{"ID":2832217,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.06358","arxiv_id":"2512.06358","title":"Rectifying Latent Space for Generative Single-Image Reflection Removal","abstract":"Single-image reflection removal is a highly ill-posed problem, where existing methods struggle to reason about the composition of corrupted regions, causing them to fail at recovery and generalization in the wild. This work reframes an editing-purpose latent diffusion model to effectively perceive and process highly ambiguous, layered image inputs, yielding high-quality outputs. We argue that the challenge of this conversion stems from a critical yet overlooked issue, i.e., the latent space of semantic encoders lacks the inherent structure to interpret a composite image as a linear superposition of its constituent layers. Our approach is built on three synergistic components, including a reflection-equivariant VAE that aligns the latent space with the linear physics of reflection formation, a learnable task-specific text embedding for precise guidance that bypasses ambiguous language, and a depth-guided early-branching sampling strategy to harness generative stochasticity for promising results. Extensive experiments reveal that our model achieves new SOTA performance on multiple benchmarks and generalizes well to challenging real-world cases.","short_abstract":"Single-image reflection removal is a highly ill-posed problem, where existing methods struggle to reason about the composition of corrupted regions, causing them to fail at recovery and generalization in the wild. This work reframes an editing-purpose latent diffusion model to effectively perceive and process highly am...","url_abs":"https://arxiv.org/abs/2512.06358","url_pdf":"https://arxiv.org/pdf/2512.06358v1","authors":"[\"Mingjia Li\",\"Jin Hu\",\"Hainuo Wang\",\"Qiming Hu\",\"Jiarui Wang\",\"Xiaojie Guo\"]","published":"2025-12-06T09:16:14Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Variational Autoencoder\"]","has_code":false}