Pith. sign in

REVIEW 6 cited by

RelightVid: Temporal-Consistent Diffusion Model for Video Relighting

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2501.16330 v1 pith:BXHMNJC6 submitted 2025-01-27 cs.CV cs.AI

Ye Fang , Zeyi Sun , Shangzhan Zhang , Tong Wu , Yinghao Xu , Pan Zhang , Jiaqi Wang , Gordon Wetzstein
show 1 more author
Dahua Lin
This is my paper · ORCID
classification cs.CVcs.AI
keywords relightingvideodiffusionimagemodelsrelightvidconsistencyhigh
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models have demonstrated remarkable success in image generation and editing, with recent advancements enabling albedo-preserving image relighting. However, applying these models to video relighting remains challenging due to the lack of paired video relighting datasets and the high demands for output fidelity and temporal consistency, further complicated by the inherent randomness of diffusion models. To address these challenges, we introduce RelightVid, a flexible framework for video relighting that can accept background video, text prompts, or environment maps as relighting conditions. Trained on in-the-wild videos with carefully designed illumination augmentations and rendered videos under extreme dynamic lighting, RelightVid achieves arbitrary video relighting with high temporal consistency without intrinsic decomposition while preserving the illumination priors of its image backbone.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. LiveLight: Real-time Streaming Video Relighting with Interactive Control

    cs.CV 2026-08 conditional novelty 6.0 of 10

    A diffusion-based system performs real-time, interactive video relighting by injecting multi-plane light irradiance conditions and streaming latent chunks.

  2. ID-V2V: Identity-Preserving Video Restylization

    cs.CV 2026-07 conditional novelty 6.0 of 10

    ID-V2V restyles video by conditioning a diffusion model on edited keyframes, depth, relit faces, and face normals, so scene edits propagate while facial identity and performance are preserved.

  3. Cinematic Compositing Using Character-Environment-Harmonized Video Generation Models

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    End-to-end video diffusion framework with tri-mask guidance and RGB-D denoising for joint modeling of character-to-environment physical interactions and environment-to-character lighting harmonization in cinematic com...

  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. IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation

    cs.CV 2025-06 reject novelty 6.0 of 10

    A diffusion video model that jointly uses HDR lighting, relit frames, and 3D point tracks to relight videos from text prompts.

  6. VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation

    cs.CV 2025-02 conditional novelty 6.0 of 10

    VidCRAFT3 is a single image-to-video diffusion system that accepts camera, object, and lighting direction controls separately or jointly, trained in three stages with a new synthetic lighting dataset.

Pith tools