Generation & Editing

1. DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

2. Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

3. MotionCtrl: A Unified and Flexible Motion Controller for Video Generation

4. MagicStick: Controllable Video Editing via Control Handle Transformations

5. LivePhoto: Real Image Animation with Text-guided Motion Control

6. StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

7. FaceStudio: Put Your Face Everywhere in Seconds

8. DragVideo: Interactive Drag-style Video Editing

9. FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting

10. Fast View Synthesis of Casual Videos

11. VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models

12. VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence

13. MoMask: Generative Masked Modeling of 3D Human Motions

---

5. Image Segmentation 

1. Segment and Caption Anything

2. Segment Any 3D Gaussians

3. SANeRF-HQ: Segment Anything for NeRF in High Quality

---

6. Image Recognition 

1. Object Recognition as Next Token Prediction

---

Are you looking to start a career in data science and AI and do not know how? I offer data science mentoring sessions and long-term career mentoring:

• Mentoring sessions: https://lnkd.in/dXeg3KPW

• Long-term mentoring: https://lnkd.in/dtdUYBrM