LoGo introduces a hybrid reward system combining global and spatially localized rewards to improve 3D consistency in camera-controlled video generation. The local reward offers fine-grained credit assignment, reducing object shifts and artifacts, while the global reward maintains camera following and overall video quality. Evaluations on DL3DV and the new TrajectoryBench benchmark demonstrate LoGo’s advantage over existing post-training techniques.
arXiv:2610.14293v1 Announce Type: cross Abstract: Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches a...
WorldAlign introduces a decoupled 4D reward framework for improving world consistency in generated videos. It separates static regions from dynamic subjects, aligning each with a suitable world prior—geometric priors for static geometry and a vision‑language model for dynamic subjects—using masked reprojection and a VLM‑as‑a‑judge reward. The method enhances both static and dynamic consistency in pretrained image‑to‑video generators without relying on human preference data.
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces artifacts when input views are sparse or target v...
arXiv:2604. 14556v2 Announce Type: replace-cross Abstract: Video object insertion places a user-specified object in an existing dynamic scene.
DynaTokens introduces lightweight, scene‑specific tokens that enable camera‑controlled video models to learn and generate dynamic scene motion while keeping the base model frozen. By leveraging cross‑attention, the tokens are trained from a few example trajectories, allowing the model to handle both camera‑induced motion and localized object dynamics. Experiments on VBench2 and WorldScore show that DynaTokens outperforms LoRA, block finetuning, and other trainable‑layer baselines in balancing dynamics and camera control.
arXiv:2610.17434v1 Announce Type: cross Abstract: Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on vis...
LIFT is a unified image‑to‑video generation framework that adds Layout‑In‑Future control, letting users specify what should appear and where in a future view. It addresses the limitation of existing camera controls and text prompts by using the last‑frame layout as an explicit signal for the desired future scene, especially under large viewpoint changes. To handle sparse layout guidance, LIFT employs on‑policy self‑distillation to transfer knowledge from a dense‑layout teacher to a last‑frame‑layout student, and introduces the LIFT‑Vista dataset with large viewpoint changes and consistent layout annotations. Experiments demonstrate that LIFT improves video quality, future‑layout controllability, and camera controllability compared to other methods.
Orbia is a new benchmark that systematically evaluates 3D consistency in interactive video world models. It organizes evaluation into three dimensions—input preservation, generated‑content persistence, and 3D self‑consistency—using controlled exploration and revisit protocols. The benchmark covers 720 instances across indoor and outdoor scenes and tests 27 different models, providing a comprehensive framework for diagnosing and improving 3D consistency.
World in World introduces a training‑free, inference‑time interface that transforms diverse control signals—such as source‑video observations, target‑view projections, geometry renderings, and retrieved states—into camera‑ and time‑labelled visual states. These states are processed by a frozen causal video model’s self‑attention, enabling tasks like camera‑controlled rerendering, long‑horizon revisiting, and human‑motion transfer without additional training. The method employs a correspondence router and evidence‑wise attention to align token identities and regulate auxiliary channel contributions during a single denoising pass.
DiffWAM is a geometry‑conditioned navigation world‑action model that transforms predictive features from a frozen video foundation model into continuous camera trajectories, eliminating the need for future‑video synthesis and multi‑frame reconstruction during deployment. Its Grid‑Motion module preserves spatial‑temporal motion associations, while Latent2Pose grounds them with first‑frame geometry to recover metrically meaningful 3D motion. The system, complemented by FastDreamer for asynchronous trajectory handoff, achieves a trajectory RMSE of 0.3492 m and a 74.40 % endpoint success rate on the DiffWAM‑1000 benchmark, with real‑world tests showing complex UAV behaviors and an onboard implementation reaching 1.08 s latency on NVIDIA Jetson AGX Thor.
Generative Cinematographer (GenCine) lifts a single image into an editable 3D scene scaffold, allowing artists to jointly author camera paths and foreground motion using local 3D motion handles. The system projects these controls into guidance maps that encode handle positions and colors across frames, enabling a pretrained video model to follow camera-relative, piecewise-rigid motion without physics simulation. Training recovers controls from real videos and synthetic ground-truth geometry, and experiments demonstrate consistent camera-relative motion, improved geometric consistency, and strong controllability across diverse real-world scenes.