Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion

• URL: http://arxiv.org/abs/2603.15614v1
• Date: Mon, 16 Mar 2026 17:59:05 GMT
• Title: Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion
• Abstract summary: Tri-Prompting is a unified framework that integrates scene composition, multi-view subject consistency, and motion control.<n>Results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.
• Score: 69.64308172688368
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent video diffusion models have made remarkable strides in visual quality, yet precise, fine-grained control remains a key bottleneck that limits practical customizability for content creation. For AI video creators, three forms of control are crucial: (i) scene composition, (ii) multi-view consistent subject customization, and (iii) camera-pose or object-motion adjustment. Existing methods typically handle these dimensions in isolation, with limited support for multi-view subject synthesis and identity preservation under arbitrary pose changes. This lack of a unified architecture makes it difficult to support versatile, jointly controllable video. We introduce Tri-Prompting, a unified framework and two-stage training paradigm that integrates scene composition, multi-view subject consistency, and motion control. Our approach leverages a dual-condition motion module driven by 3D tracking points for background scenes and downsampled RGB cues for foreground subjects. To ensure a balance between controllability and visual realism, we further propose an inference ControlNet scale schedule. Tri-Prompting supports novel workflows, including 3D-aware subject insertion into any scenes and manipulation of existing subjects in an image. Experimental results demonstrate that Tri-Prompting significantly outperforms specialized baselines such as Phantom and DaS in multi-view subject identity, 3D consistency, and motion accuracy.

Related papers

• An Evaluation Framework for Generating Multi-View Images of a Person in a Scene [8.826327162415287]
  A primary bottleneck in training foundation models to execute free-form, promptable camera angle changes is the lack of specialized training data.<n>We propose the Head Scene Rotation Difference (HSRD) metric to quantitatively evaluate camera movements around a person.<n>HSRD provides the pipeline necessary to evaluate 3D spatial parallax for a person in a scene, paving the way to reliably construct high-quality multi-view synthetic datasets.
  arXiv  Detail & Related papers  (2026-09-04T01:02:12Z)
• CameraAnything: Refilming Videos with Arbitrary Camera Control [104.67227614978822]
  We introduce CameraAnything, the first unified framework for camera controlled video editing.<n>It enables joint control of both intrinsic and extrinsic camera parameters.<n>With a tailored training strategy, CameraAnything enables expressive video reshooting with arbitrary viewpoint control, focal length adjustment, resolution adaptation, and multi-shot transitions within a single generation process.
  arXiv  Detail & Related papers  (2026-07-27T15:55:08Z)
• View-Consistent 3D Scene Editing via Dual-Path Structural Correspondense and Semantic Continuity [11.663455227298122]
  Cross-view inconsistency remains a major bottleneck in text-driven 3D scene editing.<n>We recast multi-view consistent 3D editing from a distributional perspective.<n>We introduce a dual-path consistency mechanism consisting of projection-guided structural guidance and patch-level semantic propagation.
  arXiv  Detail & Related papers  (2026-04-20T04:47:15Z)
• NavCrafter: Exploring 3D Scenes from a Single Image [25.95468802469574]
  NavCrafter is a framework that explores 3D scenes from a single image by synthesizing novel-view video sequences.<n>We propose a multi-stage camera control mechanism that conditions diffusion models with diverse trajectories.<n>Experiments demonstrate that NavCrafter achieves state-of-the-art novel-view synthesis under large viewpoint shifts.
  arXiv  Detail & Related papers  (2026-04-03T07:50:39Z)
• MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model [83.12400850233034]
  Human-Object Interaction (HOI) video reenactment with realistic motion remains a frontier in digital human creation.<n>We propose MVHOI, a two-stage HOI video reenactment framework that bridges multi-view reference conditions and video foundation models.<n>Our framework shows superior performance in generating long-duration HOI videos with intricate object manipulations.
  arXiv  Detail & Related papers  (2026-03-16T00:43:38Z)
• OpenSubject: Leveraging Video-Derived Identity and Diversity Priors for Subject-driven Image Generation and Manipulation [53.33087515226418]
  We introduce OpenSubject, a video-derived large-scale corpus with 2.5M samples and 4.35M images for subject-driven generation and manipulation.<n>The dataset is built with a four-stage pipeline that exploits cross-frame identity priors.<n>In addition, we introduce a benchmark covering subject-driven generation and manipulation, and then evaluate identity fidelity, prompt adherence, manipulation consistency, and background consistency with a VLM judge.
  arXiv  Detail & Related papers  (2025-12-09T06:49:33Z)
• Free-Form Motion Control: Controlling the 6D Poses of Camera and Objects in Video Generation [78.65431951506152]
  We introduce a Synthetic dataset for Free-Form Motion Control (SynFMC)<n>The proposed SynFMC dataset includes diverse object and environment categories.<n>It covers various motion patterns according to specific rules, simulating common and complex real-world scenarios.<n>The complete 6D pose information facilitates models learning to disentangle the motion effects from objects and the camera in a video.
  arXiv  Detail & Related papers  (2025-01-02T18:59:45Z)
• Shape of Motion: 4D Reconstruction from a Single Video [42.42669078777769]
  We introduce a method for reconstructing generic dynamic scenes, featuring explicit, persistent 3D motion trajectories in the world coordinate frame.<n>First, we exploit the low-dimensional structure of 3D motion by representing scene motion with a compact set of SE(3) motion bases.<n>Second, we take advantage of off-the-shelf data-driven priors such as monocular depth maps and long-range 2D tracks, and devise a method to effectively consolidate these noisy supervisory signals.
  arXiv  Detail & Related papers  (2024-07-18T17:59:08Z)
• Decoupling Dynamic Monocular Videos for Dynamic View Synthesis [50.93409250217699]
  We tackle the challenge of dynamic view synthesis from dynamic monocular videos in an unsupervised fashion. Specifically, we decouple the motion of the dynamic objects into object motion and camera motion, respectively regularized by proposed unsupervised surface consistency and patch-based multi-view constraints.
  arXiv  Detail & Related papers  (2023-04-04T11:25:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.