camera-control

WorldCast 通过 3D 点云引导与几何对齐记忆注意力（GAMA），实现大角度相机运动下角色视频生成的外观、几何与身份一致性，并提出大规模基准数据集 CLACT。

Holo4D is a video reshooting framework that uses reconstructed 3D trajectory scaffolds to guide a pretrained video diffusion model for novel-view video synthesis, preserving scene geometry and motion while generatively completing unseen regions without retraining the generator.

4LC 提出一种用于动态世界建模的 4D 潜空间缓存，通过复合视觉表示（VAE、DINO、V-JEPA、VGGT）和灵活的时空访问接口，高效复用静态与动态内容作为生成条件，支持相机控制、时间控制、新视角合成与长时生成等多项视频生成任务，且无需任务特定微调。

Using DeepSeek V4 Flash, the author reverse-engineered the DJI Pocket 3 protocol in half a day and built a custom CLI tool for shooting, previewing, and gimbal control, unifying computer-based control across multiple cameras and RGB lights.

HLA-WM提出一种训练免费的混合线性注意力框架，通过几何引导的检索与递归线性状态重组合来缓解GatedDeltaNet在长时视频世界模型中的远距离遗忘问题，在60秒基准上以12倍内存节省同时提升所有一致性与相机控制指标。

This paper introduces GEAR, a Geometry-Enabled Attention Routing framework that uses geometry as explicit token-level addresses for visual memory to enhance long-horizon camera-controlled video generation, achieving state-of-the-art results.

WorldCrafter is a video world model that learns a camera-queryable implicit 3D-aware memory for consistent and camera-controllable streaming scene exploration from a single image or text prompt.

AlayaVista is a camera-controllable streaming video world model that decouples panoramic scene evolution from perspective video synthesis, supported by the large-scale MUGEN dataset for high-fidelity interactive world modeling.

The paper presents World in World, a training-free interface that enables flexible camera and time control in frozen autoregressive video world models by using correspondence-guided queries and evidence-wise attention guidance.

FlashRender is a few-step generative rendering framework that accelerates video synthesis by aligning representations and using mean-flow objectives, achieving comparable quality to multi-step methods with significantly reduced sampling cost.

Atlas by World Labs is an omni world model that generates camera-controlled HD video from text, images, video, and 3D inputs, reconstructs scenes, and simulates space-time for robotics, available in early access.

World Labs introduces Atlas, a multimodal world model that can generate, reconstruct, and simulate 3D environments with camera control and spatial consistency.

This paper presents JoyAI-Echo-1.5, a unified audio-visual generation system for long-form video and interactive worlds, using cross-shot memory and geometry-aware control to maintain coherence and persistence.

SCoPE is a model from TencentARC that adds camera sightlines as positional coordinates to a pretrained video diffusion transformer, enabling camera trajectory control while preserving the image-to-video prior. The release includes a self-contained checkpoint for Wan2.2-I2V-A14B inference.

TopviewAI's Film Studio provides six controls for AI video generation, including performance direction, camera control, and 3D blocking, allowing filmmakers to direct shots rather than just prompt clips.

Wonder is a general-purpose video world model that enables real-time, camera-controllable world exploration from an image or conditional video. It introduces camera conditioning via dense coordinate fields, a sparse attention memory mechanism, and techniques to improve distillation, allowing minute-scale video generation at 16 FPS.

AlayaWorld is a full-stack, open-source video world model capable of generating 720p, 24 FPS streaming video with camera control, enabling dynamic scene creation.

Introduces ViewSuite, a benchmark with 6DoF camera control and ~165K tasks for evaluating VLMs' ability to plan camera moves. Finds a planning gap where models can track but not compose plans, and proposes View Graph Distillation (RL-Graph-SFT) to improve success from 2.5% to 47.8%.

Holo-World presents a unified controllable video world model that generates videos from a single image with explicit control over camera, object motion, and weather. It introduces a novel dataset and techniques to preserve scene structure while transferring to target weather states.

DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model that supports camera navigation, scene persistence, and promptable events across multiple domains, using novel techniques like E-PRoPE, causal forcing, and memory-conditioned scene persistence to achieve controllable long-horizon generation.