Tag
This paper proposes using generative inpainting to create photorealistic perturbations for LIME, improving the quality of explanations by avoiding out-of-distribution artifacts common in traditional occlusion methods.
Recommend 5 open-source local image processing tools: rembg for background removal, Upscayl for HD upscaling, IOPaint for content removal, Real-ESRGAN for super-resolution, and GFPGAN for face restoration. All free, offline, no server upload.
Jordi Pons announces Stable Audio 3, a family of open-weight models for generating instrumental music and sound effects, supporting fast generation and editing on licensed audio.
Proposes TAP, a tabular augmentation policy that couples diffusion inpainting with a learner-conditioned policy to improve downstream model performance under data scarcity, outperforming strong baselines on real-world datasets.
This paper analyzes zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, providing information-theoretic guarantees and proposing a projected-Langevin initialization method.
Netflix releases VOID, a video inpainting model that removes objects from videos while realistically simulating physical interactions (e.g., objects falling when a person is removed), built on CogVideoX and fine-tuned with interaction-aware quadmask conditioning.