Dingming Liu

2 accepted papers

2026

AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression

ICML 2026poster

Object removal aims to eliminate specified objects from images while plausibly inpainting the affected regions with background content. Current training-free methods typically block attention to object regions within self-attention layers during the image generation process, leveraging surrounding b…

Cited by 0 Source ↗Scholar ↗

2025

LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering

Xiaohang Zhan, Dingming Liu

ICCV 2025poster

We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often lack precision. While layout-to-image methods provide control o…

Cited by 0 Source ↗PDF ↗Scholar ↗