Pith. sign in

REVIEW 9 cited by

RelightVid: Temporal-Consistent Diffusion Model for Video Relighting

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

RelightVid: Temporal-Consistent Diffusion Model for Video Relighting

classification cs.CV cs.AI
keywords relightingvideodiffusionimagemodelsrelightvidconsistencyhigh
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

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

  1. TokenLight: Precise Lighting Control in Images using Attribute Tokens

    cs.CV 2026-04 unverdicted novelty 7.0

    TokenLight encodes lighting attributes as tokens in a conditional image generation model trained mostly on synthetic data, enabling precise relighting control and implicit learning of light-scene interactions.

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

    cs.CV 2026-08 conditional novelty 6.0

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

  3. ID-V2V: Identity-Preserving Video Restylization

    cs.CV 2026-07 conditional novelty 6.0

    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.

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

    cs.CV 2026-06 conditional novelty 6.0

    An end-to-end diffusion model generates backgrounds, relights green-screen actors, and replaces or creates props in one pass, improving over cascaded inpainting plus relighting baselines in user preference and auto metrics.

  5. Relit-LiVE: Relight Video by Jointly Learning Environment Video

    cs.CV 2026-05 unverdicted novelty 6.0

    Relit-LiVE jointly predicts relit videos and viewpoint-aligned environment maps inside a single diffusion process to achieve physically consistent video relighting without camera pose input.

  6. Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion

    cs.CV 2026-04 unverdicted novelty 6.0

    Hybrid Domain Knowledge Fusion distills expertise from specialized models across synthetic, OLAT, and real datasets into a lightweight student model for state-of-the-art portrait relighting with 6x-240x faster inference.

  7. VibeFlow: Versatile Video Chroma-Lux Editing through Self-Supervised Learning

    cs.CV 2026-04 unverdicted novelty 6.0

    VibeFlow performs versatile video chroma-lux editing in zero-shot fashion by self-supervised disentanglement of structure and color-illumination cues inside pre-trained video models, plus residual velocity fields and ...

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

    cs.CV 2026-06 unverdicted novelty 5.0

    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...

  9. HarmoVid: Relightful Video Portrait Harmonization

    cs.CV 2026-05 unverdicted novelty 5.0

    HarmoVid trains a video diffusion model on deflickered paired data from real and synthetic videos using asymmetric alpha mask conditioning to produce temporally coherent relightful portrait harmonization.