+

Research Posts

Paint Bucket Colorization Using Anime Character Color Design Sheets

Papers with Code
Reporter Kate Martin

By Kate Martin

Posted on: October 28, 2024

Paint Bucket Colorization Using Anime Character Color Design Sheets

Line art colorization plays a crucial role in hand-drawn animation production, where digital artists manually colorize segments using a paint bucket tool, guided by RGB values from character color design sheets. This process, often called paint bucket colorization, involves two main tasks: keyframe ...

Read More

Blendify -- Python rendering framework for Blender

Papers with Code
Reporter Kate Martin

By Kate Martin

Posted on: October 25, 2024

Blendify -- Python rendering framework for Blender

With the rapid growth of the volume of research fields like computer vision and computer graphics, researchers require effective and user-friendly rendering tools to visualize results. While advanced tools like Blender offer powerful capabilities, they also require a significant effort to master. Th...

Read More

3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation

Papers with Code
Reporter Kate Martin

By Kate Martin

Posted on: October 25, 2024

3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation

Multi-view image diffusion models have significantly advanced open-domain 3D object generation. However, most existing models rely on 2D network architectures that lack inherent 3D biases, resulting in compromised geometric consistency. To address this challenge, we introduce 3D-Adapter, a plug-in m...

Read More

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

Papers with Code
Reporter Javier Vásquez

By Javier Vásquez

Posted on: October 25, 2024

Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances

Current image watermarking methods are vulnerable to advanced image editing techniques enabled by large-scale text-to-image models. These models can distort embedded watermarks during editing, posing significant challenges to copyright protection. In this work, we introduce W-Bench, the first compre...

Read More

SNAC: Multi-Scale Neural Audio Codec

Papers with Code
Reporter Naomi Wilson

By Naomi Wilson

Posted on: October 21, 2024

SNAC: Multi-Scale Neural Audio Codec

Neural audio codecs have recently gained popularity because they can represent audio signals with high fidelity at very low bitrates, making it feasible to use language modeling approaches for audio generation and understanding. Residual Vector Quantization (RVQ) has become the standard technique fo...

Read More

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

Papers with Code
Reporter Javier Vásquez

By Javier Vásquez

Posted on: October 21, 2024

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified framework that covers several recent methods and their novel varian...

Read More

aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Completion

Papers with Code
Reporter Naomi Wilson

By Naomi Wilson

Posted on: October 18, 2024

aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Completion

Large Language Models (LLMs) have been widely used in code completion, and researchers are focusing on scaling up LLMs to improve their accuracy. However, larger LLMs will increase the response time of code completion and decrease the developers' productivity. In this paper, we propose a lightweight...

Read More

MANet: Fine-Tuning Segment Anything Model for Multimodal Remote Sensing Semantic Segmentation

Papers with Code
Reporter Kate Martin

By Kate Martin

Posted on: October 16, 2024

MANet: Fine-Tuning Segment Anything Model for Multimodal Remote Sensing Semantic Segmentation

Multimodal remote sensing data, collected from a variety of sensors, provide a comprehensive and integrated perspective of the Earth's surface. By employing multimodal fusion techniques, semantic segmentation offers more detailed insights into geographic scenes compared to single-modality approaches...

Read More