Pith. sign in

REVIEW 7 cited by

Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

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 2501.03847 v2 pith:7L4FNR6R submitted 2025-01-07 cs.CV cs.AIcs.GR

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

Diffusion models have demonstrated impressive performance in generating high-quality videos from text prompts or images. However, precise control over the video generation process, such as camera manipulation or content editing, remains a significant challenge. Existing methods for controlled video generation are typically limited to a single control type, lacking the flexibility to handle diverse control demands. In this paper, we introduce Diffusion as Shader (DaS), a novel approach that supports multiple video control tasks within a unified architecture. Our key insight is that achieving versatile video control necessitates leveraging 3D control signals, as videos are fundamentally 2D renderings of dynamic 3D content. Unlike prior methods limited to 2D control signals, DaS leverages 3D tracking videos as control inputs, making the video diffusion process inherently 3D-aware. This innovation allows DaS to achieve a wide range of video controls by simply manipulating the 3D tracking videos. A further advantage of using 3D tracking videos is their ability to effectively link frames, significantly enhancing the temporal consistency of the generated videos. With just 3 days of fine-tuning on 8 H800 GPUs using less than 10k videos, DaS demonstrates strong control capabilities across diverse tasks, including mesh-to-video generation, camera control, motion transfer, and object manipulation.

Discussion (0). Sign in to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Video Models as Native 4D Renderers: World-Grounded Conditioning from Animated Mesh

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Tracking plus world-position maps in a neural G-buffer outperform depth as a geometric condition for reference-guided video diffusion rendering on a 68-clip synthetic benchmark.

  2. Motion4Motion: Motion Transfer Across Subjects at Inference

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Training-free motion transfer across species works by extracting source motion flows, matching semantic points, and injecting them into DiT self-attention via TransPE positional padding.

  3. PostCam: Camera-Controllable Novel-View Video Generation with Query-Shared Cross-Attention

    cs.CV 2025-11 conditional novelty 6.0 of 10

    PostCam generates new videos from a reference video along user-specified camera trajectories using a query-shared cross-attention that fuses pose data and rendered frames, improving control precision and detail preservation.

  4. ANYPORTAL: Zero-Shot Consistent Video Background Replacement

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A training-free video background replacement pipeline that keeps the foreground pixel-consistent by projecting refined latents through a deterministic reparameterization.

  5. O-DisCo-Edit: Object Distortion Control for Unified Realistic Video Editing

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A video editor trained on randomly distorted objects, then steered by adaptive noise at inference, is claimed to surpass dedicated and unified editors across eight tasks with far less training.

  6. Discovering and using Spelke segments

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SpelkeNet, a self-supervised video world model, discovers Spelke segments in static images by aggregating motion correlations across imagined pokes.

  7. SpatialTrackerV2: 3D Point Tracking Made Easy

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A single feed-forward model jointly estimates video depth, camera poses, and 3D point trajectories from monocular video, setting a new state of the art on TAPVid-3D.

Pith tools