Pith. sign in

REVIEW 9 cited by

CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance

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 2503.10391 v1 pith:VOFFQUXK submitted 2025-03-13 cs.CV cs.AI

classification cs.CVcs.AI
keywords videogenerationsubjectimagesmulti-subjectpersonalizedtextambiguity
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Video generation has witnessed remarkable progress with the advent of deep generative models, particularly diffusion models. While existing methods excel in generating high-quality videos from text prompts or single images, personalized multi-subject video generation remains a largely unexplored challenge. This task involves synthesizing videos that incorporate multiple distinct subjects, each defined by separate reference images, while ensuring temporal and spatial consistency. Current approaches primarily rely on mapping subject images to keywords in text prompts, which introduces ambiguity and limits their ability to model subject relationships effectively. In this paper, we propose CINEMA, a novel framework for coherent multi-subject video generation by leveraging Multimodal Large Language Model (MLLM). Our approach eliminates the need for explicit correspondences between subject images and text entities, mitigating ambiguity and reducing annotation effort. By leveraging MLLM to interpret subject relationships, our method facilitates scalability, enabling the use of large and diverse datasets for training. Furthermore, our framework can be conditioned on varying numbers of subjects, offering greater flexibility in personalized content creation. Through extensive evaluations, we demonstrate that our approach significantly improves subject consistency, and overall video coherence, paving the way for advanced applications in storytelling, interactive media, and personalized video generation.

Discussion (0). Sign in 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. FlowMimic: Mask-free Visual Editing and Generation with Pixel-pair Warped Flow Field for Online Video Editing Data Generation and Modality Mimicry

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Video editing can be learned from image-edit pairs that are synthetically warped into videos, plus self-distillation losses that align image and video outputs.

  2. HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

    cs.CV 2026-07 conditional novelty 6.0 of 10

    HOMIE unifies inter- and intra-subject video personalization by injecting MLLM-derived relational features into DiT self-attention (GMG) and tagging tokens with modality/reference embeddings (MRE), reporting SOTA on a...

  3. Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Aura combines VLM meta-queries, T5-teacher alignment, subject-aware RoPE shifts, memory tokens, and a large AIGC-curated dataset to claim SOTA multi-element subject-to-video generation under OpenS2V-Eval Total score.

  4. RefAlign: Representation Alignment for Reference-to-Video Generation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Explicit training-time alignment of DiT reference features to a VFM (with pull/push loss) raises OpenS2V-Eval TotalScore over prior R2V methods with no inference cost.

  5. HOComp: Interaction-Aware Human-Object Composition

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A diffusion-transformer method that composes a foreground object into a human image with MLLM-chosen interaction regions, pose keypoint supervision, and appearance/background consistency losses, plus a new paired dataset.

  6. Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Phantom-Data provides around one million cross-context, identity-consistent reference-video pairs for subject-to-video generation, and training on it improves prompt following and visual quality.

  7. DreamActor-H1: High-Fidelity Human-Product Demonstration Video Generation via Motion-designed Diffusion Transformers

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A diffusion transformer model generates human-product demonstration videos from paired human and product images while preserving both identities through masked cross-attention and motion template guidance.

  8. AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    AnimeShooter provides hierarchical story and shot annotations plus reference images for 148K one-minute animation stories, and AnimeShooterGen trained on it shows improved cross-shot consistency.

  9. OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A benchmark and five-million-clip dataset for evaluating and training subject-to-video generation models, with three new metrics for subject consistency, naturalness, and text alignment.

Pith tools