Papers for

film postproduction teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Video object removal method improves background filling and smoothness

TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native Generation

Abstract: Video object removal presents a uniquely difficult editing challenge. Because a removal prompt specifies only what to erase rather than what to generate, the model must infer and reconstruct a highly specific occluded background entirely from the surrounding context. Existing training-free methods struggle with this because their editing mechanisms act primarily as localized erasers. They fail to actively synthesize the missing background details and often leave behind ghosting artifacts. To solve this, we propose TripleFlow, a training-free framework that tightly couples erasure and generation. It coordinates a source flow, a residual flow, and a synthesis flow throughout the entire process. By reusing a single target prediction, the residual flow isolates and suppresses the object, while the synthesis flow independently reconstructs the occluded background. Crucially, TripleFlow injects this newly synthesized background back into the editing trajectory at every step. This continuous feedback loop ensures that the generated structures actively guide the removal process, achieving seamless completion that is spatiotemporally consistent with the unedited scene. Extensive evaluations across five challenging benchmarks demonstrate that TripleFlow establishes a new state-of-the-art, significantly outperforming existing baselines in both reconstruction fidelity and temporal consistency.

Wed 30 SeptComputer Vision and Pattern Recognition
The gist
Removing objects from videos is hard because the system needs to guess and redraw the hidden parts behind those objects. Existing methods mainly erase the object locally but do not recreate the missing background well, causing leftover ghosts or blurs. The authors propose TripleFlow, which combines object removal and new background creation at every step, so the video looks smooth and consistent over time. This method works well without extra training and beats previous techniques on several tests.
Open → 2609.39157v1