arXiv:2609.18393v1 Announce Type: new Abstract: Conditioning a video generator on multiple images requires preserving appearance while associating each reference with its intended role. We present MS...
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
arXiv:2602. 12304v5 Announce Type: replace-cross Abstract: Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts.
SemantiScene-Edit is a video editing system that uses a multimodal encoder and a pretrained video diffusion transformer to follow natural‑language instructions while preserving the source video’s appearance and temporal structure. The encoder processes source frames and the instruction together, sending semantic queries to the generator via a trainable connector and cross‑attention. A dual‑path visual route concatenates source‑video latents with noisy target latents to provide dense spatial and temporal information, and the model is trained with flow matching and a three‑stage curriculum on over 1.2 million instruction‑conditioned records, with a 100‑case benchmark for evaluation.
Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing approaches often rely on fragmented task-specific models. A general model must distinguish heterogeneous target, source, and reference signals to determine what to generate, preserve, or use as guidance, while reducing interference among tasks.
arXiv:2610.22744v1 Announce Type: new Abstract: Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image references (e.g., subject appearance), v...
Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must simultaneously preserve the appearance of each sub...
arXiv:2608.05648v2 Announce Type: replace Abstract: Video identity replacement seeks to transfer the identities of one or more subjects while preserving the motion, expressions, and temporal structur...
arXiv:2609.36503v1 Announce Type: new Abstract: Adding or removing a sounding object requires coordinated changes to visual content and sound while preserving the surrounding scene. Yet paired superv...
arXiv:2608.22819v1 Announce Type: new Abstract: Text-conditioned image-to-video (I2V) generation has advanced rapidly, yet generating videos with multiple subjects remains challenging. A model must s...
arXiv:2608.05803v2 Announce Type: replace Abstract: Recent advances in generative video modeling have enabled diverse generation, reference-based synthesis, extension, and editing, but existing appro...
arXiv:2605.23891v2 Announce Type: replace Abstract: Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. Howev...