arXiv:2603. 06140v2 Announce Type: replace-cross Abstract: Video object insertion is fundamental to video editing, yet existing diffusion methods often produce visually plausible but physically inconsistent results.
While traditional graphics methods often synthesize 3D indoor scenes autoregressively or hierarchically, recent vision-language model (VLM)-based generators predominantly adopt a one-shot paradigm where the full layout is planned at once. This one-shot approach often requires global re-optimization or complete reconstruction during interactive editing (e.
Bernini proposes a unified framework that separates semantic planning and pixel rendering for video generation and editing. An MLLM-based planner predicts target semantics in ViT embedding space, while a DiT-based renderer synthesizes pixels conditioned on this plan, text features, and source VAE features for editing. The approach introduces Segment-Aware 3D Rotary Positional Embedding and chain-of-thought reasoning, achieving state‑of‑the‑art performance on diverse video benchmarks.
The paper introduces IG‑VLA, a vision‑language‑action framework that learns to imagine task‑relevant future scene evolution in a latent spatiotemporal space, guiding action prediction without generating full pixel‑level videos. It further compresses this future reasoning into a compact Scene Gist Token via Scene Gist Memory, enabling efficient inference. Experiments on LIBERO, LIBERO‑Plus, and VLABench show that IG‑VLA improves success rates by nearly 6% and speeds up inference up to 6.38× compared to strong baselines.
arXiv:2602.08277v3 Announce Type: replace-cross Abstract: The landscape of AI video generation is undergoing a pivotal shift: moving beyond general generation - which relies on exhaustive prompt-engi...
arXiv:2601.14056v2 Announce Type: replace-cross Abstract: Training robust visual surveillance models requires large-scale datasets with precise spatial annotations, yet collecting real surveillance d...
CameraEditor is a new framework that transforms camera-controlled image editing into a temporal sequence prediction problem. By using video diffusion models, it incorporates a geometric perception module and dynamic reference routing to create precise visual references through dynamic panorama cropping. The method also inserts intermediate transition frames to handle large perspective shifts, maintaining content identity and spatial coherence, and is evaluated on a dataset of 5,760 instances with a benchmark of 462 test cases, achieving state‑of‑the‑art performance.
arXiv:2601. 23286v4 Announce Type: replace-cross Abstract: While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift.
arXiv:2512. 17504v2 Announce Type: replace-cross Abstract: Recent advances in diffusion models have enabled impressive video editing capabilities, yet production-grade Video Object Insertion (VOI) remains challenging due to inadequate 4D scene understanding and a lack of proper optical interactions, such as shadows and reflections.
arXiv:2604. 14556v2 Announce Type: replace-cross Abstract: Video object insertion places a user-specified object in an existing dynamic scene.
arXiv:2512. 10359v1 Announce Type: cross Abstract: Video Question Answering (VideoQA) task serves as a critical playground for evaluating whether foundation models can effectively perceive, understand, and reason about dynamic real-world scenarios.
arXiv:2606. 11683v1 Announce Type: cross Abstract: Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory.
CounterVid introduces a scalable counterfactual video generation framework that creates videos differing only in actions or temporal structure while keeping scene context intact. The approach uses multimodal LLMs for action proposals and diffusion models for editing, producing a synthetic dataset of ~26k preference pairs for action recognition and sequence ordering. With the MixDPO optimization method, the authors demonstrate significant improvements in action recognition and temporal ordering on Qwen2.5‑VL and InternVL3 backbones, while maintaining overall video understanding.