Pith. sign in

REVIEW 9 cited by

Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.13840 v3 pith:M6CAAPZC submitted 2023-05-23 cs.CV cs.AIcs.LGcs.MM

classification cs.CVcs.AIcs.LGcs.MM
keywords generationmotionvideodiffusionvideoscontrollablemodelsprior
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advances in text-to-image (T2I) diffusion models have enabled impressive image generation capabilities guided by text prompts. However, extending these techniques to video generation remains challenging, with existing text-to-video (T2V) methods often struggling to produce high-quality and motion-consistent videos. In this work, we introduce Control-A-Video, a controllable T2V diffusion model that can generate videos conditioned on text prompts and reference control maps like edge and depth maps. To tackle video quality and motion consistency issues, we propose novel strategies to incorporate content prior and motion prior into the diffusion-based generation process. Specifically, we employ a first-frame condition scheme to transfer video generation from the image domain. Additionally, we introduce residual-based and optical flow-based noise initialization to infuse motion priors from reference videos, promoting relevance among frame latents for reduced flickering. Furthermore, we present a Spatio-Temporal Reward Feedback Learning (ST-ReFL) algorithm that optimizes the video diffusion model using multiple reward models for video quality and motion consistency, leading to superior outputs. Comprehensive experiments demonstrate that our framework generates higher-quality, more consistent videos compared to existing state-of-the-art methods in controllable text-to-video generation

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation

    cs.CV 2025-02 conditional novelty 7.0 of 10

    Users control a text-to-video model by arranging 3D bounding boxes and camera motion, and the system renders depth maps that steer the diffusion model to generate matching object and camera motion.

  2. LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion

    cs.CV 2026-03 accept novelty 6.0 of 10

    LatSearch improves video diffusion quality and efficiency by scoring intermediate latents with a trained reward model and performing reward-guided resampling plus final pruning.

  3. When Distillation Breaks Motion Control: Restoring Generative Trajectories for Fast Video Generators

    cs.CV 2025-06 conditional novelty 6.0 of 10

    MotionEcho adaptively re-injects teacher-model guidance into few-step distilled video generators so reference motion can be copied at test time without training.

  4. Interactive Video Generation via Domain Adaptation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A training-free method combines mask normalization and temporal intrinsic denoising to improve trajectory control and perceptual quality in text-to-video diffusion.

  5. EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance

    cs.CV 2025-05 conditional novelty 6.0 of 10

    EPiC trains a 30M-parameter visibility-aware ControlNet on mask-based anchor videos from 5,000 in-the-wild videos and 500 steps, reaching SOTA camera accuracy on RealEstate10K and MiraData.

  6. MotionPro: A Precise Motion Controller for Image-to-Video Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    MotionPro uses region-wise trajectories and a motion mask to control object and camera motion in image-to-video generation, reporting improved trajectory alignment over prior methods.

  7. An Exploratory Study on Multi-modal Generative AI in AR Storytelling

    cs.HC 2025-05 conditional novelty 6.0 of 10

    The paper maps how storytellers prefer to use AI-generated text, audio, images, videos, and 3D content to augment AR stories, based on a 223-video analysis and two user studies with 30 participants.

  8. Consistent and Editable: A Balanced Framework for Text-Guided Video Editing

    cs.CV 2026-07 conditional novelty 5.0 of 10

    EquiEdit balances temporal consistency and editability in diffusion-based text-guided video editing via a temporal Mamba module and spectral noise injection on initial latents.

  9. EndoControlMag: Robust Endoscopic Vascular Motion Magnification with Periodic Reference Resetting and Hierarchical Tissue-aware Dual-Mask Control

    eess.IV 2025-07 conditional novelty 4.0 of 10

    A training-free Lagrangian motion magnification framework with periodic reference resetting and tissue-aware dual-mask control improves vascular pulsation visibility in endoscopic surgery videos.

Pith tools