Top Important Computer Vision Papers for the Week from 18/12 to 24/12

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 third 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. DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

2. Faster Diffusion: Rethinking the Role of UNet Encoder in Diffusion Models

3. VecFusion: Vector Font Generation with Diffusion

4. SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

5. Your Student is Better Than Expected: Adaptive Teacher-Student Collaboration for Text-Conditional Diffusion Models

6. Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models

7. VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder

8. Towards Accurate Guided Diffusion Sampling through Symplectic Adjoint Method

9. StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation

10. Carve3D: Improving Multi-view Reconstruction Consistency for Diffusion Models with RL Finetuning

11. Zero-Shot Metric Depth with a Field-of-View Conditioned Diffusion Model

12. RadEdit: stress-testing biomedical vision models via diffusion image editing

13. DREAM-Talk: Diffusion-based Realistic Emotional Audio-driven Method for Single Image Talking Face Generation

14. Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models

15. HD-Painter: High-Resolution and Prompt-Faithful Text-Guided Image Inpainting with Diffusion Models

2. Vision Language Models

1. Silkie: Preference Distillation for Large Visual Language Models

2. 3D-LFM: Lifting Foundation Model

3. Jack of All Tasks, Master of Many: Designing General-purpose Coarse-to-Fine Vision-Language Model

4. A Challenger to GPT-4V? Early Explorations of Gemini in Visual Expertise

3. Image Generation & Editing

1. Stable Score Distillation for High-Quality 3D Generation

2. Rich Human Feedback for Text-to-Image Generation

3. GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

4. MagicScroll: Nontypical Aspect-Ratio Image Generation for Visual Storytelling via Multi-Layered Semantic-Aware Denoising

5. MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance

6. StarVector: Generating Scalable Vector Graphics Code from Images

7. HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles

8. TIP: Text-Driven Image Processing with Semantic and Restoration Instructions

9. Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior

10. Unlocking Pre-trained Image Backbones for Semantic Image Synthesis

11. Splatter Image: Ultra-Fast Single-View 3D Reconstruction

12. Repaint123: Fast and High-quality One Image to 3D Generation with Progressive Controllable 2D Repainting

13. ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors

14. DreamTuner: Single Image is Enough for Subject-Driven Generation

15. PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

4. Video Generation & Editing

1. VidToMe: Video Token Merging for Zero-Shot Video Editing

2. GauFRe: Gaussian Deformation Fields for Real-time Dynamic Novel View Synthesis

3. Text-Conditioned Resampler For Long Form Video Understanding

4. HeadCraft: Modeling High-Detail Shape Variations for Animated 3DMMs

5. VideoPoet: A Large Language Model for Zero-Shot Video Generation

6. InstructVideo: Instructing Video Diffusion Models with Human Feedback

7. MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers

8. Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis

5. Image Segmentation

1. MobileSAMv2: Faster Segment Anything to Everything

2. TinySAM: Pushing the Envelope for Efficient Segment Anything Model

6. Object Tracking 

1. Tracking Any Object Amodally

---

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